Benchmark Data Research Articles

Portfolio Optimization with Multi-Trend Objective and Accelerated Quasi-Newton Method

We propose a portfolio optimization method with a multi-trend objective and an accelerated quasi-Newton method (MTO-AQNM). It leverages a BFGS-based quasi-Newton algorithm and incorporates an ℓ1 regularization term and the self-funding constraint. The MTO is designed to identify multiple trend reversals. Different trend reversals are asymmetric, and we hoped to extract rich and effective information from them. The AQNM adopts the BFGS method with the Wolfe conditions, which reduces computational complexity and improves convergence speed. We wanted to evaluate the performance of our algorithm through financial markets that were asymmetric in all respects. To this end, we conducted comprehensive experimental approaches on six benchmark data sets of real-world financial markets that were asymmetric in time, frequency, and asset type. Our method demonstrated superior performance over other state-of-the-art competitors across several mainstream evaluation metrics.

Design and Development of Fractional Order Convolutional Neural Network Based Fractional Order Nonlinear Reactor Power Simulator for CANDU-PHWR

A highly complex nonlinear Reactor Regulating System (RRS) of Canadian Deuterium Uranium Pressurized Heavy Water Reactor (CANDU-PHWR) based Nuclear Power Plant (NPP) simulated in the present research. The internal design of RRS is secured and vendor controlled which is embedded in AC-132 Programmable Logic Controller (PLC). Therefore, the problem of the identification of the RRS controller model is addressed. A data-driven Fractional Order Nonlinear MIMO Hammerstein Model (FO-NC-MIMO-HM) of NPP is identified using an Adaptive Immune Algorithm (AIA) based on a Global Search Strategy (GSS) and Auxiliary Model Recursive Least Square Method (AMRLSM). Parameters of FO-MIMO-HM are identified using Innovative Real-Time Plant Operational Data (IRTPOD). The original PLC-based controller is replaced with a new Fractional Order Convolutional Neural Network (FO-CNN) based Fractional Order Nonlinear Controller (FO-NC). Therefore, a visual Simulator is developed for detailed modeling, control, simulation, and analysis of the proposed design scheme for RRS in Visual Basic (VB) Software. The performance of the proposed design scheme is tested and validated for different modes of RRS against benchmark data obtained from Plant Data Recorder (PDR) and found in close agreement well within the design bounds.

A self-training method based on fast binary bare-bones particle swarm optimization for semi-supervised classification

The generalization performance of self-training methods for semi-supervised classification depends on the selection of pseudo-labeled samples. While multiple variations of self-training methods are developed, strategies for selecting pseudo-labeled samples still suffer from the following challenging issues: a) heavily relying on specific assumptions about geometric and class relationships between different instances; b) parameter dependency; c) failure to effectively eliminate mislabeled pseudo-labeled noisy samples. These issues lead to low robustness and performance deterioration. To select pseudo-labeled samples more effectively and overcome the above-mentioned challenging issues, a self-training method based on fast binary bare-bones particle swarm optimization (ST-F3BPSO) is proposed. The core ideas of ST-F3BPSO are that a) a binary bare-bones particle swarm optimization (F3BPSO) with a new search space reduction strategy, a new particle update mechanism, and a new fitness function is first proposed; b) an F3BPSO-based sample sub-space optimization (SSO–F3BPSO) is second proposed to help ST-F3BPSO select pseudo-labeled samples and eliminate mislabeled pseudo-labeled noisy samples in the iterative self-training process without parameters and assumptions about geometric and class relationships of data. Intensive experiments on benchmark data sets have proven that a) ST-F3BPSO outperforms 7 state-of-the-art non-evolutionary algorithms-based self-training methods and 2 state-of-the-art evolutionary algorithms-based self-training methods in classification accuracy and marco F-measure of 2 popular base classifiers with various ratios of the initial labeled data or the class noise; b) ST-F3BPSO outperforms 2 state-of-the-art evolutionary algorithms-based self-training methods in computational efficiency.

The Incidence and Propensity of Head Acceleration Events in a Season of Men’s and Women’s English Elite-Level Club Rugby Union Matches

ObjectivesTo describe and compare the incidence and propensity of head acceleration events (HAEs) using instrumented mouthguards (iMG) by playing position in a season of English elite-level men’s and women’s rugby union matches.MethodsiMG data were collected for 255 men and 133 women from 1,865 and 807 player-matches, respectively, and synchronised to video-coded match footage. Head peak resultant linear acceleration (PLA) and peak resultant angular acceleration (PAA) were extracted from each HAE. Mean incidence and propensity values were calculated across different recording thresholds for forwards and backs in addition to positional groups (front row, second row, back row, half backs, centres, back three) with 95% confidence intervals (CI) estimated. Significance was determined based on 95% CI not overlapping across recording thresholds.ResultsFor both men and women, HAE incidence was twice as high for forwards than backs across the majority of recording thresholds. HAE incidence and propensity were significantly lower in the women’s game compared to the men’s game. Back-row and front-row players had the highest incidence across all HAE thresholds for men’s forwards, while women’s forward positional groups and men’s and women’s back positional groups were similar. Tackles and carries exhibited a greater propensity to result in HAE for forward positional groups and the back three in the men’s game, and back row in the women’s game.ConclusionThese data offer valuable benchmark and comparative data for future research, HAE mitigation strategies, and management of HAE exposure in elite rugby players. Positional-specific differences in HAE incidence and propensity should be considered in future mitigation strategies.

TransfIGN: A Structure-Based Deep Learning Method for Modeling the Interaction between HLA-A*02:01 and Antigen Peptides.

The intricate interaction between major histocompatibility complexes (MHCs) and antigen peptides with diverse amino acid sequences plays a pivotal role in immune responses and T cell activity. In recent years, deep learning (DL)-based models have emerged as promising tools for accelerating antigen peptide screening. However, most of these models solely rely on one-dimensional amino acid sequences, overlooking crucial information required for the three-dimensional (3-D) space binding process. In this study, we propose TransfIGN, a structure-based DL model that is inspired by our previously developed framework, Interaction Graph Network (IGN), and incorporates sequence information from transformers to predict the interactions between HLA-A*02:01 and antigen peptides. Our model, trained on a comprehensive data set containing 61,816 sequences with 9051 binding affinity labels and 56,848 eluted ligand labels, achieves an area under the curve (AUC) of 0.893 on the binary data set, better than state-of-the-art sequence-based models trained on larger data sets such as NetMHCpan4.1, ANN, and TransPHLA. Furthermore, when evaluated on the IEDB weekly benchmark data sets, our predictions (AUC = 0.816) are better than those of the recommended methods like the IEDB consensus (AUC = 0.795). Notably, the interaction weight matrices generated by our method highlight the strong interactions at specific positions within peptides, emphasizing the model's ability to provide physical interpretability. This capability to unveil binding mechanisms through intricate structural features holds promise for new immunotherapeutic avenues.

A time-averaged method to analyze slender rods moving in tubes

The motion of slender rods in narrow tubes involves the coupling of axial movements and transverse vibrations, in which the transverse vibration exhibits high frequency and chaotic characteristics. These characteristics render the computational cost of the time integration to the motions of rods and tubes expensive. To solve this problem, this paper proposes a novel time-averaged method, which contains two innovations: 1) By time averaging the traditional dynamic equations, the time-averaged dynamic equations describing the rod-tube system are established based on the time-averaged concept used in turbulence problems; 2) Two time-averaged contact models are developed, by fitting the time-averaged sample set using the polishing function and the machine learning, respectively, to construct the relationship between the time-averaged contact gaps and the time-averaged contact forces. The time-averaged method can use a large time step, which is far larger than that required for the time integration of traditional methods, thus reducing the computational cost. Inclined and rolling experiments of the rod-tube system, as well as numerical experiments of the control rod drop in a nuclear reactor, are conducted to validate the accuracy of the time-averaged method. Comparative analyses are carried out between the time-averaged method and six continuous contact models, demonstrating the high computational efficiency of the proposed method. Moreover, the experimental results can provide benchmark data for algorithm verification for scholars studying dynamic contact algorithms.

Interval type-2 fuzzy stochastic configuration networks for soft sensor modeling of industrial processes

Soft sensors have been widely applied to predict key variables that are difficult to measure for industrial process modeling. In this paper, a novel randomized interval type-2 fuzzy neural network with parallel learning, called IT2F-PSCN, is presented for soft sensor modeling of industrial processes. It trains the upper and lower bounds of the interval type-2 fuzzy logic system separately to facilitate type reduction, thereby integrating the fuzzy logic system with stochastic configuration networks. To achieve the appropriate structure and parameters of the model, we develop a two-phase training scheme. In the first phase, a sparse rule interpolation method with stochastic configuration is applied to generate new fuzzy rules. In the second phase, the hidden layer is constructed through parallel stochastic configuration to enhance the nonlinear representational capacity. The validity of IT2F-PSCN is confirmed by a series of experiments, including four benchmark data modelings, simulation on the Tennessee Eastman process, and soft sensor modeling for the slurry grade of the first rougher in a zinc flotation process. The experimental results indicate that the proposed IT2F-PSCN performs favorably compared with other methods.

Proposal for standardized prenatal assessment of fetal open dysraphisms by the European reference network for Intellectual disability, TeleHealth, Autism and Congenital Anomalies (ITHACA) and eUROGEN.

Open dysraphisms, that is, myelomeningocele and myeloschisis, are rare diseases associated with a risk of severe disability, including lower limb motor and sensory deficiency, sphincter deficiency, and potential intellectual deficiency. Open dysraphism is diagnosed in Europe in 93.5% of cases. In case of suspicion of fetal open dysraphism, a detailed fetal morphologic assessment is required to confirm the diagnosis and exclude associated structural anomalies, as well as genetic assessment. In case of isolated fetal open dysraphism, assessment of prognosis is based on fetal imaging including the level of the lesion, the presence or not of a sac, the presence and nature of intra cranial anomalies, and the anatomical and functional evaluation of the lower extremities. Based on these biomarkers, a personalized prognosis as well as comprehensive information about prenatal management alternatives will allow parents to decide on further management options. Standardization of prenatal assessment is essential to compare outcomes with benchmark data and make assessment of surgical innovation possible. Herein, we propose a protocol for the standardized ultrasound assessment of fetuses with isolated open dysraphism.

MDF-DTA: A Multi-Dimensional Fusion Approach for Drug-Target Binding Affinity Prediction.

Drug-target affinity (DTA) prediction is an important task in the early stages of drug discovery. Traditional biological approaches are time-consuming, effort-consuming, and resource-consuming due to the large size of genomic and chemical spaces. Computational approaches using machine learning have emerged to narrow down the drug candidate search space. However, most of these prediction models focus on single feature encoding of drugs and targets, ignoring the importance of integrating different dimensions of these features. We propose a deep learning-based approach called Multi-Dimensional Fusion for Drug Target Affinity Prediction (MDF-DTA) incorporating different dimensional features. Our model fuses 1D, 2D, and 3D representations obtained from different pretrained models for both drugs and targets. We evaluated MDF-DTA on two standard benchmark data sets: DAVIS and KIBA. Experimental results show that MDF-DTA outperforms many state-of-the-art techniques in the DTA task across both data sets. Through ablation studies and performance evaluation metrics, we evaluate the importance of individual representations and the impact of each representation on MDF-DTA.

Stereologically corrected particle size distributions for polymer-mounted additive manufacturing powders

Well-defined particle size distributions are required for good flowability and powder packing properties of additive manufacturing powders. Mounting powders within a polymer and using standard metallurgical preparation techniques to cross-section and prepare powder particles for optical analysis allows for simple characterisation processes. However, measured diameters of cross-sectioned particles are typically underestimates of actual particle diameters and hence require stereological correction. The effectiveness of three stereological corrections are investigated in this work, namely the Scheil-Schwartz-Saltykov method, the Goldsmith-Cruz-Orive method and a Finite Difference Method. These methods are investigated against plasma-atomised, gas-atomised and ultrasonically processed Ti-6Al-4V powders. The corrected outputs are compared to laser size diffraction, benchmark data for each powder. Although all three stereological corrections produce improved estimations of the particle size distributions, the Finite Difference Method is recommended producing cumulative mean absolute error values of 2.4%, 3.1% and 7.5% for the plasma-atomised, gas-atomised and ultrasonically processed powders respectively.

New approach for learning structured graph with Laplacian rank constraint

Many existing graph-clustering methods get results in a two-stage manner, including constructing a graph from data and partitioning it. It always leads to sub-optimal performances. To address the drawbacks, imposing rank constraint on the graph’s Laplacian matrix is an effective way. It can learn a structured graph that connected components are exactly equal to the cluster numbers. According to separate connected components, it directly obtains clustering assignments. However, previous works heuristically solve it during the optimization without any theory guarantee. To handle this issue, we propose a novel solver to optimize this problem with theoretical advantages, enabling the structured bipartite graphs to directly indicate clustering results. Initially, we discover that pairwise and bipartite graphs exhibit the same connected components after undergoing a specific operation. Then, we derive an efficient algorithm to optimize two different clustering models with rank constraints based on this property. Moreover, our proposed method exhibits linear computational complexity to the data scale. Extensive empirical results on both synthetic and real benchmark data demonstrate that the proposed method outperforms existing methods.

Sequencing whole genomes of the West Javanese population in Indonesia reveals novel variants and improves imputation accuracy.

Existing genotype imputation reference panels are mainly derived from European populations, limiting their accuracy in non-European populations. To improve imputation accuracy for Indonesians, the world's fourth most populous country, we combined Whole Genome Sequencing (WGS) data from 227 West Javanese individuals with East Asian data from the 1000 Genomes Project. This created three reference panels: EAS 1KGP3 (EASp), Indonesian (INDp), and a combined panel (EASp+INDp). We also used ten West-Javanese samples with WGS and SNP-typing data for benchmarking. We identified 1.8 million novel single nucleotide variants (SNVs) in the West Javanese population, which, while similar to the East Asians, are distinct from the Central Indonesian Flores population. Adding INDp to the EASp reference panel improved imputation accuracy (R2) from 0.85 to 0.90, and concordance from 87.88% to 91.13%. These findings underscore the importance of including Indonesian genetic data in reference panels, advocating for broader WGS of diverse Indonesian populations to enhance genomic studies.

A hybrid swarm intelligence algorithm for region-based image fusion

This paper proposes a novel multi-hybrid algorithm named DHPN, using the best-known properties of dwarf mongoose algorithm (DMA), honey badger algorithm (HBA), prairie dog optimizer (PDO), cuckoo search (CS), grey wolf optimizer (GWO) and naked mole rat algorithm (NMRA). It follows an iterative division for extensive exploration and incorporates major parametric enhancements for improved exploitation operation. To counter the local optima problems, a stagnation phase using CS and GWO is added. Six new inertia weight operators have been analyzed to adapt algorithmic parameters, and the best combination of these parameters has been found. An analysis of the suitability of DHPN towards population variations and higher dimensions has been performed. For performance evaluation, the CEC 2005 and CEC 2019 benchmark data sets have been used. A comparison has been performed with differential evolution with active archive (JADE), self-adaptive DE (SaDE), success history based DE (SHADE), LSHADE-SPACMA, extended GWO (GWO-E), jDE100, and others. The DHPN algorithm is also used to solve the image fusion problem for four fusion quality metrics, namely, edge-based similarity index (QAB/F\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$Q^{AB/F}$$\\end{document}), sum of correlation difference (SCD), structural similarity index measure (SSIM), and artifact measure (NAB/F\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$N^{AB/F}$$\\end{document}). The average QAB/F=0.765508\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$Q^{AB/F} = 0.765508$$\\end{document}, SCD=1.63185\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$SCD = 1.63185$$\\end{document}, SSIM=0.726317\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$SSIM = 0.726317$$\\end{document}, and NAB/F=0.006617\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$N^{AB/F} = 0.006617$$\\end{document} shows the best combination of results obtained by DHPN with respect to the existing algorithms such as DCH, CBF, GTF, JSR and others. Experimental and statistical Wilcoxon’s and Friedman’s tests show that the proposed DHPN algorithm performs significantly better in comparison to the other algorithms under test.

Hierarchical Autoencoder-Based Lossy Compression for Large-Scale High-Resolution Scientific Data

Lossy compression has become essential an important technique to reduce data size in many domains. This type of compression is especially valuable for large-scale scientific data, whose size ranges up to several petabytes. Although Autoencoder-based models have been successfully leveraged to compress images and videos, such neural networks have not widely gained attention in the scientific data domain. Our work presents a neural network that not only significantly compresses large-scale scientific data, but also maintains high reconstruction quality. The proposed model is tested with scientific benchmark data available publicly and applied to a large-scale high-resolution climate modeling data set. Our model achieves a compression ratio of 140 on several benchmark data sets without compromising the reconstruction quality. 2D simulation data from the High-Resolution Community Earth System Model (CESM) Version 1.3 over 500 years are also being compressed with a compression ratio of 200 while the reconstruction error is negligible for scientific analysis.

Towards a framework for reliable performance evaluation in defect prediction

Enhancing software reliability, dependability, and security requires effective identification and mitigation of defects during early development stages. Software defect prediction (SDP) models have emerged as valuable tools for this purpose. However, there is currently a lack of consensus in evaluating the predictive performance of newly proposed models, which hinders accurate measurement of progress and can lead to misleading conclusions. To tackle this challenge, we present MATTER (a fraMework towArd a consisTenT pErformance compaRison), which aims to provide reliable and consistent performance comparisons for SDP models. MATTER incorporates three key considerations. First, it establishes a global reference point, ONE (glObal baseliNe modEl), which possesses the 3S properties (Simplicity in implementation, Strong predictive ability, and Stable prediction performance), to serve as the baseline for evaluating other models. Second, it proposes using the SQA-effort-aligned threshold setting to ensure fair performance comparisons. Third, it advocates for consistent performance evaluation by adopting a set of core performance indicators that reflect the practical value of prediction models in achieving tangible progress. Through the application of MATTER to the same benchmark data sets, researchers and practitioners can obtain more accurate and meaningful insights into the performance of defect prediction models, thereby facilitating informed decision-making and improving software quality. When evaluating representative SDP models from recent years using MATTER, we surprisingly observed that: none of these models demonstrated a notable enhancement in prediction performance compared to the simple baseline model ONE. In future studies, we strongly recommend the adoption of MATTER to assess the actual usefulness of newly proposed models, promoting reliable scientific progress in defect prediction.

Development and Evaluation of a Two-Staged 3D Keypoint Based Workflow for the Co-Registration of Unstructured Multi-Temporal and Multi-Modal 3D Point Clouds

Abstract. Robust and automated point cloud registration methods are required in many geoscience applications using multi-temporal and multi-modal 3D point clouds. Therefore, a 3D keypoint-based coarse registration workflow has been implemented, utilizing the ISS keypoint detector and 3DSmoothNet descriptor. This paper contributes to keypoint-based registration research through variations of the standard workflow proposed in the literature, applying a two-staged strategy of global and local keypoint matching as well as prototypical keypoint projection and fine registration based on ICP. Further, by testing the utilized detector and descriptor on unstructured, multi-temporal and multi-source point clouds with variations in point cloud density, generalization ability is tested outside benchmark data. Therefore, data of the Bøverbreen glacier in Jotunheimen, Norway has been acquired in 2022 and 2023, deploying UAV-based image matching and terrestrial laser scanning. The results show good performance of the implemented robust matching algorithm PROSAC, requiring fewer iterations than the well-known RANSAC approach, but solving the rigid body transformation with TEASER++ is faster and more robust to outliers without demanding pre-knowledge of the data. Further, the results identify the keypoint detection as most limiting factor in speed and accuracy. Summarizing, keypoint-based coarse registration on low density point clouds, applying a global and local matching strategy and transformation estimation using TEASER++ is recommended. Keypoint projection shows potential, increasing number and precision in low density clouds, but has to be more robust. Further research needs to be carried out, focusing on identifying a fast and robust keypoint detector.

GestaltMatcher Database - A global reference for facial phenotypic variability in rare human diseases.

The most important factor that complicates the work of dysmorphologists is the significant phenotypic variability of the human face. Next-Generation Phenotyping (NGP) tools that assist clinicians with recognizing characteristic syndromic patterns are particularly challenged when confronted with patients from populations different from their training data. To that end, we systematically analyzed the impact of genetic ancestry on facial dysmorphism. For that purpose, we established the GestaltMatcher Database (GMDB) as a reference dataset for medical images of patients with rare genetic disorders from around the world. We collected 10,980 frontal facial images - more than a quarter previously unpublished - from 8,346 patients, representing 581 rare disorders. Although the predominant ancestry is still European (67%), data from underrepresented populations have been increased considerably via global collaborations (19% Asian and 7% African). This includes previously unpublished reports for more than 40% of the African patients. The NGP analysis on this diverse dataset revealed characteristic performance differences depending on the composition of training and test sets corresponding to genetic relatedness. For clinical use of NGP, incorporating non-European patients resulted in a profound enhancement of GestaltMatcher performance. The top-5 accuracy rate increased by +11.29%. Importantly, this improvement in delineating the correct disorder from a facial portrait was achieved without decreasing the performance on European patients. By design, GMDB complies with the FAIR principles by rendering the curated medical data findable, accessible, interoperable, and reusable. This means GMDB can also serve as data for training and benchmarking. In summary, our study on facial dysmorphism on a global sample revealed a considerable cross ancestral phenotypic variability confounding NGP that should be counteracted by international efforts for increasing data diversity. GMDB will serve as a vital reference database for clinicians and a transparent training set for advancing NGP technology.

Physicochemical and microbiological assessment of multi‐village drinking water source in diarrheal hotspot areas of north Shoa zone, Amhara region, Ethiopia

AbstractQuality water is essential to people's health and social and economic well‐being. Evaluation of the quality of the water sources provides benchmark data on quality status and insights into the development of further protective measures. A laboratory‐based cross‐sectional study design was conducted in the diarrheal hotspot area of the North Shewa zone. The contamination risks of water sources were assessed using the World Health Organization (WHO) sanitary inspection checklist. A grab water sample was collected from 138 multi‐village drinking water sources according to WHO guidelines. The collected sample was processed for physicochemical and microbiological analysis. Data were recorded and analyzed using SPSS version 25 software. The inspection survey indicated there was no proper handling of the water sources. The water temperature range was between 7 and 32°C, while the turbidity values ranged from 1.8 to 6 NTU. Electrical conductivity, pH, and total dissolved solutes were 100% within the acceptable limits of WHO and the Ethiopian Ministry of Health (EMoH) water quality guidelines. However, only (77/138, 55.79%) and (101/138, 73.29%) drinking water sources were within the acceptable range of temperature and turbidity, respectively. The mean bacteriological counts in multi‐village drinking water sources were a mean value of 72.14, 29.78, 21.09, and 15.64 for TMC, TCC, FC, and FSC, respectively. A total of (19/138, 13.8%) drinking water samples were positive for total coliform (Tc) and/or fecal coliforms (Fc). The remaining (119/138, 86.2%) water samples were bacteriologically potable. The physicochemical quality of the drinking water sources was consistent with WHO and national water quality standards, except that turbidity exceeded the acceptable range. The results also showed that some water sources were contaminated with fecal and total coliform, which was supported by an inspection survey in which most water sources were poorly protected. These research findings can serve as a valuable evidence base for informing policy decisions and guiding practical interventions aimed at ensuring access to safe drinking water in diarrheal hotspot areas.

Multi-dimensional classification via class space fusion and comprehensive label correlations

Multi-dimensional Classification (MDC) is a new multi-output learning paradigm, where each instance in this framework is annotated with labels from multiple semantic class spaces. The vital challenge in MDC problem is how to address the heterogeneity of output space. Existing methods typically focus on the decomposition of output space, rarely consider the comprehensive fine-grained label correlations and the exploration of the intrinsic structure of the output space. And the local label correlations, which only exist within specific groups of instances, remain largely untapped in existing MDC methods. Therefore, we focus on tackling these above problems in this paper by simultaneously conducting label space fusion and considering the comprehensive label correlations to fully exploit the latent discriminative information hidden in the output space. Heuristically, we utilize low-rank representation method to achieve label space fusion to capture the intrinsic structure and implicit global correlation of label space. Then the predictive MDC model is extrapolated from the reconstructed instances equipped with the fused label space. Moreover, the topological structure information of samples is fully taken advantage of for MDC model establishment. Benefiting from these strategies, the heterogeneous label space can be fully excavated to boost the performance of MDC. Empirically, comparative experiments are conducted over several multi-dimensional benchmark data sets, and corresponding experimental results firmly illustrate that the proposed algorithm can effectively solve the MDC problem and outperform state-of-the-art methods.

QupKake: Integrating Machine Learning and Quantum Chemistry for Micro-pKa Predictions.

Accurate prediction of micro-pKa values is crucial for understanding and modulating the acidity and basicity of organic molecules, with applications in drug discovery, materials science, and environmental chemistry. This work introduces QupKake, a novel method that combines graph neural network models with semiempirical quantum mechanical (QM) features to achieve exceptional accuracy and generalization in micro-pKa prediction. QupKake outperforms state-of-the-art models on a variety of benchmark data sets, with root-mean-square errors between 0.5 and 0.8 pKa units on five external test sets. Feature importance analysis reveals the crucial role of QM features in both the reaction site enumeration and micro-pKa prediction models. QupKake represents a significant advancement in micro-pKa prediction, offering a powerful tool for various applications in chemistry and beyond.