Input Data Formats Research Articles

Novel R package to quantify and monetize burden of disease attributable to air pollution and noise

Abstract Background Ambient air pollution and noise substantially impact public health and the economy. Different methods to quantify these impacts are described in the literature. Objectives Within the European project BEST-COST (Burden of disease-based methods for estimating the socio-economic cost of environmental stressors), we aim to develop an open-source R package to quantify and monetise the disease burden attributable to air pollution and noise, including the impact of social inequalities. Methods The developed code will allow for different calculation pathways including: single baseline health data vs. age-specific estimates from life tables; relative and absolute risk; scenario comparison based on the population attributable fraction vs. population impact fraction; single-pollutant vs. correlated exposures; and outdoor vs. indoor air pollution. Moreover, the package can digest a variety of input data formats for the exposure-response function (e.g. relative risk with fixed shape vs. user-defined function) and exposure data (e.g. population-weighted mean vs. categorical distribution, spatial data). Eligible impact metrics will include morbidity incidence and prevalence, number of deaths, years of life lost, and years lived with disability. Finally, the R package will enable quantifying social inequities (using a novel multiple deprivation index) and monetising the attributable disease burden (using a state-of-the-art approach). Results During development, the R package will be tested in BEST-COST case studies in 5 European countries (BE, EE, FR, NO, PT), compared with existing tools, and discussed with key users in a workshop. The final R package will be available on GitHub in 2026. Conclusions This tool will allow the quantification and monetisation of the health impact of air pollution and noise. The R package will be a flexible programming resource that can be used as a standalone or combined with existing tools to build a more solid basis for evidence-based policy making. Key messages • This open-source tool will allow the quantification and monetisation of the health impact of air pollution and noise, including the impact of social inequalities. • The R package will be a flexible programming resource that can be used as a standalone or combined with existing tools to build a more solid basis for evidence-based policy making.

Predicting host species susceptibility to influenza viruses and coronaviruses using genome data and machine learning: a scoping review.

Predicting which species are susceptible to viruses (i.e., host range) is important for understanding and developing effective strategies to control viral outbreaks in both humans and animals. The use of machine learning and bioinformatic approaches to predict viral hosts has been expanded with advancements in in-silico techniques. We conducted a scoping review to identify the breadth of machine learning methods applied to influenza and coronavirus genome data for the identification of susceptible host species. The protocol for this scoping review is available at https://hdl.handle.net/10214/26112. Five online databases were searched, and 1,217 citations, published between January 2000 and May 2022, were obtained, and screened in duplicate for English language and in-silico research, covering the use of machine learning to identify susceptible species to viruses. Fifty-three relevant publications were identified for data charting. The breadth of research was extensive including 32 different machine learning algorithms used in combination with 29 different feature selection methods and 43 different genome data input formats. There were 20 different methods used by authors to assess accuracy. Authors mostly used influenza viruses (n = 31/53 publications, 58.5%), however, more recent publications focused on coronaviruses and other viruses in combination with influenza viruses (n = 22/53, 41.5%). The susceptible animal groups authors most used were humans (n = 57/77 analyses, 74.0%), avian (n = 35/77 45.4%), and swine (n = 28/77, 36.4%). In total, 53 different hosts were used and, in most publications, data from multiple hosts was used. The main gaps in research were a lack of standardized reporting of methodology and the use of broad host categories for classification. Overall, approaches to viral host identification using machine learning were diverse and extensive.

Cumulative prospect theory under different types of input data for public health resilience assessment during natural disasters

Despite the significance of health and the threats natural disasters pose to public health and the well-being of the affected communities, comprehensive research that explores critical factors and indicators that measure health implications brought about by disasters is underdeveloped in the literature. The primary objective of this study is twofold: (1) to develop a list of indicators that assess health-related impacts during disasters through a literature survey, and (2) to create a “public health resilience index” that measures the resilience of affected communities with a case study in Southern Cebu, Philippines. A hybrid model based on the fuzzy stepwise weight assessment ratio analysis and the extended cumulative prospect theory was deployed to advance these objectives. The proposed model considers subjective judgment and cognitive biases while exhibiting high scalability and flexibility and accommodating diverse data input formats. Results revealed that the promptness of response, the allocated budget for humanitarian aid and services, the availability of drinking water per household, the number of personnel assigned for humanitarian aid, and the location of water distribution points are highly prioritized during natural disasters. On the other hand, among the 21 municipalities under consideration, 10 demonstrated strong performance, while the other 10 exhibited poor performance, leaving one municipality in the middle of both extremes. Sensitivity and comparative analyses show that the proposed hybrid model is not sensitive to model parameter changes. The findings of this study would aid decision-makers in developing initiatives aimed at optimizing resources and efforts, mitigating risks, and enhancing the overall health resilience of local communities in the onslaught of natural disasters.

FUME 2.0 – Flexible Universal processor for Modeling Emissions

Abstract. This paper introduces FUME 2.0, an open-source emission processor for air quality modeling, and documents the software structure, capabilities, and sample usage. FUME provides a customizable framework for emission preparation tailored to user needs. It is designed to work with heterogeneous emission inventory data, unify them into a common structure, and generate model-ready emissions for various chemical transport models (CTMs). Key features include flexibility in input data formats, support for spatial and temporal disaggregation, chemical speciation, and integration of external models like MEGAN. FUME employs a modular Python interface and PostgreSQL/PostGIS backend for efficient data handling. The workflow comprises data import, geographical transformation, chemical and temporal disaggregation, and output generation steps. Outputs for mesoscale CTMs CMAQ, CAMx, and WRF-Chem and the large-eddy-simulation model PALM are implemented along with a generic NetCDF format. Benchmark runs are discussed on a typical configuration with cascading domains, with import and preprocessing times scaling near-linearly with grid size. FUME facilitates air quality modeling from continental to regional and urban scales by enabling effective processing of diverse inventory datasets.

Fast constrained optimization for cloth simulation parameters from static drapes

AbstractWe present a cloth simulation parameter estimation method that integrates the flexibility of global optimization with the speed of neural networks. While global optimization allows for varied designs in objective functions and specifying the range of optimization variables, it requires thousands of objective function evaluations. Each evaluation, which involves a cloth simulation, is computationally demanding and impractical time‐wise. On the other hand, neural network learning methods offer quick estimation results but face challenges such as the need for data collection, re‐training when input data formats change, and difficulties in setting constraints on variable ranges. Our proposed method addresses these issues by replacing the simulation process, typically necessary for objective function evaluations in global optimization, with a neural network for inference. We demonstrate that, once an estimation model is trained, optimization for various objective functions becomes straightforward. Moreover, we illustrate that it is possible to achieve optimization results that reflect the intentions of expert users through visualization of a wide optimization space and the use of range constraints.

Improving respiratory signal prediction with a deep neural network and simple changes to the input and output data format

Objective. To improve respiratory gating accuracy and radiation treatment throughput, we developed a generalized model based on a deep neural network (DNN) for predicting any given patient’s respiratory motion. Approach. Our model uses long short-term memory (LSTM) based on a recurrent neural network (RNN), and improves upon common techniques. The first improvement is that the data input is not a one-dimensional sequence, but two-dimensional block data. This shortens the input sequence length, reducing computation time. Second, the output is not a scalar, but a sequence prediction. This increases the amount of available data, allowing improved prediction accuracy. For training and evaluation of our model, 434 sets of real-time position management data were retrospectively collected from clinical studies. The data were separated in a ratio of 4:1, with the larger set used for training models and the remaining set used for testing. We measured the accuracy of respiratory signal prediction and amplitude-based gating with prediction windows equaling 133, 333, and 533 ms. This new model was compared with the original LSTM and a non-recurrent DNN model. Main results. The mean absolute errors with the prediction window at 133, 333 and 533 ms were 0.036, 0.084, 0.119 with our model; 0.049, 0.14, 0.246 with the original LSTM-based model; and 0.041, 0.119, 0.16 with the non-recurrent DNN model, respectively. The computation time were 0.66 ms with our model; 0.63 ms the original LSTM-based model; 1.60 ms the non-recurrent DNN model, respectively. The accuracies of amplitude-based gating with the same prediction window settings and a duty cycle of approximately 50% were 98.3%, 95.8% and 92.7% with our model, 97.6%, 93.9% and 87.2% with the original LSTM-based model; and 97.9%, 94.3% and 89.5% with the non-recurrent DNN model, respectively. Significance. Our RNN algorithm for respiratory signal prediction successfully estimated tumor positions. We believe it will be useful in respiratory signal prediction technology.

A novel hybrid forecasting model with feature selection and deep learning for wind speed research

AbstractAccurate wind speed prediction is of great importance for the operation of wind farms, and extensive efforts have been made to develop effective forecasting methods in this regard. However, the feature selection of data input as well as optimization of deep learning models have received comparatively less attention, leading to unreliable forecasting results. This research proposes a novel hybrid model that integrates data preprocessing, feature selection, and optimized forecasting for improved wind speed prediction. Specifically, a powerful preprocessing technique is utilized to reduce data noise disturbances, while an innovative two‐stage feature selection is designed to achieve the optimal input data format for forecasting purposes. Moreover, a hybrid forecasting module based on long‐short term memory, which is optimized by the Bayesian optimization algorithm, has been developed to enhance the efficiency and reliability of the model. The empirical study used 10‐min interval wind speed data of four seasons for presentation and evaluation results demonstrated its superior performance in effectively learning the volatility and irregularity features of wind speed series, which established a solid foundation for practical applications in wind power systems.

Deep learning-enabled detection of hypoxic-ischemic encephalopathy after cardiac arrest in CT scans: a comparative study of 2D and 3D approaches.

To establish a deep learning model for the detection of hypoxic-ischemic encephalopathy (HIE) features on CT scans and to compare various networks to determine the best input data format. 168 head CT scans of patients after cardiac arrest were retrospectively identified and classified into two categories: 88 (52.4%) with radiological evidence of severe HIE and 80 (47.6%) without signs of HIE. These images were randomly divided into a training and a test set, and five deep learning models based on based on Densely Connected Convolutional Networks (DenseNet121) were trained and validated using different image input formats (2D and 3D images). All optimized stacked 2D and 3D networks could detect signs of HIE. The networks based on the data as 2D image data stacks provided the best results (S100: AUC: 94%, ACC: 79%, S50: AUC: 93%, ACC: 79%). We provide visual explainability data for the decision making of our AI model using Gradient-weighted Class Activation Mapping. Our proof-of-concept deep learning model can accurately identify signs of HIE on CT images. Comparing different 2D- and 3D-based approaches, most promising results were achieved by 2D image stack models. After further clinical validation, a deep learning model of HIE detection based on CT images could be implemented in clinical routine and thus aid clinicians in characterizing imaging data and predicting outcome.

TCRosetta: An Integrated Analysis and Annotation Platform for T-cell Receptor Sequences.

T cells and T-cell receptors (TCRs) are essential components of the adaptive immune system. Characterization of the TCR repertoire offers a promising and highly informative source for understanding the functions of T cells in the immune response and immunotherapy. Although TCR repertoire studies have attracted much attention, there are few online servers available for TCR repertoire analysis, especially for TCR sequence annotation or advanced analyses. Therefore, we developed TCRosetta, a comprehensive online server that integrates analytical methods for TCR repertoire analysis and visualization. TCRosetta combines general feature analysis, large-scale sequence clustering, network construction, peptide-TCR binding prediction, generation probability calculation, and k-mer motif analysis for TCR sequences, making TCR data analysis as simple as possible. The TCRosetta server accepts multiple input data formats and can analyze ∼ 20,000 TCR sequences in less than 3 min. TCRosetta is the most comprehensive web server available for TCR repertoire analysis and is freely available at https://guolab.wchscu.cn/TCRosetta/.

Multi-MSIProcessor: Data Visualizing and Analysis Software for Spatial Metabolomics Research.

Mass spectrometry imaging (MSI) has emerged as a revolutionary analytical strategy in biomedical research for molecular visualization. By linking the characterization of functional metabolites with tissue architecture, it is now possible to reveal unknown biological functions of tissues. However, due to the complexity and high dimensionality of MSI data, mining bioinformatics-related peaks from batch MSI data sets and achieving complete spatially resolved metabolomics analysis remain a great challenge. Here, we propose novel MSI data processing software, Multi-MSIProcessor (MMP), which integrates the data read-in, MSI visualization, processed data preservation, and biomarker discovery functions. The MMP focuses on the AFADESI-MSI data platform but also supports mzXML and imzmL data input formats for compatibility with data generated by other MSI platforms such as MALDI/SIMS-MSI. MMP enables deep mining of batch MSI data and has flexible adaptability with the source code opened that welcomes new functions and personalized analysis strategies. Using multiple clinical biosamples with complex heterogeneity, we demonstrated that MMP can rapidly establish complete MSI analysis workflows, assess batch sample data quality, screen and annotate differential MS peaks, and obtain abnormal metabolic pathways. MMP provides a novel platform for spatial metabolomics analysis of multiple samples that could meet the diverse analysis requirements of scholars.

Time-Aware Smart City Services Based on QoS Prediction: A Contrastive Learning Approach

Smart cities are designed to satisfy the needs of residents and improve their quality of life by providing a wide range of smart city services. The key to the efficient operation of smart city services is accurate forecast of the missing QoS (Quality of Service).. At present, many approaches utilize the context information of users and services, such as geographic location and network location, to somewhat increase the prediction accuracy and forecast the missing QoS values.. However, because the network conditions and server status are unpredictable, time is also considered as one of the important factors affecting QoS prediction, which brings more challenges as follows: higher data dimension, more complex data characteristics and higher data sparsity. To overcome these challenges,z we suggest an approach for time-aware Web service QoS prediction based on contrastive learning(named CLpred). CLpred utilizes a sequential data input format for QoS data and models these QoS sequences through Transformer encoder with contrastive learning framework. Therefore, it can downscale QoS data and extract a more efficient representation in complex QoS data. Furthermore, it makes it possible to apply data augmentation methods to address these probelms of data sparsity. In order to prove the superiority of the this approach, particularly inside the presence of extremely high data sparsity, extensive tests are carried out on the well-known service QoS data set WSDREAM.

MalbacR: A Package for Standardized Implementation of Batch Correction Methods for Omics Data.

Mass spectrometry is a powerful tool for identifying and analyzing biomolecules such as metabolites and lipids in complex biological samples. Liquid chromatography and gas chromatography mass spectrometry studies quite commonly involve large numbers of samples, which can require significant time for sample preparation and analyses. To accommodate such studies, the samples are commonly split into batches. Inevitably, variations in sample handling, temperature fluctuation, imprecise timing, column degradation, and other factors result in systematic errors or biases of the measured abundances between the batches. Numerous methods are available via R packages to assist with batch correction for omics data; however, since these methods were developed by different research teams, the algorithms are available in separate R packages, each with different data input and output formats. We introduce the malbacR package, which consolidates 11 common batch effect correction methods for omics data into one place so users can easily implement and compare the following: pareto scaling, power scaling, range scaling, ComBat, EigenMS, NOMIS, RUV-random, QC-RLSC, WaveICA2.0, TIGER, and SERRF. The malbacR package standardizes data input and output formats across these batch correction methods. The package works in conjunction with the pmartR package, allowing users to seamlessly include the batch effect correction in a pmartR workflow without needing any additional data manipulation.

Novel Emotion Recognition System Using Edge Computing Platform with Deep Convolutional Networks

Human faces have been naturally viewed as a central part in each image. One interesting task is to classify each face into different categories based on the emotion shown in the facial expression. In addition, an awareness of emotion during work on a project and how affective states are presented in the communication style might help system developers work more effectively, thus improving the performance of a collaborative team. Currently, the feasibility and portability of emotion recognition in the platform with Raspberry PI are insufficient. Hereby, a novel emotion recognition system in real time using the edge computing platform with deep learning has been implemented successfully. The feature values of objects are calculated by a high computing processor on the embedded platform. When an object with the matching features is detected, it is drawn as a rectangular bounding box and the results are displayed on the screen. In the proposed system, it first annotates the image datasets and saves them in the corresponding input data format for model training. Thus, the You Only Look Once (YOLOv5) model has been employed for training because it is a state-of-the-art object detection system. In other words, a fast and accurate emotion recognition is the main benefits of choosing YOLOv5 model. Then, the correctly trained YOLOv5 model file is loaded into an edge computing platform; and the feature values of objects are analyzed by a high computing processor. Finally, the experimental results show that the promising mean Average Precision (mAP), 92.6%, and recognition speed in Frames Per Second (FPS), 40, are obtained, which outperforms other existing systems.

Benchmarking and survey of explanation methods for black box models

The rise of sophisticated black-box machine learning models in Artificial Intelligence systems has prompted the need for explanation methods that reveal how these models work in an understandable way to users and decision makers. Unsurprisingly, the state-of-the-art exhibits currently a plethora of explainers providing many different types of explanations. With the aim of providing a compass for researchers and practitioners, this paper proposes a categorization of explanation methods from the perspective of the type of explanation they return, also considering the different input data formats. The paper accounts for the most representative explainers to date, also discussing similarities and discrepancies of returned explanations through their visual appearance. A companion website to the paper is provided as a continuous update to new explainers as they appear. Moreover, a subset of the most robust and widely adopted explainers, are benchmarked with respect to a repertoire of quantitative metrics.

Engineering Applications of Artificial Intelligence in Mechanical Design and Optimization

This study offers a complete analysis of the use of deep learning or machine learning, as well as precise recommendations on how these methods could be used in the creation of machine components and nodes. The examples in this thesis are intended to identify areas in mechanical design and optimization where this technique could be widely applied in the future, benefiting society and advancing the current state of modern mechanical engineering. The review begins with a discussion on the workings of artificial intelligence, machine learning, and deep learning. Different techniques, classifications, and even comparisons of each method are described in detail. The most common programming languages, frameworks, and software used in mechanical engineering for this problem are gradually introduced. Input data formats and the most common datasets that are suitable for the field of machine learning in mechanical design and optimization are also discussed. The second half of the review describes the current use of machine learning in several areas of mechanical design and optimization, using specific examples that have been investigated by researchers from around the world. Further research directions on the use of machine learning and neural networks in the fields of mechanical design and optimization are discussed.

Structural damage severity classification from time-frequency acceleration data using convolutional neural networks

Structural damage identification involves interpretation of vibration measurements to identify patterns that are indicative of changes in structural characteristics. Identification of such patterns using machine learning (ML) algorithms is a primary task in data-driven structural health monitoring. However, providing ML algorithms with features that are sensitive to damage has always been a challenge for accurate damage detection. In recent years, deep Convolutional Neural Networks (CNNs) proved to be versatile and powerful tools to identify the underlying patterns directly from low-level raw data. This study explores the applicability of CNNs to damage severity classification. A new format of input data for CNN damage identifiers is proposed based on time–frequency representations of acceleration data from multiple sensors. First, Continuous Wavelet Transformation (CWT) of acceleration response is employed to derive the time–frequency data, then, the results of transformations from multiple accelerometers are stored in separate channels creating a three-dimensional block of data. Such input data provide a CNN with structural information that expands into time, frequency, and spatial domains. To evaluate the accuracy of such a CNN-based classifier, a dataset comprised of free vibration response of a concrete beam under impact hammer tests is utilized. It is shown that a CNN trained with CWT data can successfully classify various severity of the damage, from minor to severe, with 100% accuracy. Also, this study examines the sensitivity of the CNN classifier to the number of training samples. It is demonstrated that the accuracy of such a network has a relatively lower sensitivity to the number of training samples and/or the number of measurement points to the degree that it maintains an F1-score above 0.813 when trained with data from one impact point and one sensor. On the other hand, for the case of a CNN classifier trained directly with time-series acceleration data the value of the F1-score drops to 0.590. Moreover, when compared with a multilayer perceptron trained with the extracted modal properties, it is illustrated that CNN classifiers have a better capability in capturing key features from the measurement, and thus produce more accurate predictions. Therefore, the combination of CNN classifiers with time–frequency data from multiple sensors results in damage identifiers that are less sensitive to sample size and more robust to changes in excitations and measurement points.

Gated recurrent unit-enhanced deep convolutional neural network for real-time industrial process fault diagnosis

When deep learning-based models are employed for the fault diagnosis of chemical processes, problems of poor calculation accuracy and efficiency often occur in the scenarios of high-dimensional, nonlinear, and time-varying data, which affects the overall robustness of the fault diagnosis model. This study proposes a novel Gated Recurrent Unit (GRU) - enhanced deep convolutional neural network (EDCNN) model for the improved fault detection and diagnosis of chemical processes. In the GRU-EDCNN model, a maximum smooth function (MSF) is developed and presented to replace the classical activation function for better matching the input data format, which can significantly improve the calculation accuracy and the overall efficiency of DCNN models. Moreover, the convolutional layers in DCNN are optimized by a decentralized convolutional structure, thereby reducing the problem of parameter redundancy. The issue of gradient disappearance is tackled by the embedment of GRU, whose ability to control time series features and gateway information can ensure that no overfitting occurs in the GRU-EDCNN training processes. In two case studies, the GRU-EDCNN model was applied to the benchmark Tennessee Eastman (TE) process and an acid gas absorption process, and the corresponding data of fault diagnosis rate (FDR), false positive rate (FPR), and fault diagnosis time (FDT) of the GRU-EDCNN model were analyzed and compared with those of the other deep learning-based models, verifying the effectiveness of the GRU-EDCNN model for fault diagnosis in both simulated and real-time industrial processes.

A Spatiotemporal Deep Learning Approach for Urban Pluvial Flood Forecasting with Multi-Source Data

This study presents a deep-learning-based forecast model for spatial and temporal prediction of pluvial flooding. The developed model can produce the flooding situation for the upcoming time steps as a sequence of flooding maps. Thus, a dynamic overview of the forthcoming flooding situation is generated to support the decision of crisis management actors. The influence of different input data, data formats, and model setups on the prediction results was investigated. Data from multiple sources were considered as follows: precipitation information, spatial information, and an overflow forecast. In addition, models with different layers and network architectures such as convolutional layers, graph convolutional layers, or generative adversarial networks (GANs) were considered and evaluated. The data required to train and test the models were generated using a coupled hydrodynamic 1D/2D model. The model setup with the inclusion of all available input variables and an architecture with graph convolutional layers presented, in general, the best results in terms of root mean square error (RMSE) and critical success index (CSI). The prediction results of the final model showed a high agreement with the simulation results of the hydrodynamic model, with drastic reductions in computation time, making this model suitable for integration into an early warning system for pluvial flooding.

Improved neural distinguishers with multi-round and multi-splicing construction

In CRYPTO 2019, Gohr successfully applied deep learning to differential cryptanalysis against the NSA block cipher Speck32/64, achieving higher accuracy than traditional differential distinguishers. Until now, the improvement of neural differential distinguishers is a mainstream research direction in neural-aided cryptanalysis. But the current development of training data formats for neural distinguishers forms barriers: (1) The source of data features is limited to linear combinations of ciphertexts, which does not provide more learnable features to the training samples for improving the neural distinguishers. (2) Lacking breakthroughs in constructing data format for network training from the deep learning perspective. In this paper, considering both the domain knowledge about deep learning and information on differential cryptanalysis, we use the output features of the penultimate round to proposing a two-dimensional and non-realistic input data generation method of neural differential distinguishers. Then, we validate that the proposed new input data format has excellent features through experiments and theoretical analysis. Moreover, combining the idea of multiple ciphertext pairs, we generate two specific models for data input construction: MRMSP(Multiple Rounds Multiple Splicing Pairs) and MRMSD(Multiple Rounds Multiple Splicing Differences) and then build new neural distinguishers against Speck and Simon family, which effectively improve the performance compared with the previous works. To the best of our knowledge, our neural distinguishers achieve the longest rounds and the higher accuracy for NSA block ciphers Speck and Simon.

The openVA Toolkit for Verbal Autopsies.

Verbal autopsy (VA) is a survey-based tool widely used to infer cause of death (COD) in regions without complete-coverage civil registration and vital statistics systems. In such settings, many deaths happen outside of medical facilities and are not officially documented by a medical professional. VA surveys, consisting of signs and symptoms reported by a person close to the decedent, are used to infer the COD for an individual, and to estimate and monitor the COD distribution in the population. Several classification algorithms have been developed and widely used to assign causes of death using VA data. However, the incompatibility between different idiosyncratic model implementations and required data structure makes it difficult to systematically apply and compare different methods. The openVA package provides the first standardized framework for analyzing VA data that is compatible with all openly available methods and data structure. It provides an open-source, R implementation of several most widely used VA methods. It supports different data input and output formats, and customizable information about the associations between causes and symptoms. The paper discusses the relevant algorithms, their implementations in R packages under the openVA suite, and demonstrates the pipeline of model fitting, summary, comparison, and visualization in the R environment.