2D Scatter Plot Research Articles

P-264. Fournier-transform Infrared spectrometry is a quick, reliable and economical method used to determine clonality and nosocomial transmission of an extended Spectrum β-lactamase E.coli contaminated endoscope

Abstract Background Nosocomial transmission of bacteria via contaminated endoscopes is known to occur due to inadequacies in the complex cleaning process of multi-channel endoscopes. At our institution we do regular surveillance culture screening of endoscopes. Upon receiving positive cultures with an Extended Spectrum β-lactamase producing (ESBL) E.coli we alerted our hospital hygiene unit. After screening potentially exposed patients we determined clonality of ESBL E.coli isolates from 4 patients with expensive en specialized molecular diagnostics, at our local academic hospital using Amplification Fragment Length Polymorphism (AFLP). We were testing the BiotyperIR (Bruker Daltronics) in our laboratory and wanted to see how de FTIR compared to AFLP in our small peripheral hospital setting. BiotyperIR 3D scatterplot Cluster of endoscope isolate and exposed patient isolates with 2 non related patient control isolates Methods We determined that a total of 16 patients had endoscopic investigations preformed with the contaminated endoscope. We were able to do rectal screening cultures for ESBL positive organisms using ESBL selective media from 11 of the 16 patients. We were unable to screen 5 patients. Of the 11 patients that were screened 4 were positive with an ESBL E.coli. Clonal testing was done on these isolates and 2 non outbreak ESBL E.coli patient isolates with AFLP and FTIR using the BiotyperIR. IR spectra were acquired from dried spots of bacterial suspensions in ethanol solution. Exploratory data analysis of the FTIR spectra was performed by Hierarchical Cluster Analysis (HCA) using Bruker’s updated software. BiotyperIR dendrogram Cluster of endoscope isolate and exposed patient isolates with 2 non related patient control isolates Results Both results from AFLP and the BiotyperIR showed that all 4 ESBL E.coli patient isolates were identical to the contaminated endoscope isolate and the 2 non outbreak patient control isolates were unrelated to the outbreak isolate. We concluded that there had been nosocomial transmission of an ESBL E.coli. Clonal typing using the BiotyperIR FTIR was done within 24 hours in our own laboratory compared to 2 weeks using AFLP which had to be sent to our local academic hospital. Conclusion The BiotyperIR FTIR spectrometry results were identical to molecular typing using AFLP to determine nosocomial transmission of a clonal ESBL E.coli. Results were obtained significantly faster and at a fraction of the cost of molecular AFLP. Disclosures Carolyn Moonen, PhD, Bruker Daltonics GmbH & Co. KG: Advisor/Consultant

Dr.Emb Appyter: A web platform for drug discovery using embedding vectors.

Using embedding methods, compounds with similar properties will be closely located in latent space, and these embedding vectors can be used to find other compounds with similar properties based on the distance between compounds. However, they often require computational resources and programming skills. Here we develop Dr.Emb Appyter, a user-friendly web-based chemical compound search platform for drug discovery without any technical barriers. It uses embedding vectors to identify compounds similar to a given query in the embedding space. Dr.Emb Appyter provides various types of embedding methods, such as fingerprinting, SMILES, and transcriptional response-based methods, and embeds numerous compounds using them. The Faiss-based search system efficiently finds the closest compounds of query in the library. Additionally, Dr.Emb Appyter offers information on the top compounds; visualizes the results with 3D scatter plots, heatmaps, and UpSet plots; and analyses the results using a drug-set enrichment analysis. Dr.Emb Appyter is freely available at https://dremb.korea.ac.kr.

Detection of spatiotemporal changes in eco-environmental quality based on RSEI and SG filtering and its driving force analysis: a case study in Sichuan Province, China.

Landsat images were extracted using Google Earth Engine (GEE) platform and optimized by Savitzky-Golay (SG) filtering. The Remote Sensing Ecological Index (RSEI) method was used to analyze the eco-environmental quality in Sichuan Province in recent 20years. In addition, Theil-Sen median method and Mann-Kendall (MK) test were used to test the change trend of eco-environmental quality. Furthermore, drivers were evaluated by partial correlation analysis, 2D scatter plots, and t tests. The results showed that (1) in the past 20years, the eco-environmental quality of Sichuan Province was on the rise, and the eco-environmental quality in the western region was better than that in the eastern region. The eco-environmental quality was positively correlated with forest and grassland types, and negatively correlated with cultivated land and urban and rural construction land types. (2) The eco-environmental quality of Sichuan Province is linearly correlated with the digital elevation model, but poorly correlated with slope and slope direction. In the range of slope 0° ~ 9° and southeast direction, the eco-environmental quality is the worst. (3) The eco-environmental quality of Sichuan Province was most significantly affected by soil moisture and sunshine hours. The study can help us to understand and assess the health of ecosystems in Sichuan Province, provide a scientific basis for protecting and improving the environment, and guide the formulation and implementation of environmental protection policies.

Discovery of narrow-band emitting phosphor Na5Al3F14:Eu2+ using local structure similarity

Narrow-band emitting phosphors are utilized to improve the color purity and expand the color gamut of display. Data-driven approach is an effective technique to search the host material of the narrow-band emitting phosphors. Herein, we discover a new narrow-band emitting phosphor Na5Al3F14:Eu2+ by a local structure similarity. 2D scatter plot of the structural similarity revealed that the local structure of Na1-site of the Na5Al3F14 located to near the Sr-sites of the narrow-band emitting phosphor SrLiAl3N4:Eu2+. A powder of the narrow-band emitting phosphor Na5Al3F14:Eu2+ was successfully synthesized by a solid-state reaction method. The Na5Al3F14:Eu2+ phosphor exhibited a narrow-band emission at 393 nm with a full width at half-maximum of 30 nm (1549 cm−1). The internal and external quantum efficiency was 56.0 % and 45.0 %, respectively. The photoluminescence intensity at 200°C was maintained at 63 % of room temperature. This approach accelerates the discovery of new phosphors with specific luminescence properties.

Direct Identification of Complex Glycans via a Highly Sensitive Engineered Nanopore.

The crucial roles that glycans play in biological systems are determined by their structures. However, the analysis of glycan structures still has numerous bottlenecks due to their inherent complexities. The nanopore technology has emerged as a powerful sensor for DNA sequencing and peptide detection. This has a significant impact on the development of a related research area. Currently, nanopores are beginning to be applied for the detection of simple glycans, but the analysis of complex glycans by this technology is still challenging. Here, we designed an engineered α-hemolysin nanopore M113R/T115A to achieve the sensing of complex glycans at micromolar concentrations and under label-free conditions. By extracting characteristic features to depict a three-dimensional (3D) scatter plot, glycans with different numbers of functional groups, various chain lengths ranging from disaccharide to decasaccharide, and distinct glycosidic linkages could be distinguished. Molecular dynamics (MD) simulations show different behaviors of glycans with β1,3- or β1,4-glycosidic bonds in nanopores. More importantly, the designed nanopore system permitted the discrimination of each glycan isomer with different lengths in a mixture with a separation ratio of over 0.9. This work represents a proof-of-concept demonstration that complex glycans can be analyzed using nanopore sequencing technology.

Abstract 4919: AI-enabled hit selection of drug screening on human pancreatic cancer organoids

Abstract Cancer remains one of the leading causes of death in the 21st century. Despite the latest advances in oncology, most cancer patients lack tailored therapeutic approaches with lasting benefit. Measuring the impact of anticancer compounds and their combinations is only possible on ex vivo assays. To this end, patient-derived organoids (PDOs) have been proposed as viable and efficient models for ex vivo testing. PDOs show long-term expansion potential while retaining tumor histopathology as well as cancer gene mutations. However, the translation of organoids in screening applications has so far been hampered by the lack of homogeneity and difficulties in handling and automation. Moreover, organoids are typically randomly distributed across the culture which complicates imaging and images analyses. To overcome these challenges, we set up a compound screening workflow with PDOs using Gri3D platform, comprising plates with micro-cavities suitable for high-throughput and reproducible organoid culture. Based on a standard 96 microtiter plate, each well contains a microwell array patterned in a cell repellent hydrogel. On Gri3D®, organoids are robustly generated in the microwells and are located in the same imaging plane. This greatly facilitates quantitative analyses in high content image-based screens. Furthermore, the pipetting port enables automation of cell seeding, media exchange and compound incubation with liquid-handlers, thus increasing assay reproducibility. In the presented work, we exposed human pancreatic cancer PDOs to a panel of anti-cancer compounds at different doses and followed their response to the drugs using viability dyes Calcein AM (live stain) and Ethidium Homodimer-1 (dead stain) with high-content confocal imaging. Using an AI-based approach, we efficiently detected each single organoid and extracted phenotypic features from all three channels (TL, live stain and dead stain) which correlate with cytotoxicity. The extracted features (more than 100) were first dimensionally reduced to 3 components using either PCA or UMAP, the treatments were then visualized in 3D scatter plots, ranked and clustered using machine learning. The data suggests that the compound treatment Palbociclib 50uM has significant cytotoxicity effects similar to the positive control, which is consistent with the traditional live/dead analysis. The AI approach demonstrates feasibility to perform drug screening in a robust and un-biased data analysis approach. Citation Format: Zhisong Tong, Angeline Lim, Marine Meyer, Maria Clapes, Oksana Sirenko, Nathalie Brandenberg. AI-enabled hit selection of drug screening on human pancreatic cancer organoids [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4919.

Temperature-Energy Relationships and Spatial Distribution Analysis for Nano-Enhanced Phase Change Materials Via Thermal Energy Storage

Despite the abundance and affordability of solar energy, its adoption in industrial and domestic sectors, especially in developing countries, still needs to be improved. This study addresses the gap by proposing integrated storage systems to align energy supply and demand, essential for various industrial processes. Investigating Nano-enhanced Phase Change Material (PCM), the research formulates governing equations for the phase change process, explores numerical simulations using MATLAB's Finite Volume Method, and validates models. The PCM comprises a solid salt mixture with Sodium Chloride Nanoparticles. The analysis of nano-enhanced PCMs for thermal energy storage focuses on understanding the interrelationship between temperature, energy, and nanoparticle distribution within the PCM. Visuals based on 3D surface plots and scatter plots illustrate how energy storage characteristics vary with temperature and spatial variables, identifying phase change temperatures and energy absorption/release points. These visualizations guide PCM optimization for improved thermal conductivity and heat capacity, which is crucial for diverse applications like solar energy systems and thermal management in electronics. Nano-enhanced PCM performance can be further enhanced by employing advanced numerical methods and simulation tools for accurate prediction and optimization before experimental validation.

Exploring the Efficacy of LightGBM, AdaBoost, and CatBoost in Alzheimer’s Disease Classification

Alzheimer’s disease (AD) is a major public health concern that requires prompt and accurate diagnosis to intervene effectively. We present a comprehensive machine learning system in our work that is specifically designed to classify AD. It incorporates various neuroimaging and clinical features, including air time1, disp index1, gmrt in air1, max x extension1, and max y extension1. We can decipher complex data correlations suggesting AD pathology using rigorous preprocessing and visualization methods, such as correlation heatmaps and 3D scatter plots. We can distinguish minute changes between AD, moderate cognitive impairment, and healthy controls using CatBoost, LightGBM, and AdaBoost classifiers. A thorough assessment of the model’s performance is provided by the rigorous evaluation metrics of accuracy, precision, recall, and F1-score, which are supplemented by detailed classification reports and confusion matrices. Learning curves also provide information about the generalization and flexibility of models. Our findings support integrated analysis approaches across many data modalities and highlight the revolutionary potential of machine learning in AD diagnosis. Developing customized treatment plans and cutting-edge clinical decision support systems is expected to improve patient outcomes and the standard of care for neurodegenerative diseases.

Constructing a Mathematical Model of Product Color Design Based on Data Mining: Case Study of a Thermos Cup

In product design, color is the first element that acts on the human visual senses and significantly influences consumer decisions. This study aimed to analyze consumers’ color preferences for products and explore the mathematical patterns of product color design. Firstly, sales data and images of popular thermos cups from Tmall and Jingdong (JD), two prominent e-commerce platforms in China, were obtained through data mining. Subsequently, this research focused on single-color thermos cups with high sales as the research subject, extracting the hue (H), saturation (S), and value (V) for each cup from the product images. Furthermore, a 3D scatter plot of HSV values was generated using Origin Pro, visually representing the consumers’ color preferences. Finally, this study examined the relationships among HSV values of the popular product colors through multiple regression analysis and constructed a mathematical model for HSV. This method enables manufacturers to gain valuable insights into consumer color preferences, facilitating digital color design and enhancing design efficiency and accuracy.

Pattern analysis on <em>Aquilaria Malaccensis</em> using machine learning

Aquilaria Malaccensis was found to generate agarwood. Because of its multiple benefits, agarwood essential oil, sometimes known as “black gold” is highly regarded universally. There is currently no accepted method for classifying various grades of agarwood essential oil. Due to the fact that the agarwood essential oil is assessed using a human sensory panel, the existing grading method is ineffective. Since different people may have different viewpoints on how to grade agarwood essential oil, it is not practical to apply the method universally. Several innovative methods for determining the classification of agarwood essential oil have been proposed and put into practise as a result of advanced technology. The study has constructed a pattern analysis on different grades of agarwood essential oil using 2D scatter plot. The results successfully indicate the scatter plots are scattered groupedly.

Exploring the provision, efficiency and improvements of urban green spaces on accessibility at the metropolitan scale

Accurately assessing urban green space (UGS) accessibility and proposing effective and specific proposals for UGS provision improvement accordingly is vital to urban development. Taking the metropolitan of Shanghai, China as the study site, this study first assessed its UGS provision by improved multiple step floating catchment area methods and multiple indexes, including UGS accessibility, theoretical capacity, potential demand, and traffic supply. Second, it investigated the impacts on citywide UGS accessibility justice for each UGS by comparing Gini index differences of citywide UGS accessibility between the conditions when exist and non-exist for each UGS. Third, it used ternary plots to explore the influence mechanism of the factors of UGS theoretical capacity, potential demand, and traffic supply on accessibility, and introduced an RGB color triangle to spatially and simultaneously display the effects of these three factors on accessibility for each UGS in Shanghai. Fourth, it assessed and classified the UGS provision efficiency for accessibility according to the relationships among the theoretical capacity, potential demand, and traffic supply factors by 3D scatter plot. Fifth, it proposed specific types and priorities of requirement for UGS improvement according to its impact on citywide UGS accessibility justice and the effect of its theoretical capacity factor on UGS accessibility. The findings showed that UGS accessibility and its three factors in Shanghai were correlative and had a spatial clustering trend in central city areas. The majority of UGSs showed positive impact on citywide accessibility justice, which went up with the values of accessibility and the three factors. Most UGSs were dominated by theoretical capacity power. The UGS provision efficiency was relatively good for most UGSs, which had relatively well-matched conditions and demands. The improvement requirements for UGSs on accessibility investigated in this study will improve UGS provision.

Predicting the Productivity of Municipality Workers: A Comparison of Six Machine Learning Algorithms

One of the most significant areas of local government in the world is the municipality sector. It provides various services to the residents and businesses in their areas, such as water supply, sewage disposal, healthcare, education, housing, and transport. Municipalities also promote social and economic development and ensure democratic and accountable governance. It also helps in encouraging the involvement of communities in local matters. Workers of Municipalities need to maintain their services regularly to the public. The productivity of the employees is just one of the main important factors that influence the overall organizational performance. This article compares various machine learning algorithms such as XG Boost, Random Forest (RF), Histogram Gradient Boosting Regressor, LGBM Regressor, Ada Boost Regressor, and Gradient Boosting Regressor on the dataset of municipality workers. The study aims to propose a machine learning approach to predict and evaluate the productivity of municipality workers. The evaluation of the overall targeted and actual productivity of each department shows that out of 12 different departments, only 5 departments were able to meet their targeted productivity. A 3D Scatter plot visually displays the incentive given by the department to each worker based on their productivity. The results show that XG Boost performs best in comparison with the other five algorithms, as the value of R Squared is 0.71 and MSE (Mean Squared Error) is 0.01.

Speech and lexico-semantic errors during direct cortical stimulation mapping of the language-dominant hemisphere: effects of object and action naming.

In this retrospective study, the authors aimed to establish the stereotactically defined probability distribution for speech (i.e., anarthria, speech arrest) and lexico-semantic errors (i.e., anomia) through direct cortical stimulation (DCS) by using two tasks: action naming and object naming. They also analyzed the patterns of interindividual variability in the localization of the language sites involved, and investigated whether any patient or lesion location factors were associated with greater variability. Eighty-one Italian-speaking patients who underwent awake surgery between 2010 and 2021 for low- and high-grade gliomas in eloquent areas of the language-dominant hemisphere were entered in the analyses. The intraoperative DCS protocol included automatic speech tasks, object naming, and action naming. The position of the tags, as depicted on the intraoperative video or photograph, was transposed into Montreal Neurological Institute space. Subsequently, a 2D scatterplot and cluster analysis were performed. Associations between various clinical and radiological characteristics and the quantity of positive stimulated sites were determined by univariate analyses using binary logistic regression. Associated variables (p < 0.2) were included in stepwise multivariate logistic regression with backward elimination (p < 0.05). A total of 1380 cortical sites were stimulated, with a positive response in 511 cases (37%). Most anarthric errors were triggered when stimulating the left precentral gyrus, and most speech arrest errors were elicited when stimulating the left posterior inferior frontal gyrus. Anomias were found in the left inferior frontal gyrus and in the posterior part of the left temporal lobe for object naming. DCS to the left dorsal premotor cortex elicited anomic errors for action naming. Anomias were also elicited during DCS to the left posterior temporal lobe, with both object and action naming. The distribution of speech and lexico-semantic errors is in line with the current literature. The action-naming results are new and mostly involve the dorsal premotor cortex. These findings stress the importance of maximizing the use of different language tasks during surgery, because even when looking for the same type of errors, different tasks may be better suited to map specific brain regions. DCS with action and object naming identifies more positive sites than object naming alone.

Understanding the Radiation Dose Variability in Nasopharyngeal Cancer: An Organs-at-Risk Approach.

Objective This study aims to thoroughly assess the radiation dose distributionto critical organs in patients with nasopharyngeal carcinoma, focusing on the correlation between the radiation dosages for the various organs at risk (OARs) in nasopharyngeal cancer patients. Methods We meticulously analysed a dataset comprising 38 nasopharyngeal carcinoma patients, focusing on radiation dosages measured in Gray (Gy) and volumetric data in cubic centimetres (cc) of critical organs, including the lens, brainstem, spinal cord, optic nerve, optic chiasm, and cochlea. A detailed exploratory data analysis approach encompassed univariate, bivariate, and multivariate techniques. Results Our analysis revealed several key findings. The mean and median values across various dose measurements were closely aligned, indicating symmetrical distributions with minimal skewness. The histograms further corroborated this, showing evenly distributed dose values across different anatomical regions. The correlation matrix highlighted varying degrees of interrelationships between the doses, with some showing strong correlations while others exhibited minimal or no correlation. The 3D scatter plot provided a view of the multi-dimensional dose relationships, with a specific focus on the spinal cord, lens, and brainstem doses. The bivariate scatter plotsrevealed symmetrical distributions between the right and left lens doses and more complex relationships involving the brainstem and spinal cord, illustrating the intricacies of dose distribution in radiation therapy. Conclusion Our findings reveal distinct radiation exposure patterns to OARs of nasopharyngeal carcinoma. This research emphasises the need for tailored radiation therapy planning to achieve optimal clinical outcomes while safeguarding vital organs.

A Novel Method for Assessing the 3-dimensional Morphology of Cartilaginous Acetabulum Via Childhood Magnetic Resonance Imaging.

Periarticular cartilage is abundant in children, making evaluations of 3-dimensional (D) cartilaginous acetabular morphology using x-ray or computed tomography (CT) difficult. The study aimed to visualize the 3D cartilaginous acetabular morphology in normal children and patients with pediatric developmental dysplasia of the hip (DDH). Magnetic resonance imaging (MRI) of 17 female children without acetabular dysplasia at 7.5 years and CT of 33 normal female adolescents with mature bones at 14.6 years were used as controls. Subjects were 26 female patients with unilateral DDH who underwent angulated Salter innominate osteotomy (A-SIO) at 5.5 years. Preoperative and postoperative MRIs were performed at 5.2 and 7.0 years, respectively. The MRI sequence was 3D-MEDIC. The medial intersection (point A) of the line connecting the centers of the bilateral femoral head and the femoral head were defined as point zero. The 3D coordinates (X, Y, Z) of the cartilaginous acetabular edge (point C) from anterior to posterior were calculated. Subsequently, a 3D scatter plot was created using 3D graph software. The subjects were divided into 6 groups, including control MRI, control CT, unaffected DDH before and after A-SIO, and affected DDH before and after A-SIO. The femoral head coverage ratio (FHCR: AC/AB) was used to quantify coverage and was compared in each group. In the control MRI group, the acetabular coverage was small anteriorly, largest anterolaterally, and gradually decreased posteriorly, similar to the bony acetabulum in adolescents. In the affected DDH before A-SIO group, the coverage was significantly lower than that of the control MRI and unaffected DDH groups. After A-SIO, the morphology improved beyond the unaffected DDH and the control MRI group. The global defect of the cartilaginous acetabulum in the affected DDH group was significantly improved to normal morphology after A-SIO. Evaluating the cartilaginous acetabulum using MRI was useful for assessing hip morphology in childhood. Level III-retrospective comparative study.

Laplacian-based Cluster-Contractive t-SNE for High-Dimensional Data Visualization

Dimensionality reduction techniques aim at representing high-dimensional data in low-dimensional spaces to extract hidden and useful information or facilitate visual understanding and interpretation of the data. However, few of them take into consideration the potential cluster information contained implicitly in the high-dimensional data. In this article, we propose Lap tSNE, a new graph-layout nonlinear dimensionality reduction method based on t-SNE, one of the best techniques for visualizing high-dimensional data as 2D scatter plots. Specifically, Lap tSNE leverages the eigenvalue information of the graph Laplacian to shrink the potential clusters in the low-dimensional embedding when learning to preserve the local and global structure from high-dimensional space to low-dimensional space. It is nontrivial to solve the proposed model because the eigenvalues of normalized symmetric Laplacian are functions of the decision variable. We provide a majorization-minimization algorithm with convergence guarantee to solve the optimization problem of Lap tSNE and show how to calculate the gradient analytically, which may be of broad interest when considering optimization with Laplacian-composited objective. We evaluate our method by a formal comparison with state-of-the-art methods on seven benchmark datasets, both visually and via established quantitative measurements. The results demonstrate the superiority of our method over baselines such as t-SNE and UMAP. We also provide out-of-sample extension, large-scale extension, and mini-batch extension for our Lap tSNE to facilitate dimensionality reduction in various scenarios.

Manifold learning for fMRI time-varying functional connectivity.

Whole-brain functional connectivity (FC) measured with functional MRI (fMRI) evolves over time in meaningful ways at temporal scales going from years (e.g., development) to seconds [e.g., within-scan time-varying FC (tvFC)]. Yet, our ability to explore tvFC is severely constrained by its large dimensionality (several thousands). To overcome this difficulty, researchers often seek to generate low dimensional representations (e.g., 2D and 3D scatter plots) hoping those will retain important aspects of the data (e.g., relationships to behavior and disease progression). Limited prior empirical work suggests that manifold learning techniques (MLTs)-namely those seeking to infer a low dimensional non-linear surface (i.e., the manifold) where most of the data lies-are good candidates for accomplishing this task. Here we explore this possibility in detail. First, we discuss why one should expect tvFC data to lie on a low dimensional manifold. Second, we estimate what is the intrinsic dimension (ID; i.e., minimum number of latent dimensions) of tvFC data manifolds. Third, we describe the inner workings of three state-of-the-art MLTs: Laplacian Eigenmaps (LEs), T-distributed Stochastic Neighbor Embedding (T-SNE), and Uniform Manifold Approximation and Projection (UMAP). For each method, we empirically evaluate its ability to generate neuro-biologically meaningful representations of tvFC data, as well as their robustness against hyper-parameter selection. Our results show that tvFC data has an ID that ranges between 4 and 26, and that ID varies significantly between rest and task states. We also show how all three methods can effectively capture subject identity and task being performed: UMAP and T-SNE can capture these two levels of detail concurrently, but LE could only capture one at a time. We observed substantial variability in embedding quality across MLTs, and within-MLT as a function of hyper-parameter selection. To help alleviate this issue, we provide heuristics that can inform future studies. Finally, we also demonstrate the importance of feature normalization when combining data across subjects and the role that temporal autocorrelation plays in the application of MLTs to tvFC data. Overall, we conclude that while MLTs can be useful to generate summary views of labeled tvFC data, their application to unlabeled data such as resting-state remains challenging.

UNSW‐NB15 computer security dataset: Analysis through visualization

AbstractClass imbalance refers to a major issue in data mining where data with unequal class distribution can deteriorate classification performance. Although it alone affects the performance of the classifiers, the joint‐effect of class imbalance and overlap is more damaging. Data overlap happens when multiple classes are assigned to a single data point causing the classifiers to misidentify the class boundaries. This study offers a deep insight into the intricacies of the UNSW‐NB15 dataset and two issues that may lead the data‐driven models to demonstrate poor performance. The most commonly used visualization methods such as bar chart, 3D and 2D scatter plots, intercluster distance map, and parallel coordinate diagram were employed to depict the data imbalanced and overlap. However, their limitations in capturing the overlapping issue led us to propose an accurate, easy‐to‐interpret, and scalable overlapping visualization method. The method clearly detects the data overlap and illustrates the effect of several data scalers in dealing with the data overlap. To verify the accuracy of the proposed method, a number of classifiers were implemented along with the scalers and the calculated AUC scores were compared to those calculated from the classifiers that were implemented on the original dataset.

SEAHORS: Spatial Exploration of ArcHaeological Objects in R Shiny

This paper presents SEAHORS, an R shiny application available as an R package, dedicated to the intra-site spatial analysis of piece-plotted archaeological remains. This open-source script generates 2D and 3D scatter and density plots for archaeological objects located with cartesian coordinates. Many different GIS software already exist for this, but they mostly require specific skills and training to be used and are rarely designed for the particular needs of archaeological applications. The goal of SEAHORS is to make the two and three-dimensional intra-site spatial exploration of archaeological data as user-friendly as possible, in order to give the opportunity to researchers not familiar with GIS and R software to utilise such approaches. SEAHORS has an easily accessible interface and can import data from text and Excel files (.csv and .xls/xlsx respectively) without preformatting. The application includes functions to concatenate columns and to merge databases, for example when spatial data (XYZ coordinates) and analytical data (e.g. taxonomical attribution of faunal remains, typo-technological attributes of artifacts, etc.) are stored in separate files. SEAHORS can generate five types of plots: 3D, 2D and density plots, as well as 2D plots by slices (i.e. subdivisions according to a third dimension) and 2D plots with a modification of the angle of projection (i.e. to explore spatial organization without the constraints of the field grid orientation). SEAHORS has visualization tools with several sorting and formatting options (color, size, etc.) applicable to coordinates and all possible analytical variables (i.e. levels, spits, identified species, taphonomical alterations, etc.). Orthophotos can also be imported and directly used in the program. The application also allows the grouping of objects into new variables by selecting items on the interactive 2D plots. We present an overview of the application’s functions by using the case study of the Cassenade Paleolithic site (France).

Analyzing piece-plotted artifacts just got simpler: A good solution to the wrong problem?

This paper presents SEAHORS, an R shiny application available as an R package, dedicated to the intra-site spatial analysis of piece-plotted archaeological remains. This open-source script generates 2D and 3D scatter and density plots for archaeological objects located with cartesian coordinates. Many different GIS software already exist for this, but they mostly require specific skills and training to be used and are rarely designed for the particular needs of archaeological applications. The goal of SEAHORS is to make the two and three-dimensional intra-site spatial exploration of archaeological data as user-friendly as possible, in order to give the opportunity to researchers not familiar with GIS and R software to utilise such approaches. SEAHORS has an easily accessible interface and can import data from text and Excel files (.csv and .xls/xlsx respectively) without preformatting. The application includes functions to concatenate columns and to merge databases, for example when spatial data (XYZ coordinates) and analytical data (e.g. taxonomical attribution of faunal remains, typo-technological attributes of artifacts, etc.) are stored in separate files. SEAHORS can generate five types of plots: 3D, 2D and density plots, as well as 2D plots by slices (i.e. subdivisions according to a third dimension) and 2D plots with a modification of the angle of projection (i.e. to explore spatial organization without the constraints of the field grid orientation). SEAHORS has visualization tools with several sorting and formatting options (color, size, etc.) applicable to coordinates and all possible analytical variables (i.e. levels, spits, identified species, taphonomical alterations, etc.). Orthophotos can also be imported and directly used in the program. The application also allows the grouping of objects into new variables by selecting items on the interactive 2D plots. We present an overview of the application’s functions by using the case study of the Cassenade Paleolithic site (France).