Preprocessing Step Research Articles

Analysis of the degree of correlation of spatial distribution of electricity theft and exogenous variables: case study of Florianopolis, Brazil

Abstract This article presents a geospatial study case on electricity theft. The main objective is to identify the degree of correlation between exogenous variables and areas with a high density of irregular cases. Firstly, the geospatial study is carried out to asses the null hypothesis and check whether the data pattern presents clustering, for this the ANN method is applied, which ruled out the null hypothesis for the data set. Once the clustering pattern is confirmed, the spatial weight matrix is created to study spatial autocorrelation by applying Global Moran’s I and Local Moran’s I. Moran scatterplot is used to evaluate the degree of fitness, identify outliers, and local pockets of stationarity. The Local Moran index is used to determine the location of the clusters and the relationship between the points. In the data pre-processing step, spatial interpolation is implemented to the exogenous variables as a tool to better association of consumer units points and socioeconomic variables, the method utilized is IDW interpolation. The R-squared value of the spatial lag model after model tuning by feature selection was 87 % indicating that the model fit the observed data well.

Crop Leaf Type Classification and Multi-Class Leaf Disease Identification with Tangent Hunter Prey Optimization-Based LeNet

The early detection and accurate rate of classification of plant leaf disease are more important for reliable and good agriculture, which prevents unwanted financial loss and resources. In this study, Tangent Hunter Prey Optimization-based LeNet (THPO-LeNet) is utilized for crop leaf classification and multi-class plant leaf disease identification. In this case, the input image that goes through the image pre-processing step is obtained from the plant village dataset. An adaptive Wiener filter is applied at the pre-processing stage to reduce needless mistakes and improve image quality. The pre-processed image is then sent to the leaf segmentation step, where a Mask Region-based Convolution Neural Network (Mask R-CNN) performs the segmentation. Consequently, image augmentation is performed using techniques such as scaling, rotation, translation, flipping, contrast, saturation, and hue. Afterwards, first-level classification plant leaf classification is processed by LeNet, which is optimized by Tangent Hunter Prey Optimization (THPO). The THPO is the incorporation of a Tangent Search Algorithm (TSA) and Hunter–Prey Optimizer (HPO). At last, the second-level classification of plant leaf disease is conducted by THPO-LeNet. Furthermore, the efficiency of THPO-LeNet is examined based on measures, like accuracy, Negative Predictive Value (NPV), True Positive Rate (TPR), True Negative Rate (TNR), Positive Predictive Value (PPV), loss value, and False Positive Rate (FPR), and the value attained is 95.68%, 92.50%, 91.48%, 92.25%, 92.54%, 8.321%, and 7.754%, respectively.

Enhancing RAG Performance Through Chunking and Text Splitting Techniques

In the world of Generative Artificial Intelligence (GenAI) and Large Language Models (LLM), Retrieval-Augmented Generation (RAG) has transformed the way we interact with data. Using RAG, these models can leverage new data contexts to respond to user queries and gain valuable insights. Behind the outstanding capabilities of RAG, a fundamental pre-processing step is present known as chunking. This step plays a crucial role in the effectiveness of these RAG-enhanced models. Chunking involves the breaking down of large text or documents into smaller segments of a fixed size. This allows the retriever to focus on smaller units at a time, making it easier to process and analyse the text. Finding the ideal chunking strategy can be a challenging task. Experimenting and analysis play a decisive role here, as different chunking strategies cater to different use cases. This paper, mainly targeted for an audience that is exploring RAG tuning techniques for higher accuracy, explores the various chunking techniques and their practical implementation using code snippets. After analysing the results for various use cases, the paper also suggests the best use cases for the different chunking strategies. Finally, it concludes by discussing the future potential and extending scope of RAG-enhanced applications.

Radon-domain acoustic and elastodynamic interferometric redatuming of VSP data

Summary The virtual source method (VSM) is a useful tool for imaging and monitoring below complex and time-varying overburden. When it is applied to VSP geometries, the redatumed virtual source data often suffer from artifacts and aliasing due to the violation of theoretical acquisition conditions and partial focusing of virtual multiples, which further degrade seismic imaging quality. While the conventional Radon-domain VSM (R-VSM) mitigates these issues to some extent, it is still possible to improve upon the imaging. This study develops a simple and effective high-resolution Radon-domain VSM (HR-VSM) to effectively address these issues, offering superior noise and artifact suppression compared to traditional VSM and R-VSM. HR-VSM shows a strong performance across a wide range of VSP configurations and data types, especially in applications to multi-component and passive seismic data, demonstrating its versatility and effectiveness in seismic exploration and showing potential for use in earthquake seismology. To extend subsurface illumination, we combined correlation-type and convolution-type HR-VSM for automatically redatuming virtual surface seismic profile (SSP) shot gathers with a complete receiver array covering all surface source locations, without the additional pre-processing steps typically required by VSM. It was also tested on reverse VSP (RVSP) synthetic active data and passive seismic data, proving effective in constructing virtual shot gathers and showing potential for extending its use to earthquake data and ambient-noise seismology. Moreover, HR-VSM can perform elastodynamic interferometric redatuming, enabling the redatuming of pure P-P and pure P-SV waves from multi-component VSP data. We applied HR-VSM to redatum virtual single well profile (SWP) data containing fault-related P-P and P-SV reflections from VSP data, which were further used for fault imaging. Finally, HR-VSM was used to generate virtual crosswell data with receivers in both boreholes, eliminating the need for downhole sources. The obtained virtual crosswell containing direct waves, as well as P-P and P-SV reflections, enable constructing a velocity model and imaging the structure between wells.

CTARR: A fast and robust method for identifying anatomical regions on CT images via atlas registration

Medical image analysis tasks often focus on regions or structures located in a particular location within the patient’s body. Often large parts of the image may not be of interest for the image analysis task. When using deep-learning based approaches, this causes an unnecessary increases the computational burden during inference and raises the chance of errors. In this paper, we introduce CTARR, a novel generic method for CT Anatomical Re- gion Recognition. The method serves as a pre-processing step for any deep learning-based CT image analysis pipeline by automatically identifying the pre-defined anatomical region that is relevant for the follow-up task and removing the rest. It can be used in (i) image segmentation to prevent false positives in anatomically implausible regions and speeding up the inference, (ii) image classification to produce image crops that are consistent in their anatomical context, and (iii) image registration by serving as a fast pre-registration step. Our proposed method is based on atlas registration and provides a fast and robust way to crop any anatomical region encoded as one or multiple bounding box(es) from any unlabeled CT scan of the brain, chest, abdomen and/or pelvis. We demonstrate the utility and robustness of the proposed method in the context of medical image segmentation by evaluating it on six datasets of public segmentation challenges. The foreground voxels in the regions of interest are preserved in the vast majority of cases and tasks (97.45-100%) while taking only fractions of a seconds to compute (0.1-0.21s) on a deep learning worksta- tion and greatly reducing the segmentation runtime (2.0-12.7x). Our code is available at <a href='https://github.com/ThomasBudd/ctarr'>https://github.com/ThomasBudd/ctarr</a>

Tree hierarchical deep convolutional neural network optimized with sheep flock optimization algorithm for sentiment classification of Twitter data

ABSTRACT The increasing volume of online reviews and tweets poses significant challenges for sentiment classification because of the difficulty in obtaining annotated training data. This paper aims to enhance sentiment classification of Twitter data by developing a robust model that improves classification accuracy and computational efficiency. The proposed method named Tree Hierarchical Deep Convolutional Neural Network optimized with Sheep Flock Optimization Algorithm for Sentiment Classification of Twitter Data (SCTD-THDCNN-SFOA) utilizes the Stanford Sentiment Treebank dataset. The process begins with pre-processing steps including Tokenization, Stop words Elimination, Filtering, Hashtag Removal, and Multiword Grouping. The Gray Level Co-occurrence Matrix Window Adaptive Algorithm is employed to extract features, such as emoticon counts, punctuation counts, gazetteer word existence, n-grams, and part of speech tags. These features are selected using Entropy–Kurtosis-based Feature Selection approach. Finally, the Tree Hierarchical Deep Convolutional Neural Network enhanced by the Sheep Flock Optimization Algorithm is used to categorize the Twitter data as positive, negative, and neutral sentiments. The proposed SCTD-THDCNN-SFOA method demonstrates superior performance, achieving higher accuracy and lesser computation time than the existing models, respectively. The SCTD-THDCNN-SFOA framework significantly improves the accuracy and efficiency of sentiment classification for Twitter data.

Anatomical landmark detection on bi-planar radiographs for predicting spinopelvic parameters.

Accurate landmark detection is essential for precise analysis of anatomical structures, supporting diagnosis, treatment planning, and monitoring in patients with spinal deformities. Conventional methods rely on laborious landmark identification by medical experts, which motivates automation. The proposed deep learning pipeline processes bi-planar radiographs to determine spinopelvic parameters and Cobb angles without manual supervision. The dataset used for training and evaluation consisted of 555 bi-planar radiographs from un-instrumented patients, which were manually annotated by medical professionals. The pipeline performed a pre-processing step to determine regions of interest, including the cervical spine, thoracolumbar spine, sacrum, and pelvis. For each ROI, a segmentation network was trained to identify vertebral bodies and pelvic landmarks. The U-Net architecture was trained on 455 bi-planar radiographs using binary cross-entropy loss. The post-processing algorithm determined spinal alignment and angular parameters based on the segmentation output. We evaluated the pipeline on a test set of 100 previously unseen bi-planar radiographs, using the mean absolute difference between annotated and predicted landmarks as the performance metric. The spinopelvic parameter predictions of the pipeline were compared to the measurements of two experienced medical professionals using intraclass correlation coefficient(ICC) and mean absolute deviation (MAD). The pipeline was able to successfully predict the Cobb angles in 61% of all test cases and achieved mean absolute differences of 3.3° (3.6°) and averaged ICC of 0.88. For thoracic kyphosis, lumbar lordosis, sagittal vertical axis, sacral slope, pelvic tilt, and pelvic incidence, the pipeline produced reasonable outputs in 69%, 58%, 86%, 85%, 84%, and 84% of the cases. The MAD was 5.6° (7.8°), 4.7° (4.3°), 2.8mm (3.0mm), 4.5° (7.2°), 1.8° (1.8°), and 5.3° (7.7°), while the ICC was measured at 0.69, 0.82, 0.99, 0.61, 0.96, and 0.70, respectively. Despite limitations in patients with severe pathologies and high BMI, the pipeline automatically predicted coronal and sagittal spinopelvic parameters, which has the potential to simplify clinical routines and large-scale retrospective data analysis.

TestCompareR: an R package to compare two binary diagnostic tests using paired data.

Binary diagnostic tests are commonly used in medicine to answer a question about a patient's clinical status, most commonly, do they or do they not have some disease. Recent advances in statistical methodologies for performing inferential statistics to compare commonly used test metrics for two diagnostic tests have not yet been implemented in a robust statistical package. Up-to-date statistical methods to compare the test metrics achieved by two binary diagnostic tests are implemented in the new R package testCompareR. The output and efficiency of testCompareR is compared to the only other available package which performs this function, DTComPair, as well as an open-source program, compbdt, using a motivating example. testCompareR achieves similar results to DTComPair using statistical methods with improved coverage and asymptotic performance. Further, testCompareR is faster than the currently available package and requires fewer pre-processing steps in order to produce accurate results. testCompareR provides a new tool to compare the test metrics for two binary diagnostic tests compared with the gold standard. This tool allows flexible inputs, which minimises the need for data pre-processing, and operates in very few steps, so that it is easy to use even for those less experienced with R. testCompareR achieves results comparable to those computed by DTComPair, using optimised statistical methods and with improved computational efficiency.

TestCompareR: an R package to compare two binary diagnostic tests using paired data

Background Binary diagnostic tests are commonly used in medicine to answer a question about a patient’s clinical status, most commonly, do they or do they not have some disease. Recent advances in statistical methodologies for performing inferential statistics to compare commonly used test metrics for two diagnostic tests have not yet been implemented in a robust statistical package. Methods Up-to-date statistical methods to compare the test metrics achieved by two binary diagnostic tests are implemented in the new R package testCompareR. The output and efficiency of testCompareR is compared to the only other available package which performs this function, DTComPair, as well as an open-source program, compbdt, using a motivating example. Results testCompareR achieves similar results to DTComPair using statistical methods with improved coverage and asymptotic performance. Further, testCompareR is faster than the currently available package and requires fewer pre-processing steps in order to produce accurate results. Conclusions testCompareR provides a new tool to compare the test metrics for two binary diagnostic tests compared with the gold standard. This tool allows flexible inputs, which minimises the need for data pre-processing, and operates in very few steps, so that it is easy to use even for those less experienced with R. testCompareR achieves results comparable to those computed by DTComPair, using optimised statistical methods and with improved computational efficiency.

Multi-head Network based Students Behaviour Prediction with Feedback Generation for Enhancing Classroom Engagement and Teaching Effectiveness

Emotions are pivotal in the learning process, highlighting the importance of identifying students' emotional states within educational settings. While neural network models, particularly those rooted in deep learning, have demonstrated remarkable accuracy in detecting primary emotions like happiness, sadness, fear, disgust, and anger from facial expressions in videos, these emotions occur infrequently in learning environments. Conversely, cognitive emotions such as engagement, confusion, frustration, and boredom are significantly more prevalent, transpiring five times more frequently than basic emotions. However, unlike basic emotions which are relatively distinct, cognitive emotions present a subtler distinction, necessitating the utilization of more sophisticated models for accurate recognition. The proposed work presents an efficient Facial Expression Recognition (FER) model for monitoring the student engagement in a learning environment by considering their facial expressions like boredom, frustration, confusion and engagement. The proposed methodology includes certain pre-processing steps followed by facial expression recognition founded on Efficient-Net B3 CNN in which the learning parameters are optimized using Circle-Inspired Optimization Algorithm (CIOA). Finally, the post processing stage estimates the frame-wise group engagement level (GEL) of students based on certain expression labels. Based on the acquired results, it is noted that the suggested Efficient-Net B3 CNN-CIOA based FER model provides promising results in terms of accuracy by 99.5%, precision by 99.2%, recall by 99.5% and f1-score by 99.6%, when compared with some state-of-art facial expression recognition approaches. Also, the suggested approach computational complexity is very much less than the compared existing approaches.

Exploring deep learning models for 4D-STEM-DPC data processing

For the study of magnetic materials at the nanoscale, differential phase contrast (DPC) imaging is a potent tool. With the advancements in direct detector technology, and consequent popularity gain for four-dimensional scanning transmission electron microscopy (4D-STEM), there has been an ongoing development of new and enhanced ways for STEM-DPC big data processing. Conventional algorithms are experimentally tailored, and so in this article we explore how supervised learning with convolutional neural networks (CNN) can be utilized for automated and consistent processing of STEM-DPC data. Two different approaches are investigated, one with direct tracking of the beam with regression analysis, and one where a modified U-net is used for direct beam segmentation as a pre-processing step. The CNNs are trained on experimentally obtained 4D-STEM data, enabling them to effectively handle data collected under similar instrument acquisition parameters. The model outputs are compared to conventional algorithms, particularly in how they process data in the presence of strong diffraction contrast, and how they affect domain wall profiles and width measurement.

Simulation study of turning-ultrasonic rolling compound processing for 42CrMo steel

The ultrasonic rolling processing technology has been shown to significantly reduce surface roughness and enhance the residual stress of parts, thereby improving their surface properties and extending their service life. This technology is particularly effective for the precision machining and surface strengthening of ultra-high-strength steel 42CrMo. This study aims to investigate the impact of turning pre-processing on the distribution of residual stress during ultrasonic rolling, a simulation model incorporating turning pre-processing was developed and used to conduct ultrasonic rolling simulation experiments, enabling the analysis of residual stress distribution patterns. Concurrently, ultrasonic rolling strengthening experiments were performed to validate the accuracy of the simulation model. The results confirm that with increasing rotational speed and feed rate, residual stress decreases, whereas with increasing static pressure and amplitude, residual stress increases. The residual stress variation obtained from the simulation of combined turning and ultrasonic rolling closely matched the results of experimental ultrasonic rolling tests. This consistency validates the accuracy of the simulation model. This study offers a novel approach for simulating and experimentally validating ultrasonic rolling processes, particularly for shaft-like parts that undergo turning as a pre-processing step.

Sentiment Analysis Using Improved CT-BERT_CONVLayer Fusion Model for COVID-19 Vaccine Recommendation

COVID-19 has significantly impacted individuals, communities, and countries worldwide. These effects include health impacts, economics impacts, social impacts, educational, political and environmental impacts. The COVID-19 vaccine development was crucial for disease control and monitoring, yet the threat still looms large. Vaccine recommender systems can help the health practitioners in combating COVID-19 by providing the information and guidance on the benefits and risks of COVID-19 vaccines to individuals based on their preferences and medical history. In this paper, we have proposed sentiment analysis based recommender system for COVID-19 vaccines. We used Twitter data of 10,000 tweets about COVID-19 vaccines and applied pre-processing steps. We propose an ensemble of random forest with CT-BERT_CONVLayerFusion model, a novel algorithm, for classifying the tweets into seven different categories of sentiments. We also performed aspect-based review categorization which works on the queries given by a user. We compared the results of sentiment classification with the state-of-the-art with metrics including accuracy, recall, precision, and F1-score, and found out that our proposed approach outperformed all other state-of-the-art model by achieving maximum accuracy, recall, precision and F1-measure. Hence, such advanced methods can help somehow to fight COVID-19 as well as reducing the vaccine hesitancy by suggesting proper vaccines to patients based on the their specific concerns and questions.

A-327 Statistical Technique-based Image Analysis for Digital Reading of Immunochemistry Cassette

Abstract Background Covid-19 transformed healthcare and how we think about clinical diagnostics. People prefer at home testing options that enable them to focus on staying healthy at their own comfort and privacy. Fast and accurate lateral flow assays or rapid diagnostic test (RDT) meets that need, however ensuring high test specificity and accuracy are of utmost importance. Visual readout of RDTs is subjective and time consuming. With the current technological advancement, medical devices are smarter and can be used for automated readout. The core of such devices are the algorithms that process the information despite several limitations and unknown variations affecting input signals. Many such algorithms are developed and are used for similar applications. Here, a statistical model for any optical device that is designed to automatically read an RDT with one or more test lines is described. Methods The described LFA algorithm is a innovative way to analyze images acquired with Complementary Metal-Oxide-Semiconductor (CMOS) based optical system with low Signal-to-noise ratio (SNR), giving a semi quantitative result. This also takes care of variations in illumination sources with relatively reduced computation, by converting the images to a 1 Dimensional (1D) signal. Algorithm workflow: Image pre-processing: Affine transformations such as rotation, translation, etc. (depends on the inherent setup) are applied on the acquired images as a pre-processing step. Pattern matching techniques using Gaussian templates are applied to determine the window region of the LFA and precisely identify the test and control line regions. Image formatting: The sample region of the cassette is converted from RGB color space to the weighted gray (Gw) for digital interpretation of the primary biomarker present. Characterization of the Gw channel enables test peak detection with enhanced resolution. This helps in early call out of results and improved accuracy, thereby reducing chances of erroneous results. A second order Butterworth low pass filter is applied to reduce system noise and enhance SNR. The images are converted to 1D signal by averaging for mathematical read out. Mathematical interpretation: Maximum peak height (max) and minimum peak depth (min) of Gw channel values in the test line region (t-peak) are extracted from the 1D signal. The mathematical representation of the test line is calculated as: Test Peak Signal = {max(t-peak) - min(t-peak)} / Alpha; Normalization Factor, Alpha = (sum of all Gw channel values for any clear non-reactive part of the test device) / (number of Gw channel values) Results TPS values for various biomarkers from statistically significant replicates were computed at Low, Medium, and High levels. Two sample T-tests were performed, and respective p values are distinctly different as p-value<0.05. For a concentration level of Low to medium, p-value is 0.044 and for Medium - High p-value is 0.004. Conclusions This algorithm can run on any off-the-shelf available RDT coupled with a CMOS based optical system. The proposed algorithm can differentiate between low, medium, and high concentrations with high confidence. High throughput semiquantitative digital readouts are robust, accurate and are preferred for diagnostic test result interpretation.

Quantifying the frequency modulation in electrograms during simulated atrial fibrillation in 2D domains

Atrial fibrillation (AF) affects millions of people in the world, causing increased morbidity and mortality. Treatment involves antiarrhythmic drugs and catheter ablation, showing high success for paroxysmal AF but challenges for persistent AF. Experimental evidence suggests reentrant waves and rotors contribute to AF substrates. Ablation procedures rely on electroanatomical maps and electrogram (EGM) signals; however, current methods used in clinical practice lack consideration for time–frequency varying EGM components. The fractional Fourier transform (FrFT) can be adopted to capture time-varying frequency components, thereby enhancing the comprehension of arrhythmogenic substrates during AF for improved ablation strategies. To this end, a FrFT-based algorithm is developed to characterize non-stationary components in EGM signals from simulated AF episodes. The proposed algorithm comprises a pre-processing step to enhance the coarser features of the EGM waveform, a windowing process for dynamic assessment of the EGM, and a FrFT order optimization stage that seeks compact signal representations in fractional Fourier domains. The resulting order is related to the rate of frequency change in the signal, making it a useful indicator for frequency-modulated components. The FrFT-based algorithm is implemented on EGM signals from AF simulations in 2D domains representing a region of the atrial tissue. Consequently, the computed optimum FrFT orders are used to build maps that are spatially correlated to the underlying propagation dynamics of the simulated AF episode. The results evince that the extreme values in the optimum orders map pinpoint the localization of fibrillatory mechanisms, generating EGM activation waveforms with varying frequency content over time.

An intelligent character segmentation system coupled with deep learning based recognition for the digitization of ancient Tamil palm leaf manuscripts

Palm-leaf manuscripts, rich with ancient knowledge in areas such as history, art, and medicine, are vital cultural treasures, making their digitization essential for preserving this heritage. Digitization of these organic and fragile manuscripts is required to safeguard the essential ancient data. This requires optimal character segmentation and recognition algorithms. A limited number of studies have been carried out in Tamil character recognition in literature. Handling row-overlapped characters, noise introduced due to lightning issues, and dirt, as well as the removal of punch holes, auto-cropping the content, filtering out noisy or improper segmentation, etc. are the essential concerns carried out in our proposed work. This work is executed as a four-step process (1) Palm Leaf Manuscript Acquisition (2) Pre-Processing (3) Segmentation of Tamil Characters and (4) Tamil Character Recognition. During acquisition, the scanners are used for recording palm leaf manuscripts from the Tamil Nadu-oriented manuscript library. In the Pre-processing step, the Fast Non-Local Means (Fast-NLM) method, paired with median filtering is used for Denoising the scanner output image. Later, the pixels that make the characters and borders (i.e., the foreground) are identified using Sauvola thresholding. The proposed methodology introduces efficient techniques to remove Punch hole impressions from the pre-processed image, and to crop the written content from the edges. After pre-processing, the Segmentation of Tamil Characters is performed as a three-step process (a) Manuscript (b) Line, and (c) character segmentation, which addresses conjoined lines, partially/completely empty segmentations that are not previously addressed by existing techniques. This work introduces an Augmented HPP line-splitting algorithm that accurately segments written lines, handling wrong segmentation cases that were previously not considered by existing techniques. The system achieves an average segmentation accuracy of 98.25%, which far outperforms existing techniques. It also proposes a novel Punch hole removal algorithm that can locate and remove the punch-hole impressions in the manuscript image. This algorithm, along with the automated content cropping technique, increases recognition accuracy and eliminates any manual labor needed. These features make the proposed methodology highly suitable for real-time archaeological and historical researches that include manuscripts. All 247 letters and 12 numeric digits are analyzed and separated into 125 distinct writable characters. In our work, characters are segmented and used for recognition of all 247 letters and 12 digits in Tamil using a multi-class CNN with 125 classes, which drastically reduces the complexity of the neural network compared to having 257 output nodes. It offered a notable performance of 96.04% accuracy. As compared with existing Tamil and other character recognitions, this work is effective in essence of considering real-time images and the increased number of characters used.

A transfer learning framework for the assessment of unconventional resources opportunities in the Middle East

An inadequate understanding of fluid transport processes in ultra-low permeability rocks has propelled data-driven modeling as an alternative and complementary tool to create recovery forecasts that honor the available data in the field. However, newly discovered fields lack data, which makes it challenging to apply traditional data-driven approaches to decision-making. Transfer learning provides an opportunity to start the early-stage analysis of the asset before adequate data becomes available. Here, we present a transfer learning framework that allows the basin-wide assessment of new shale gas and tight oil prospects. The proposed method is developed on real-world data from several thousand horizontal hydraulically fractured wells in the Eagle Ford super-basin in South Texas. A novel aspect of our method is integrating reservoir engineering domain expertise and the relationship among geologic and petrophysical variables, drilling and completion parameters, and well productivity in the data pre-processing and feature generation steps. We consider the temporal and spatial balancing of the training data to ensure that the resulting predictive models honor the real-world practices followed during unconventional field development. Our full-cycle transfer learning workflow consists of dimensionality reduction and unsupervised clustering, supervised learning, and hyperparameter fine-tuning. We test the workflow by examining the performance of a data-driven model of the Eagle Ford Basin on potential plays in the Middle East: Tuwaiq Mountain and Hanifa. The existence of multiple types of hydrocarbons–liquid oil, condensate, and dry gas–in the Eagle Ford results in a model flexible enough to be tested on various types of assets in a new location. We address the challenge of model overfitting by using data types with a relatively low resolution, which allows generalization to different geologies with basin-wide accuracy.

Online Tree-Structure-Constrained RPCA for Background Subtraction of X-ray Coronary Angiography Images

Background and objectiveBackground subtraction of X-ray coronary angiograms (XCA) can significantly improve the diagnosis and treatment of coronary vessel diseases. The XCA background is complex and dynamic due to structures with different intensities and independent motion patterns, making XCA background subtraction challenging. MethodsThe current work proposes an online tree-structure-constrained robust PCA (OTS-RPCA) method to subtract the XCA background. A morphological closing operation is used as a pre-processing step to remove large-scale structures like the spine, chest and diaphragm. In the following, the XCA sequence is decomposed into three different subspaces: low-rank background, residual dynamic background and vascular foreground. A tree-structured norm is introduced and applied to the vascular submatrix to guarantee the vessel spatial coherency. Moreover, the residual dynamic background is separately extracted to remove noise and motion artifacts from the vascular foreground. The proposed algorithm also employs an adaptive regularization coefficient that tracks the vessel area changes in the XCA frames. ResultsThe proposed method is evaluated on two datasets of real clinical and synthetic low-contrast XCA sequences of 38 patients using the global and local contrast-to-noise ratio (CNR) and structural similarity index (SSIM) criteria. For the real XCA dataset, the average values of global CNR, local CNR and SSIM are 6.27, 3.07 and 0.97, while these values over the synthetic low-contrast dataset are obtained as 5.15, 2.69 and 0.94, respectively. The implemented quantitative and qualitative experiments verify the superiority of the proposed method over seven selected state-of-the-art methods in increasing the coronary vessel contrast and preserving the vessel structure. ConclusionsThe proposed OTS-RPCA background subtraction method accurately subtracts backgrounds from XCA images. Our method might provide the basis for reducing the contrast agent dose and the number of needed injections in coronary interventions.

LIDAR3DNETV2: Smart Approach to Classify 3D Objects Based on Real Point Clouds

Point clouds generated in simulators avoid collection time costs and provide a high and organized amount of point clouds, an ideal scenario for deep learning networks. However, these networks have limitations when applied to real point clouds. This work proposes a multilayer perceptron-based method to classify 3D objects based on real point clouds obtained using LiDAR sensors. The method includes a pre-processing step that normalizes and adjusts the point clouds in the 3D Cartesian plane to overcome discrepancies in the point distribution. Furthermore, we created a dataset and used the ModelNet dataset for comparison purposes. The proposed neural network, Lidar3DNetV2, achieved 98.47% and 125 μs in accuracy and test time with real data, respectively. The pre-processing step provided a significant increase in the classifier’s performance. Finally, the proposed method performs better than other state-of-the-art networks considering real point clouds.

Fake News Detection with Machine Learning Algorithms

Nowadays, with the advancement of technology, the use of news sources has also undergone a great evolution. News sources have constantly evolved from past to present, ranging from magazines to radios, from newspapers to televisions. The fact that it has become so easy to access news has caused society to pay more attention to fake news. Fake news has the ability to influence society through news sources such as social media, which can reach wider audiences with the development of technology. The difficulties of users in accessing accurate and reliable sources in this information flow that shapes their daily lives increases the potential for the spread of fake news, and it becomes increasingly difficult to distinguish between real and fake news. In this study, classification models for fake news detection were designed using machine learning algorithms. The dataset, which includes fake and real news examples, contains 42,000 examples. Each class, including fake and real samples, contains 22,000 sample data. In order to increase data quality, accuracy and usability, preprocessing methods were applied to the data set. The removal of numbers, stop words, and html tags was done in the pre-processing step to remove unnecessary information from the text. Models were created for fake news detection with singular and ensemble classification algorithms. Performance evaluation of the models was performed using 5-fold cross-validation. In the performance comparisons of the models, values such as accuracy, sensitivity, specificity, tp rate and fp rate were calculated. The highest performance results were observed in the random forest classification algorithm with an accuracy rate of 76%.