Data Modeling Tools Research Articles

Alternative futures for shared mobility systems: impacts on transport planning tools and techniques

On-demand mobility services are changing the way we move in cities, fostered by digitalisation, vehicle automation and Mobility-as-a-Service (MaaS) platforms. Transport planning tools and techniques are expected to keep up to date to support decision-makers on the successful integration of these new mobility options in the urban transport mix. However, the evolution of the emerging mobility solutions is highly uncertain, as it is a function of complex factors that go beyond the influence of transport stakeholders. This poses a challenge for the definition of the requirements that data analysis techniques and modelling tools will face. This paper presents a series of explorative scenarios that provide different contexts for the evolution of urban mobility in Europe, in order to grasp the plausible pathways that shared mobility services will follow in the upcoming decades. The scenarios are adapted from those developed by the climate change research community and are used in a Delphi poll to gather expert visions on how shared mobility services will evolve. The availability of a range of possible futures for shared mobility facilitates the identification of the capabilities that transport decision-makers will demand from data analysis techniques and modelling tools.

Novel and Emerging Capabilities that Can Provide a Holistic Understanding of the Plant Root Microbiome

In recent years, the root microbiome (i.e., microorganisms growing inside, on, or in close proximity to plant roots) has been shown to play an important role in plant health and productivity. Despite its importance, the root microbiome is challenging to study because of its complexity, heterogeneity, and subterranean location. Fortunately, root microbiome research has seen a tremendous influx of novel technologies (e.g., imaging tools, robotics, and molecular analyses), experimental platforms (e.g., micro- and mesocosms), and data integration, modeling, and prediction tools in the past decade that have greatly increased our ability to dissect the complex network of interactions between above- and belowground environmental parameters, plants, bacteria, and fungi that dictate soil and broader ecosystem health. Herein, we discuss methods that are currently used in root microbiome research and that can be expanded to phytobiome research in general ranging from laboratory studies to mesocosm-scale studies and, finally, to field studies; evaluate their relevance to ecosystem studies; and discuss future root microbiome research directions.

Energy and Cost Footprint Reduction for 5G and Beyond With Flexible Radio Access Network

This paper focuses on Beyond fifth generation (B5G) non-linear data modeling and decision-making tools to optimize cost reduction versus coverage-QoS trade-off, in other words, the number of active Remote Radio Heads or Units (RRHs) needed according to traffic demands. The cost and energy optimization are analytically expressed by modeling the complex relationships between input and output system parameters using realistic scenarios and traffic profiles for low, medium, and high traffic environments. The optimization tool is based on a multi-objective integer linear programming model, designed to reduce the network cost while maintaining a good coverage-QoS and accounting for capacity constraints, User Equipments (UEs), and different slices. Results at 3.6 and 28 GHz are presented by analyzing and comparing several Cloud Radio Access Network (C-RAN) split options in a heterogeneous deployment with Macro-RRHs (MRRHs) and Small-RRHs (SRRHs). Cost reductions ranging from 30 % to 70 % have been obtained depending on the scenario. This proposal allows mobile network operators (MNOs) to achieve further optimization, while providing better network diagnostics.

Innovative DSS for intelligent monitoring and urban square design approaches: A case of study

In this paper we proposed a new platform based on data processing suitable for urban square design optimization. The re-design of square in cities is important to make the urban squares livable especially for cities with high population density. Innovative solutions about green space design, computer vision and environmental sensing have been implemented, observing experimentally the influence of the public space on people’s behaviour. Furthermore, the platform processes data about weather condition, objects detected by image processing algorithms, environmental pollution and occupancy patterns to perform correlation analysis. A Convolutional Neural Network (CNN) has been used to predict people occupancy over time, basing on a weather dataset. The platform implements a Decision Support System (DSS) aimed to read the data, and provide guidelines for urban square design optimization. The DSS is constructed by data modeling, data mining and multiple correspondence analysis (MCA) tools tailored on the specific case of study. Experimental observations provide insights for a self-adaptive urban square design. Multiple correspondence analysis best fits qualitative and quantitative data obtained from sensors, and highlights people’s behaviour in the urban square in correlation with different variables. After a complete overview of factors which can influence the livability of a square and economical/social models are presented different results about citizen behaviour interpretation in function of weather data and attitudes. The proposed framework can be potentially applied for a generic urban square.

RF energy modelling using machine learning for energy harvesting communications systems

SummaryMachine learning (ML) theories and methods are mainly based on probability theory and statistics. It is a very powerful tool for data modelling. On the other hand, energy harvesting has been regarded as a viable solution to extending battery lifetime of wireless sensor network. Motivated by these, modelling of the radio frequency (RF) energy available to the wireless nodes is required for efficient operation of wireless networks. In this work, we will use different ML algorithms to model the RF energy data for efficient operation of energy harvesting communication systems. Four ML algorithms are studied and compared in terms of the accuracy for RF energy modelling using the energy data in the band between 1805 and 1880 MHz. The results show that linear regression (LR) has the highest accuracy and the most stable performance, while decision tree is the worst model. Also, in terms of the operation efficiency of the system, LR has the best performance, followed by support vector machine and random forest algorithm.

Research and application of automatic extraction method for submarine canyon characteristic elements based on manual supervision

Submarine canyons are the major channels for the migration of terrigenous sediments towards deep seas and an important geomorphological unit in continental shelves/slopes. With the development of multibeam bathymetry technology, a method of quickly identifying and accurately extracting the characteristics of submarine canyons from large datasets is urgently required. In this paper, under manual supervision, based on the principles of hydrological analysis and slope analysis, we established a method to quickly identify and extract the characteristic elements of submarine canyons from digital elevation model (DEM) data via the data modeling tools in ArcGIS, according to the topographic features such as U and V shaped downcutting at the bottom of the submarine canyon and high-relief steep canyon walls. The analytical results of the Shenhu Canyons in the northern slope of the South China Sea show that this method can rapidly determine the development position and characteristic elements of submarine canyons and obtain the canyon head and mouth water depth, canyon thalweg length and canyon range (area of canyon floor). To obtain the optimal parameter set applicable to the study area, the factors affecting canyon identification, such as the canyon morphology, reclassification threshold and data resolution, are discussed and analyzed. The results show that the canyon morphology has little influence on the accuracy of recognition results for straight, parallel or sub-parallel canyons. The reclassification threshold of the zero flow accumulation and the spatial resolution of the DEM data determine the accuracy of canyon thalweg recognition, which are two important factors affecting the accuracy of canyon identification results. For the Shenhu Canyons area, a spatial resolution of 200 m and reclassification threshold of 0.4 are the optimal parameters for identifying and extracting features from submarine canyons, and the identification results of automatic and manual extraction of canyon parameters show that the heads water depth differences all are less than 210 m and the thalwegs length difference of the canyon are within 7 km.

Persistent spectral graph.

Persistent homology is constrained to purely topological persistence, while multiscale graphs account only for geometric information. This work introduces persistent spectral theory to create a unified low-dimensional multiscale paradigm for revealing topological persistence and extracting geometric shapes from high-dimensional datasets. For a point-cloud dataset, a filtration procedure is used to generate a sequence of chain complexes and associated families of simplicial complexes and chains, from which we construct persistent combinatorial Laplacian matrices. We show that a full set of topological persistence can be completely recovered from the harmonic persistent spectra, that is, the spectra that have zero eigenvalues, of the persistent combinatorial Laplacian matrices. However, non-harmonic spectra of the Laplacian matrices induced by the filtration offer another powerful tool for data analysis, modeling, and prediction. In this work, fullerene stability is predicted by using both harmonic spectra and non-harmonic persistent spectra, while the latter spectra are successfully devised to analyze the structure of fullerenes and model protein flexibility, which cannot be straightforwardly extracted from the current persistent homology. The proposed method is found to provide excellent predictions of the protein B-factors for which current popular biophysical models break down.

Insights from Adopting a Data Commons Approach for Large-scale Observational Cohort Studies: The California Teachers Study.

Large-scale cancer epidemiology cohorts (CEC) have successfully collected, analyzed, and shared patient-reported data for years. CECs increasingly need to make their data more findable, accessible, interoperable, and reusable, or FAIR. How CECs should approach this transformation is unclear. The California Teachers Study (CTS) is an observational CEC of 133,477 participants followed since 1995-1996. In 2014, we began updating our data storage, management, analysis, and sharing strategy. With the San Diego Supercomputer Center, we deployed a new infrastructure based on a data warehouse to integrate and manage data and a secure and shared workspace with documentation, software, and analytic tools that facilitate collaboration and accelerate analyses. Our new CTS infrastructure includes a data warehouse and data marts, which are focused subsets from the data warehouse designed for efficiency. The secure CTS workspace utilizes a remote desktop service that operates within a Health Insurance Portability and Accountability Act (HIPAA)- and Federal Information Security Management Act (FISMA)-compliant platform. Our infrastructure offers broad access to CTS data, includes statistical analysis and data visualization software and tools, flexibly manages other key data activities (e.g., cleaning, updates, and data sharing), and will continue to evolve to advance FAIR principles. Our scalable infrastructure provides the security, authorization, data model, metadata, and analytic tools needed to manage, share, and analyze CTS data in ways that are consistent with the NCI's Cancer Research Data Commons Framework. The CTS's implementation of new infrastructure in an ongoing CEC demonstrates how population sciences can explore and embrace new cloud-based and analytics infrastructure to accelerate cancer research and translation.See all articles in this CEBP Focus section, "Modernizing Population Science."

Spatial-spectral classification of hyperspectral images based on multiple fractal-based features

Hyperspectral images are efficient tools for discriminating different types of earth's surface materials. Spectral features traditionally perform classification of hyperspectral images, but different studies have proved the efficiency of spatial features as complementary information in increasing the classification accuracy. The fractal geometry can be regarded as a potent tool for spatial data modeling. This study proposes a new classification method based on the integration of fractal and spectral features. For this purpose, three groups of fractal features, including mono-fractal, lacunarity and multi-fractal features are generated from the first few principal components of the hyperspectral image in different window sizes. These features are later stacked with spectral features and then fed to support vector machines classifier. The experiments are conducted on two real hyperspectral images Indian Pines, Pavia University. Final classification accuracy proved the superiority of the proposed classification method against the other competitive spatial-spectral methods.

Prediction of compressive strength of mortar near sodium chloride by artificial neural network

The compressive strength value of cement mortar is usually affected by the amount of sodium chloride, chemical admixture and cement grade. Therefore, the artificial neural network model is used to predict the mortar strength values of different cement grades and sodium chloride (NaCl) content. In order to predict the compressive strength of the mortar, an artificial neural network model of cement grade, different water-cement ratio, sodium chloride solution content, an output neuron and four input neurons was established. After immersion in 0%, 5%, and 10% sodium trichloride solution for 60 days, the compressive strength was measured using 12 different ratios. Artificial neural network (ANN) analysis shows that ANN as a nonlinear statistical data modeling tool can establish a strong correlation between sodium chloride content and compressive strength of cement mortar. In addition, modeling tools have a greater impact on different cement grades (42.5, 32.5 MPa).

Recurrent Interval Type-2 Fuzzy Wavelet Neural Network with Stable Learning Algorithm: Application to Model-Based Predictive Control

Fuzzy neural networks, with suitable learning strategy, have been demonstrated as an effective tool for online data modeling. However, it is a challenging task to construct a model to ensure its quality and stability for non-stationary dynamic systems with some uncertainties. To solve this problem, this paper presents a novel identification model based on recurrent interval type-2 fuzzy wavelet neural network (RIT2FWNN) with new learning algorithm. The model benefits from both advantages of recurrent and wavelet neural networks such as use of temporal data and fast convergence properties. The proposed antecedent and consequent parameters update rules are derived using sliding-mode-control-theory. To evaluate the proposed fuzzy model, it is utilized to design a nonlinear model-based predictive controller and is applied for the synchronization of fractional-order time-delay chaotic systems. Using Lyapunov stability analysis, it is shown that all update rules of the parameters are uniformly ultimately bounded. The adaptation laws obtained in this method are very simple and have closed forms. Some stability conditions are derived to prove learning dynamics and asymptotic stability of the network by using an appropriate Lyapunov function. The efficacy and performance of the proposed method is verified by simulation examples.

Assessment of strength characteristics for experimental based workable self compacting concrete using artificial neural network

Self compacting concrete (SCC) is the concrete which can flow through reinforcement without the requirement of vibration. The proportioning of materials for workable SCC requires clear understanding of material properties and their behavior with one on one to apply it in construction site. Hence, an extensive experimentation is conducted based on empirical way and produced 123 workable SCC mixtures resulting for measuring the strength characteristics such as compressive strength (fc) and splitting tensile strength (fst). The workable SCC mixture is considered for strength characteristics only after passing the requirements of workability tests of SCC namely slump flow test, L-box test, V-funnel test and sieve segregation resistance test. The 123 workable SCC mixtures experimentally obtained fc ranging from 26.6 N/mm2 to 62.1 N/mm2 and fst ranging from 2.9 N/mm2 to 6.9 N/mm2. In this study, artificial neural network (ANN) had been used which was speedy and efficient for predicting output strength characteristics based on extensive experimental data investigated in laboratory. ANN is data modeling tool where relationship between inputs and output can be found out. In this work, after investigating all parameters for producing SCC, only important inputs considered in ANN model. Marquardt back propagation training algorithm had been used with inputs containing cement content, water cement ratio, type of mineral admixture, percentage of mineral admixture and type of chemical admixture. In this study, satisfactory mean square error and correlation coefficient had been obtained during training, validation and testing of ANN for predicting two outputs fc and fst separately.

Learning at the Intersection of Self and Society: The Family Geobiography as a Context for Data Science Education

Open large-scale datasets (LSDS) and data visualization technologies are new cultural tools that have potential to inform public dialogue and learning about important socioeconomic and scientific matters, particularly if the data is used to consider both personal and shared experiences. This paper reports on a design study in which diverse middle and high school youth in a free summer workshop at an urban public library were asked to model their family geobiographies, or their personal family migration stories, with socioeconomic LSDS. Youth represented family decision-making and social conditions that might have motivated family movements with online, dynamic data modeling and mapping tools (Gapminder.org; SocialExplorer.com). The qualitative video analysis examined participants’ experiences and learning in storytelling and modeling the family geobiography, focusing on multimodal talk-in-interaction to understand how the study design engaged learners’ capacities, histories, and imagined futures in relation to the LSDS and supported learning about oneself and society. Grounded examples from two family cases are used to illustrate how participants placed their families and selves into data ontologies and the role of family members in composing storylines.

Use of Big Data to Aid Patient Recruitment for Clinical Trials Involving Biosimilars and Rare Diseases.

Patient recruitment and retention are arguably the greatest challenges to the timely execution of clinical trials. This is particularly true in the case of trials involving biosimilars and those focused on rare diseases. For biosimilars, recruitment success typically hinges on difficulty of access to reimbursement for the originator product and may be hindered by competition from studies with other biosimilars and those with new chemical entities.For rare diseases, recruitment success depends not only on finding enough patients but also on retaining them for the duration of the trial. Historical success with patient recruitment-in addition to site qualifications-needs to be considered in parallel with current market competition and results in an ever-changing patient recruitment environment. Multiple companies supporting the biopharmaceutical industry, such as Contract Research Organizations, have begun to leverage sophisticated data modeling tools and techniques to find additional patients for biosimilar and rare disease trials and/or to find patients more quickly. In addition, these companies seek to better understand the population of interest and refine their statistical assumptions when conducting clinical trials or real-world analyses. The largest and most well-established companies that support the biopharmaceutical industry now have unparalleled access to big data from clinical trials, electronic health records, medical claims, laboratory tests, and prescriptions. This paper will discuss how big data can be harnessed to aid patient recruitment with a focus on clinical trials for biosimilars and orphan rare diseases.

White Learning: A White-Box Data Fusion Machine Learning Framework for Extreme and Fast Automated Cancer Diagnosis

Deep learning as a data modeling tool is hard to be understood of how its predicted result came about from its inner working. It is generally known as a black box and is not interpretable. Often in medical applications, physicians need to understand why a model predicts a result. On the other hand, BN is a probabilistic graph with nodes representing the variables, and the arcs present the conditional dependences between the variables. In this article, a white learning framework is proposed, which advocates three levels of fusing the black-box deep learning and white box BN, that offers both predictive power and interpretability. A case of breast cancer classification is conducted in an experiment. From the results, it is observed that white learning, which combines black-box and white-box machine learning, has an edge in performance over individually BN alone or deep learning alone. The white learning framework has the benefits of interpretability and high predictive power, making it suitable for critical decision-making task where a reliable prediction is as important as knowing how the outcome is predicted. The predicted output, which is generated from white learning, can be traced back via the conditional probability at each node. It is, hence, anticipated that in the future, especially for medical domain, white learning, which has the benefits of both black -box and white-box learning, would be highly valued and raised in popularity.

RTS EPD’s – Different Methods of Producing Reliable Environmental Information of Building Products in Finland

The Building Information Foundation RTS sr launched a national EPD program in the year 2016 and after that there have been produced several RTS EPD’s published by the RTS. The Information gathered from the Environmental Product Declaration (EPD) is verified by a third party and therefore neutral and reliable. Environmental performance of construction products is compiled according to the standard EN 15804+A1 and A2 and with a guidance’s and methodology processed in the committee PT18 RT EPD’s. The name of the principal publication is “Methodology (PCR) for compiling environmental declarations for building products: EPD’s published by The Building Information Foundation RTS (2019)” and in addition there are guidance for the application process and verification processes.The Building Information Foundation got a full membership status of EcoPlatform in September 2018 and therefore the guidance has been revised. PT18 noticed the future demand of easy way of producing EPD’s and therefore it compiled a guidance of verification process of customized and product specific EPD-tools used in connection to production processes. PT18 considered also amendment of the EN15804 standard (A2) in advance as far as possible and updated the RTS methodology accordingly. The EPD’s are created in Finland by the Principal Committee PT18 of The Building Information Foundation RTS. A work group of the Committee PT18 will audit and approve/reject the applications. All RTS EPDs have been verified, there is no difference if the EPDs have been complied with the EPD tool or without it.The eco-profiles and other environmental aspects provide input data for the assessment of environmental impacts of the buildings. The purpose of the declarations is to provide environmental information of construction products in a standardized and transparent way. The EN-standardized method developed by CEN/TC350 is utilized in other European countries as well by different EPD-programs. The purpose of different EPD-tools is to provide easy way to produce EPD information of similar products and to use gathered information in multiple product information services and data modelling tools.

Multivariate-t linear mixed models with censored responses, intermittent missing values and heavy tails.

Multivariate longitudinal data arisen in medical studies often exhibit complex features such as censored responses, intermittent missing values, and atypical or outlying observations. The multivariate-t linear mixed model (MtLMM) has been recognized as a powerful tool for robust modeling of multivariate longitudinal data in the presence of potential outliers or fat-tailed noises. This paper presents a generalization of MtLMM, called the MtLMM-CM, to properly adjust for censorship due to detection limits of the assay and missingness embodied within multiple outcome variables recorded at irregular occasions. An expectation conditional maximization either (ECME) algorithm is developed to compute parameter estimates using the maximum likelihood (ML) approach. The asymptotic standard errors of the ML estimators of fixed effects are obtained by inverting the empirical information matrix according to Louis' method. The techniques for the estimation of random effects and imputation of missing responses are also investigated. The proposed methodology is illustrated on two real-world examples from HIV-AIDS studies and a simulation study under a variety of scenarios.

Application of Stochastic Analysis, Modeling and Simulation (SAMS) to Selected Hydrologic Data in the Middle East

Water resources in the Middle East are very scarce and the management of these resources is a challenge. In this paper, the use of stochastic analysis, modeling, and simulation (SAMS) software package to selected hydrologic data in the Middle East (namely Jordan and Saudi Arabia) are explored. Modeling and simulation experiments were conducted to test the capabilities of SAMS to be used for stochastic modeling and simulation in the Middle East region. The hydrologic data used in this study consist of historic observed rainfall data of different lengths at various sites in Jordan and Saudi Arabia. The models used in this study include: autoregressive moving average (ARMA) models, periodic autoregressive moving average (PARMA) models, multi-site contemporaneous autoregressive moving average (CARMA) models, and temporal disaggregation models. Results indicate that SAMS can be used as a tool for stochastic modeling and simulation of hydrologic data in Jordan and Saudi Arabia. It is important for managers and decision makers of water resources in these countries to be able to use sophisticated tools such as SAMS while deciding water management policies in these countries.

Qualitative and Cognitive Analysis and Modeling Tool for Biological Data

This article describes a qualitative cognitive analysis and modeling tool (QCAM) for biological data collected using sensors such as a simple brain-wave sensor, while executing an actual task. However, these types of sensors are generally less accurate than devices designed for medical use. Sensors may be influenced by noise or personal differences between subjects. A qualitative approach is very effective for analyzing such data, because the authors can understand their essential features by focusing on qualitative changes, such as increasing, decreasing, and steady changes in the data, without quantifying it. Therefore, in addition to statistical analysis, QCAM provides qualitative analysis and modeling of data and allows us to verify the model by using qualitative reasoning. This article explains QCAM and describes experimental results obtained by using real driving data, a combination of movie data from a camera, acceleration data from a smart phone, and brain-wave data from a simple brain-wave sensor, that was obtained while a person drove a vehicle.

Robust Tensor Approximation With Laplacian Scale Mixture Modeling for Multiframe Image and Video Denoising

Sparse and low-rank models have been widely studied in the literature of signal processing and computer vision. However, as the dimensionality of dataset increases (e.g., multispectral images, dynamic MRI images, and video sequences), the optimality of vector and matrix-based data representations and modeling tools becomes questionable. Inspired by recent advances in sparse and low-rank tensor analysis, we propose a novel robust tensor approximation (RTA) framework with the Laplacian Scale Mixture (LSM) modeling for three-dimensional (3-D) data and beyond. Our technical contributions are summarized as follows: first, conceptually similar to robust PCA, we consider its tensor extension here—i.e., low-rank tensor approximation in the presence of outliers modeled by sparse noise; second, built upon previous work on tensor sparsity, we propose to model tensor coefficients with an LSM prior and formulate a maximum a posterior estimation problem for noisy observations. Both unknown sparse coefficients and hidden LSM parameters can be efficiently estimated by the method of alternating optimization; and third, we have derived closed-form solutions for both subproblems and developed computationally efficient denoising techniques for multiframe images and video. Experimental results on three datasets have shown that the proposed algorithm can better preserve the sharpness of important image structures and outperform several existing state-of-the-art image/video denoising methods (e.g., BM4D/VBM4D and tensor dictionary learning).