Input Dataset Research Articles

Investigating groundwater potential in northeastern basement complexes: A Pulka case study using geospatial and geo-electrical techniques

Groundwater is a crucial resource for communities and plays a significant role in the economy, especially in regions where surface water sources are limited or unreliable. Nigerian Northeastern basement complexes are unique geologic formations with specific hydrological characteristics that impact groundwater availability and quality. However, there is a lack of comprehensive information on groundwater potential in these areas, hindering effective resource management. To address this gap, this study focuses on the application of geospatial and electrical techniques to map and assess groundwater potential in Pulka, a northeastern basement complex in Nigeria. This research used geospatial methodology to delineate groundwater-prospective areas in Pulka, Northern Nigeria, with the aid of a VES technique that was integrated with the Schlumberger electrode configuration, the Shuttle Radar Topography Mission (SRTM), which were used as input datasets. Lineament and drainage density, lithology and slope, land use and land cover, and thematic maps were created as GIS input rasters. The value estimates were allotted based on a pair-wise examination of elements that appeared to be important in groundwater accumulation, retention, and transportation. The Analytical Hierarchy Process (AHP) was used in GIS software to incorporate five maps of components impacting the suitability of groundwater and movement using weighted layering. The hydraulic conductivity and longitudinal conductance of Pulka are greatest towards the west, with maximum values of 0.0665 m/day and 1.75 S, respectively. Transverse resistance and transmissivity are greatest in the eastern section of Pulka, with maximum values of 48.29 m2/day and 9000 m, respectively. Based on our research using SRTM, the most important elements for groundwater potential were soil type, which represented 43%; lineament density, which represented 33%; slope, with 13%; drainage density, with 7%; and land use and land cover, which accounted for the least (around 4% of overall contributions). Pulka has enormous groundwater development potential for sustainable and profitable extractions, according to analysis based on geospatial and geo-electrical techniques.

Predicting the efficacy of immune checkpoint inhibitors monotherapy in advanced non-small cell lung cancer: a machine learning method based on multidimensional data.

Immunotherapy has improved the prognosis of patients with advanced non-small cell lung cancer (NSCLC), but only a small subset of patients achieved clinical benefit. The purpose of our study was to integrate multidimensional data using a machine learning method to predict the therapeutic efficacy of immune checkpoint inhibitors (ICIs) monotherapy in patients with advanced NSCLC. We retrospectively enrolled 112 patients with stage IIIB-IV NSCLC receiving ICIs monotherapy. The random forest (RF) algorithm was used to establish efficacy prediction models based on five different input datasets, including precontrast computed tomography (CT) radiomic data, postcontrast CT radiomic data, a combination of the two CT radiomic data, clinical data, and a combination of radiomic and clinical data. The 5-fold cross-validation was used to train and test the random forest classifier. The performance of the models was assessed according to the area under the curve (AUC) in the receiver operating characteristic curve. Survival analysis was performed to determine the difference in progression-free survival (PFS) between the two groups with the prediction label generated by the combined model. The radiomic model based on the combination of precontrast and postcontrast CT radiomic features and the clinical model produced an AUC of 0.92±0.04 and 0.89±0.03, respectively. By integrating radiomic and clinical features together, the combined model had the best performance with an AUC of 0.94±0.02. The survival analysis showed that the two groups had significantly different PFS times (p<0.0001). The baseline multidimensional data including CT radiomic and multiple clinical features were valuable in predicting the efficacy of ICIs monotherapy in patients with advanced NSCLC.

An Ensemble Multi-Layered Sentiment Analysis Model (EMLSA) for Classifying the Complex Datasets

Sentiment analysis is one domain that analyzes the feelings and emotions of the users based on their text messages. Sentiment analysis of short messages, reviews in online social media (OSM), and social networking sites (SNS) messages gives the analysis of given text data. Processing short text and SNS messages is a very tedious task because of the restricted detailed information generally contained. Solving this issue requires advanced techniques that are combined to give accurate results. This paper developed an Ensemble Multi-Layered Sentiment Analysis Model (EMLSA) that exploits the trust-based sentiment analysis on various real-time datasets. EMLA is the combined approach with VADER (Valence Aware Dictionary and sEntiment Reasoned) and Recurrent Neural Networks (RNNs). VADER is the lexicon and rule-based sentiment analysis model that predicts the sentiments extracted from input datasets and it is used for training. The feature extraction technique is term-frequency and inverse document frequency. Word-Level Embeddings (WLE) and Character-Level Embeddings (CLE) are the two models that increase the short text and single-word analysis. The proposed model was applied to four real-time datasets: Amazon, eBay, Trip-advisor, and IMDB Movie Reviews. The performance is analyzed using various parameters such as sensitivity, specificity, precision, accuracy, and F1-score.

Forecasting of garlic price based on DA-RNN using attention weight of temporal fusion transformers.

Garlic is a major condiment vegetable grown in South Korea. The price of garlic has a great impact on Korean society and the economy, which requires price stabilization through preemptive supply and demand management. Therefore, the government attempts to keep the price adjusted according to the predicted production cost. However, classic statistical models or well-known deep learning models have lower forecast accuracy when the number of input factors increases. The aforementioned issue could make analysis approaches and their implementation difficult, and the government would confront failure in proper supply and demand management. To solve this problem, we propose a new hybrid deep-learning approach that employs well-known attention models. Recent attention models have achieved outstanding performance in time-series dataset forecasting. However, when input datasets contain dozens or hundreds of variables, the forecasting performance cannot be guaranteed because the prediction accuracy decreases. In this study, a novel approach utilizing attention weights for forecasting prices is introduced. Experience shows that forecasting accuracy can be improved using the proposed model, which deals with different variables related to garlic prices, such as atmospheric conditions, logistics processes, and environmental circumstances. The proposed approach and its model contribute to forecasting outputs for different research domains by using a variety of attention weight models.

Applied machine learning for prediction of waste plastic pyrolysis towards valuable fuel and chemicals production

Pyrolysis is a suitable conversion technology to address the severe ecological and environmental hurdles caused by waste plastics' ineffective pre- and/or post-user management and massive landfilling. By using machine learning (ML) algorithms, the present study developed models for predicting the products of continuous and non-catalytically processes for the pyrolysis of waste plastics. Along with different input datasets, four algorithms, including decision tree (DT), artificial neuron network (ANN), support vector machine (SVM), and Gaussian process (GP), were compared to select input variables for the most accurate models. Among these algorithms, the DT model exhibited generalisable and satisfactory accuracy (R2 > 0.99) with training data. The dataset with the elemental composition of waste plastics achieved better accuracy than that with the plastic-type for predicting liquid yields. These observations allow the predictions by the data from ultimate analysis when inaccessible to the plastic-type data in unknown plastic wastes. Besides, the combination of ultimate analysis input and the DT model also achieved excellent accuracy in liquid and gas composition predictions.

An Ensemble Learning Approach For Task Failure Prediction In Cloud Data Centers

Due to cloud computing’s extensive use and diverse nature, they experience failures in terms of software, service, and platform, which lead to the failure of task execution, resource waste and performance deterioration. Most studies focused on failure prediction resulted in lower prediction accuracies due to limited attributes and a single prediction model. Hence, in this paper, an efficient ensemble model for task failure prediction is put forth. Initially, the input dataset is collected and pre-processed. In pre-processing, the dataset is cleaned up of all null values. Then, the dimensionality of the pre-processed dataset is reduced by using the PCA algorithm. Thus, the reconstructed dataset is split into training and testing sets to train failure prediction models. The proposed model employs an ensemble learning approach based on different ML and DL algorithms. Then, a comparative study is performed, and the results show that task failure in the cloud system can be effectively predicted using the proposed ensemble method.

Machine learning and IoT-based garbage detection system for smart cities

Today, detecting waste, collecting it, processing it, and getting rid of it are among the most significant environmental issues in developing and undeveloped counties. It has been observed that a large amount of garbage remains strewn on the roadside. This study presented a garbage detection technology such as machine learning and gadgets connected to the Internet of Things (IoT), such as an IP-enabled CCTV camera, to take pictures and send them to the city’s main server. The input images are transformed into a two-dimension array of integers using Python modules and divided into the garbage and no garbage classes. There is an 80:20 split between the training and testing datasets from the input dataset. Preprocessed images are then utilised as inputs for a wide range of machine learning and neural network models for classification; these include K-Nearest Neighbour (KNN), Logistic Regression (LR), Naive Bayes (NB), and Support Vector Machine (SVM). The test data sets are applied, and a confusion matrix is formed for all models to analyse the efficiency and performance of the trained models. Results from the confusion matrix are contrasted with those from the area under the Receiver characteristics operating curve (AUC). As a result, the ConvNet model is best suited for classifying garbage or no garbage present in open space, and the LR model proposed best suits the garbage detection problem. The proposed models are best suitable for improving the efficiency of existing garbage identification systems and developing a new system for smart cities.

Impact of PolSAR Pre-Processing and Balancing Methods on Complex-Valued Neural Networks Segmentation Tasks

In this paper, we investigated the semantic segmentation of (polSAR) using (CVNN). Although the coherency matrix is more widely used as the input of CVNN, the Pauli vector has recently been shown to be a valid alternative. We exhaustively compare both methods for six model architectures, three complex-valued, and their respective real-equivalent models. We are comparing, therefore, not only the input representation impact but also the complex- against the real-valued models. We then argue that the dataset splitting produces a high correlation between training and validation sets, saturating the task and thus achieving very high performance. We, therefore, use a different data pre-processing technique designed to reduce this effect and reproduce the results with the same configurations as before (input representation and model architectures). After seeing that the performance per class is highly different according to class occurrences, we propose two methods for reducing this gap and performing the results for all input representations, models, and dataset pre-processing.

High Performance Time Series Anomaly Detection Using Brain Inspired Cortical Coding Method

Accurate and automated anomaly detection in time series data sets has an increasingly important role in a wide range of applications. Inspired by coding in the cortical networks of the brain, here we introduce a novel approach for high performance real-time anomaly detection. Cortical coding method is adaptive and dynamic, consisting of self-organized networks. In the cortical coding network introduced herein, the morphological structuring is driven by a brain inspired feature extraction strategy that aims the minimization of the signal energy dissipation while increasing the information entropy of the system. We combine the cortical coding network with transform coding and multi resolution analysis for anomaly detection. As we demonstrate here, the new coding methodology provides high computational efficiency in addition to scalability with respect to target accuracy compared to the traditional clustering algorithms. A wide variety of data sets are used to demonstrate time series anomaly detection performance. In a preliminary work presented here, we detected 77.6% of the present anomalies correctly, using the same hyperparameters for every stage of the method. The results are compared with several clustering algorithms such as K-means and its variants mini-batch K-means, sequential K-means and finally with hierarchical agglomerative clustering. Additionally, the performance of all the clustering methods are compared by memorizing all input data set without performing any clustering. The cortical coding method has shown the best performance compared to the other methods. From the results achieved so far, it appears that there is still a significant room for improvement of the success rate by, specifically, performing hyperparameter and filter optimization according to the characteristics of data sets and using a more advanced fusion model at the output layer. Low time and space complexity, high generalization performance, suitability to real-time anomaly detection, and in-memory processing compatibility are distinct advantages of the cortical coding method in a variety of anomaly detection problems, such as predictive maintenance, cybersecurity, telemedicine, risk management, and transportation safety.

Constructing a Meta-Learner for Unsupervised Anomaly Detection

Unsupervised anomaly detection (AD) is critical for a wide range of practical applications, from network security to health and medical tools. Due to the diversity of problems, no single algorithm has been found to be superior for all AD tasks. Choosing an algorithm, otherwise known as the Algorithm Selection Problem (ASP), has been extensively examined in supervised classification problems, through the use of meta-learning and AutoML, however, it has received little attention in unsupervised AD tasks. This research proposes a new meta-learning approach that identifies an appropriate unsupervised AD algorithm given a set of meta-features generated from the unlabelled input dataset. The performance of the proposed meta-learner is superior to the current state of the art solution. In addition, a mixed model statistical analysis has been conducted to examine the impact of the meta-learner components: the meta-model, meta-features, and the base set of AD algorithms, on the overall performance of the meta-learner. The analysis was conducted using more than 10,000 datasets, which is significantly larger than previous studies. Results indicate that a relatively small number of meta-features can be used to identify an appropriate AD algorithm, but the choice of a meta-model in the meta-learner has a considerable impact.

Downscaling shallow water simulations using artificial neural networks and boosted trees

We present the application of two statistical artificial intelligence tools for multi-scale shallow water simulations. Artificial neural networks (ANNs) and boosted trees (BTs) are used to model the relationship between low-resolution (LR) and high-resolution (HR) information derived from simulations provided in the learning phase. The two statistical models are analyzed (and compared) through hyper-parameters such as the number of epochs and the network structure for ANNs, and the learning rate, tree depth and number for BTs. This analysis is performed through 4 numerical experiments the input datasets of which (for the learning, validation and test phases) are varied through the boundary conditions of the flow numerical simulation.The performance of the ANNs is remarkably consistent, regardless of the choice made for the training/validation/testing set. The performance improves with the number of epochs and the number of neurons. For a given number of neurons, a single-layer structure performs better than multi-layer structures. BTs perform significantly better than ANNs in 2 experiments, with an error 10 to 100 times lower and a computational cost 5 to 10 times larger). However, when the validation datasets differ from the training datasets, the performance of BTs performance is strongly degraded, with a modelling error more than one order of magnitude larger than that of ANNs.Used in conjunction with upscaled flood models such as porosity models, these techniques appear as a promising operational alternative to direct flood hazard assessment from HR flow simulations.

VGG-COVIDNet: A Novel model for COVID detection from X-Ray and CT Scan images

In this research work, a new deep learning model named VGG-COVIDNet has been proposed which can classify COVID-19 cases from normal cases over X-Rays and CT scan images of lungs. Medical practitioners use the X-Rays and CT scan images of lungs to identify whether a person is infected from COVID or not. In present times, it is very important to give real time COVID prediction with high reliability of results. Deep learning models equipped with machine learning support have been found very influential in accurate prediction of COVID or Non-COVID cases in real time. However, there are some limitations associated with the performance of these model which are model size, achieving good balance of model size and accuracy, and making a single model fitting well for both X-Ray and CT Scan image datasets. Keeping in mind these performance constraints, this new model (VGG-COVIDNet) has been proposed for real time prediction of COVID cases with good balance of model size and accuracy working well for both type of datasets (CT Scan and X-Ray). In order to control model size, an improved version of VGG-16 architecture has been proposed which contains only 13 convolutional layers and 5 fully connected layers. Multiple dropout layers have been added in the proposed architecture which can drop some percentage of features and applies random transformations to decrease the model over-fitting issue. Keeping in mind the primary goal to increase the model accuracy the proposed model has been trained on different datasets with ReLU activation function which is one of the best non-linear activation functions. Four different capacity datasets with CT scan and X-Ray images have been used to validate the performance of proposed model. The proposed model gives an overall accuracy of more than 90% on both types of input datasets i.e. X-Ray and CT Scan.

Открытые источники данных для моделирования ареалов: информационные системы о биоразнообразии и наборы пространственных данных условий среды

Открытые источники данных для моделирования ареалов: информационные системы о биоразнообразии и наборы пространственных данных условий среды

Connections between Deep Equilibrium and Sparse Representation Models with Application to Hyperspectral Image Denoising.

In this study, the problem of computing a sparse representation of multi-dimensional visual data is considered. In general, such data e.g., hyperspectral images, color images or video data consists of signals that exhibit strong local dependencies. A new computationally efficient sparse coding optimization problem is derived by employing regularization terms that are adapted to the properties of the signals of interest. Exploiting the merits of the learnable regularization techniques, a neural network is employed to act as structure prior and reveal the underlying signal dependencies. To solve the optimization problem Deep unrolling and Deep equilibrium based algorithms are developed, forming highly interpretable and concise deep-learning-based architectures, that process the input dataset in a block-by-block fashion. Extensive simulation results, in the context of hyperspectral image denoising, are provided, which demonstrate that the proposed algorithms outperform significantly other sparse coding approaches and exhibit superior performance against recent state-of-the-art deep-learning-based denoising models. In a wider perspective, our work provides a unique bridge between a classic approach, that is the sparse representation theory, and modern representation tools that are based on deep learning modeling.

Open source modeling for planing sustainable power development in resource-rich economies: case study for Kazakhstan

Power sector decarbonization is currently seen as a necessary condition of sustainable development in the modern world. options of resources-rich economies. Energy modeling is an effective measure to elaborate long-term decarbonisation policies. However, energy modeling evidence available for resources-rich economies remain up to the date limited, especially in part of realistic representation of the power system operation. We apply open code and open data approach to fill this gap considering a case study for Kazakhstan power system. The modeling input datasets have been validated against independent data sources with a satisfactory result. The simulation outputs are plausible both in terms reproducing the main features of the “pragmatic” scenario and in providing useful insights for the implementation of net-zero pathways. Renewable energy sources have been found to be economically viable even under the considered “pragmatic” scenario with quite conservative assumptions. Existing coal generation has been shown to dominate the investments costs hampering implementation of renewable power. A role of the power interconnection has been demonstrated for an economically optimal generation mix and a level of marginal electricity costs across the country. The results are intended to support energy transition implementation in the resources-rich economies under realistic technological assumptions.

The sensitivity kernel perspective on GRACE mass change estimates

Mass change inferences from GRACE and GRACE-FO typically involve, first, the preparation of spherical harmonic (SH) datasets on global gravity field changes and, second, their subsequent analysis that leads to mass change estimates. This study addresses the second step, which builds on SH input datasets that comprise the monthly gravity field solutions as well as amendments to low-degree components and subtraction or re-addition of certain modeled geophysical signals. A variety of methods have been developed to estimate mass changes from SH input datasets. It remains a challenge to assess and compare different methods adopted by different studies and to understand the mechanisms by which their results differ. Methods are often distinguished as belonging to either the inverse or direct approach. In the inverse approach, mass changes are estimated using a set of predefined spatial patterns. In the direct approach, surface mass density variations are integrated by using a predefined weight function, or sensitivity kernel. In this paper, we recall that sensitivity kernels are inherent not only to the direct approach. They are also inherent and may be made explicit, for inverse approaches. We prove that certain implementations of the direct and inverse approach have identical sensitivity kernels, and are therefore equivalent, under the condition that they rigorously incorporate the same signal and error covariance information. We present sensitivity kernels for the example of four different methods to estimate Greenland Ice Sheet mass changes. We discuss the sensitivity kernels in relation to the underlying differences in the methods. We propose to use sensitivity kernels as a means of communicating, assessing and comparing methods of mass change estimates. Once the sensitivity kernels associated to a method are made explicit, any user can readily investigate the method in terms of leakage effects, error propagation from the input SH datasets, or effects of the choice of the SH input datasets.

Adaptive Deep Learning Model for Software Bug Detection and Classification

Software is unavoidable in software development and maintenance. In literature, many methods are discussed which fails to achieve efficient software bug detection and classification. In this paper, efficient Adaptive Deep Learning Model (ADLM) is developed for automatic duplicate bug report detection and classification process. The proposed ADLM is a combination of Conditional Random Fields decoding with Long Short-Term Memory (CRF-LSTM) and Dingo Optimizer (DO). In the CRF, the DO can be consumed to choose the efficient weight value in network. The proposed automatic bug report detection is proceeding with three stages like pre-processing, feature extraction in addition bug detection with classification. Initially, the bug report input dataset is gathered from the online source system. In the pre-processing phase, the unwanted information from the input data are removed by using cleaning text, convert data types and null value replacement. The pre-processed data is sent into the feature extraction phase. In the feature extraction phase, the four types of feature extraction method are utilized such as contextual, categorical, temporal and textual. Finally, the features are sent to the proposed ADLM for automatic duplication bug report detection and classification. The proposed methodology is proceeding with two phases such as training and testing phases. Based on the working process, the bugs are detected and classified from the input data. The projected technique is assessed by analyzing performance metrics such as accuracy, precision, Recall, F_Measure and kappa.

A Feature Learning-Based Model for Analyzing Students’ Performance in Supportive Learning

Supportive learning plays a substantial role in providing a quality education system. The evaluation of students’ performance impacts their deeper insight into the subject knowledge. Specifically, it is essential to maintain the baseline foundation for building a broader understanding of their careers. This research concentrates on establishing the students’ knowledge relationship even in reduced samples. Here, Synthetic Minority Oversampling TEchnique (SMOTE) technique is used for pre-processing the missing value in the provided input dataset to enhance the prediction accuracy. When the initial processing is not done substantially, it leads to misleading prediction accuracy. This research concentrates on modelling an efficient classifier model to predict students’ performance. Generally, the online available student dataset comprises a lesser amount of sample, and k-fold cross-validation is performed to balance the dataset. Then, the relationship among the students’ performance (features) is measured using the auto-encoder. The stacked Long Short Term Memory () is used to learn the previous feedback connection. The stacked model handles the provided data and the data sequence for understanding the long-term dependencies. The simulation is done in the MATLAB 2020a environment, and the proposed model shows a better trade-off than the existing approaches. Some evaluation metrics like prediction accuracy, sensitivity, specificity, AUROC, F1-score and recall are evaluated using the proposed model. The performance of the model is compared with existing approaches. The proposed model gives 89% accuracy, 83% precision, 86% recall, and 87% F-score. The proposed model outperforms the existing systems in terms of the earlier metrics.

Deep learning based phishing website identification system using CNN-LSTM classifier

The term phishing refers to an attack that pretends to be the website of a large corporation, typically one dealing with money, such as a bank or other financial institution or an online retailer. Its primary objective is to acquire personally identifiable information from users, such as their social security numbers, credit card information, and passwords. Due to the rise of phishing attacks, various techniques have been developed in order to combat these threats. One of these is deep learning algorithms, which are capable of learning and analyzing massive datasets. Due to their capabilities, these algorithms are very useful in identifying and preventing phishing attacks. Due to the complexity of the phishing websites, many development systems have been created to detect them. Unfortunately, the output that was desired cannot be achieved by these systems, and they have a number of other flaws as well. The purpose of this paper is to propose a hybrid deep learning-based phishing detection system that is easy to put into practice. The quality of the input dataset is improved through the process of preprocessing the dataset. After that, the procedures of clustering and feature selection are carried out in order to improve the accuracy and decrease the amount of time required for the processing. The resulting features are then fed into the CNN_LSTM, which is a classification system that classifies websites that are phishing and legitimate. Proposed Hybrid deep learning models are proposed to combine the features of natural language processing (NLP) and character embedding. They can then reveal high-level connections between characters. In terms of the metric that is being used for the evaluation, the performance of the models that have been proposed is better than that of the other models.

Multicriteria spatial model to prioritize degraded areas for landscape restoration through agroforestry

Reconciling the restoration of ecosystem services within agricultural landscapes is an effort that has been advancing within degraded areas restoration through agroforestry systems. However, to contribute to the effectiveness of these initiatives, it is essential to integrate landscape vulnerability and local demands to better highlight in which areas the implementation of agroforestry systems should be prioritized. Thus, we developed a spatial hierarchization methodology as a decision support tool as an active strategy for agroecosystem restoration. The proposed method constitutes a spatial indicator of priority areas to guide agroforestry interventions, including resource allocation and public policies for payment for environmental services. The methodology consists of Multicriteria Decision Analysis implemented in GIS software by combining input datasets based on biophysical conditions, environmental and socioeconomic aspects, that integrated promotes an assessment of the environment fragility, the pressures and responses to land use dynamic; a strategy for landscape restoration and conservation of the natural habitats, and multiple specific scenarios for decision making regarding the agricultural and the local actors demands. The output of the model provides the spatial distribution of areas suitable for the implementation of agroforestry systems, sorted into four priority levels (Low, Medium, High, and Extreme priority). The method is a promising tool proposal for territorial management and governance and subsidizes future research on the flows of ecosystem services.•Assessment of the environment fragility and the pressures and responses to land use dynamic.•Strategy for landscape restoration and conservation of remaining natural habitats.•Multiple specific scenarios for decision making regarding the agricultural and the local actors demands.