Incomplete Input Data Research Articles

Partial Convolutional LSTM for Spatiotemporal Prediction of Incomplete Data

Advanced data analysis techniques facilitate data-driven spatiotemporal prediction in various fields. However, in real-world data, missing values are inevitable, which causes the data incomplete and makes predictions more challenging. Although we can train complex spatiotemporal correlations with deep learning techniques, most deep learning networks require data without any missing values. In this paper, we propose a novel deep learning framework that manages missing values in the grid-based data structure. We design a partial convolutional long-short-term-memory (PConvLSTM) by combining partial convolution for inpainting and convolutional long-short-term-memory (ConvLSTM) for spatiotemporal prediction. We treat incomplete spatiotemporal data with the partial convolution and train spatiotemporal dependencies with the ConvLSTM structure. The trained PConvLSTM can predict continuous spatial data with missing regions in incomplete input data. We also train the network using incomplete spatiotemporal data without ground truth to enhance practicality. Existing deep learning networks to interpolate missing data are mostly trained by applying ground truth data without missing regions. We show that PConvLSTM achieves higher prediction accuracies compared to ConvLSTM for incomplete data without ground truth.

Optimal sizing and operating strategy of a stand‐alone generation–load–storage system: An island case study

AbstractComponent sizing optimization and technoeconomic feasibility studies for stand‐alone power systems have been actively discussed in recent years. However, most models and studies overlook the importance of individual component performance, input data resolution and their integration with the system. This article compares the rapidly evolving battery storage technology applications using the context of a stand‐alone system, through a case study on Bruny Island, Tasmania, Australia, where the current electricity infrastructure is approaching its end of life. We constructed a mixed‐integer linear programming model to achieve optimal balance between modeling accuracy and computational complexity. The model was constructed to obtain the optimal component sizing on the basis of minimum lifetime net present cost. It was shown in our work that any transition of islands to become fully stand alone should be carefully considered, where a limited grid connection could still provide significant value to the infrastructure, greatly reduce its stress over peak hours. This concept was illustrated further with another set of model scenarios aiming to explore the performance of battery storage systems with different power output allowances, limited by the time‐series data resolution, were developed. It was shown that the selection of incomplete input data cycle, reliance on standardized average values and utilization of low resolution time‐series data could heavily skew the results of a model, as the use of incomplete dataset and oversimplified average values subtly conceal some of the critical sizing and operation issues in a technoeconomic feasibility study, impacting the accuracy of the model to reflect the real problem.

Computer-Aided Design of Composite Materials Using Reversible Multiscale Homogenization and Graph-Based Software Engineering

In this work, a new software for computer-aided design of composite materials with predefined thermomechanical properties is presented in case of incomplete input data. The mathematical basis of underlying computational method of the properties identification is a modified method of multiscale homogenization named reversible multiscale homogenization method. The system has a modular architecture and includes software implementation of the reversible multiscale homogenization method based on a new technique of construction of software implementations of complex computational methods. The latter was named «Graph-based software engineering» (GBSE) and is based on category and graph theories. The corresponding numerical and experimental results were obtained and compared. The expediency of GBSE approach is discussed for the case of the development of complex computational methods required when solving the applied problems of the design of new heterogeneous materials.

Vehicle Safety Analysis based on a Hybrid Approach Integrating DEMATEL, ANP and ER

Vehicle related safety is the principal focus of many agencies and organizations targeting road safety issues. There are many conflicting factors contributing to safety in motor vehicle operations. Unfortunately, the lack of reliable crash data makes it extremely difficult to evaluate the crash causations associated with defective vehicles. Furthermore, clarifying the interrelationships among vehicle related factors causing accidents is very complicated when the conventional decision techniques are used. This study aims to employ a hybrid decision method based on DEMATEL (decision-making trial and evaluation laboratory) and ANP (Analytic Network Process) to construct an Influence Relations Map (IRM) as well as obtain the influential weight of vehicle-related criteria. An empirical case study is provided to demonstrate the implementation process. This paper also employs an Evidential Reasoning algorithm (so-called ER) for assessing the inter-city buses in terms of vehicle safety in order to deal with the uncertainties associated with incomplete input data. The ER improves decision making process by using a belief decision matrix and the Demspster-Shafer theory of evidence. The results and findings reveal that the braking system is the most important criterion impacting vehicle safety, followed by fuel supply and electrical systems.

Deteksi Daging Sapi Menggunakan Electronic Nose Berbasis Bidirectional Associative Memory

E-nose is an instrument used to detect odor. E-nose developed with Bidirectional Associative memory (BAM) algorithm has advantages in processing incomplete input data and noise. The purpose of the study was to implement the BAM algorithm to detect pure beef among samples of beef, pork, and mixed meat from aroma with e-nose.Data processing of the sample reading results begins by performing the baseline manipulation process, then do difference and integral feature extraction for the data. The characteristic extraction data will be converted into bipolar matrix patterns (1 and -1) so that the threshold data is needed to be able to determine the feature extraction data to be bipolar. Data that have become bipolar matrices will be used as test and reference data in the program with cross validation testing to obtain the percentage of truth of meat detection using BAM based e-nose.Detection of meat with BAM using integral feature extraction with bipolar the first way yields a 14,8% success percentage and the second way bipolar yields a 15,7% success rate. The extraction of characteristic difference with bipolar the first way yields a success percentage of 17,3% and the second way bipolar yields a success rate of 16,4%.

Processing incomplete data for simulation-based production planning in shipbuilding

This paper presents an approach for simulation experiments at early stages of the shipbuilding process. In the early stages of the planning process, the design of the ship is not yet complete. However, an early scheduling of the production is already needed for staff employment and material ordering. Because the plan is based on incomplete input data, the uncertainty in production planning is much higher than in serial production with fully detailed product design and routings. The uncertainty reduces the accuracy of planning and, therefore, has a significant impact on its quality and robustness. The paper presents an approach to describe this uncertainty and to reduce it by generating design details from historical data.

Causal functional contributions and interactions in the attention network of the brain: an objective multi-perturbation analysis.

Spatial attention is a prime example for the distributed network functions of the brain. Lesion studies in animal models have been used to investigate intact attentional mechanisms as well as perspectives for rehabilitation in the injured brain. Here, we systematically analyzed behavioral data from cooling deactivation and permanent lesion experiments in the cat, where unilateral deactivation of the posterior parietal cortex (in the vicinity of the posterior middle suprasylvian cortex, pMS) or the superior colliculus (SC) cause a severe neglect in the contralateral hemifield. Counterintuitively, additional deactivation of structures in the opposite hemisphere reverses the deficit. Using such lesion data, we employed a game-theoretical approach, multi-perturbation Shapley value analysis (MSA), for inferring functional contributions and network interactions of bilateral pMS and SC from behavioral performance in visual attention studies. The approach provides an objective theoretical strategy for lesion inferences and allows a unique quantitative characterization of regional functional contributions and interactions on the basis of multi-perturbations. The quantitative analysis demonstrated that right posterior parietal cortex and superior colliculus made the strongest positive contributions to left-field orienting, while left brain regions had negative contributions, implying that their perturbation may reverse the effects of contralateral lesions or improve normal function. An analysis of functional modulations and interactions among the regions revealed redundant interactions (implying functional overlap) between regions within each hemisphere, and synergistic interactions between bilateral regions. To assess the reliability of the MSA method in the face of variable and incomplete input data, we performed a sensitivity analysis, investigating how much the contribution values of the four regions depended on the performance of specific configurations and on the prediction of unknown performances. The results suggest that the MSA approach is sensitive to categorical, but insensitive to gradual changes in the input data. Finally, we created a basic network model that was based on the known anatomical interactions among cortical-tectal regions and reproduced the experimentally observed behavior in visual orienting. We discuss the structural organization of the network model relative to the causal modulations identified by MSA, to aid a mechanistic understanding of the attention network of the brain.

Supplier selection based on evidence theory and analytic network process

The supplier selection is a key component of the supply chain management. Existing methods for the supplier selection are based on analytic network process. They can handle the interdependence of decision attributes; however, these methods could not guarantee an optimal solution when given vague or incomplete input data. To deal with the uncertainties of input data, we propose methods combining analytic network process with Dempster–Shafer evidence theory. We demonstrate efficiency and accuracy of the proposed method in a numerical example. We demonstrate that the proposed method is flexible and effective in dealing with the supplier selection problem.

Tomographic inversion techniques incorporating physical constraints for line integrated spectroscopy in stellarators and tokamaks.

Accurate tomographic inversion is important for diagnostic systems on stellarators and tokamaks which rely on measurements of line integrated emission spectra. A tomographic inversion technique based on spline optimization with enforcement of constraints is described that can produce unique and physically relevant inversions even in situations with noisy or incomplete input data. This inversion technique is routinely used in the analysis of data from the x-ray imaging crystal spectrometer (XICS) installed at the Large Helical Device. The XICS diagnostic records a 1D image of line integrated emission spectra from impurities in the plasma. Through the use of Doppler spectroscopy and tomographic inversion, XICS can provide profile measurements of the local emissivity, temperature, and plasma flow. Tomographic inversion requires the assumption that these measured quantities are flux surface functions, and that a known plasma equilibrium reconstruction is available. In the case of low signal levels or partial spatial coverage of the plasma cross-section, standard inversion techniques utilizing matrix inversion and linear-regularization often cannot produce unique and physically relevant solutions. The addition of physical constraints, such as parameter ranges, derivative directions, and boundary conditions, allow for unique solutions to be reliably found. The constrained inversion technique described here utilizes a modified Levenberg-Marquardt optimization scheme, which introduces a condition avoidance mechanism by selective reduction of search directions. The constrained inversion technique also allows for the addition of more complicated parameter dependencies, for example, geometrical dependence of the emissivity due to asymmetries in the plasma density arising from fast rotation. The accuracy of this constrained inversion technique is discussed, with an emphasis on its applicability to systems with limited plasma coverage.

Commentary to Gebel 2012: A quantitative review should apply meta-analytical methods—and this applies also to quantitative toxicological reviews

Gebel (In Arch Toxicol 87(5):923-924, 2013) replied to my Letter to the Editor (Morfeld in Arch Toxicol 87(5):921, 2013) in which I criticized the quantitative review of inhalation rat studies on the association of granular biopersistent dust exposures and lung cancer risk (Gebel in Arch Toxicol 86(7):995-1007, 2012). My methodological comments were not understood. The Editors of the Archives invited me to detail and substantiate my criticism. The main issues are as follows: (1) A quantitative summary of the study results was performed without weighting for precision of the single studies (the published unweighted synthesis is potentially biased). (2) No heterogeneity assessment was performed before combining the findings (it is unclear whether overall summaries are sensible). (3) Correlation coefficients were used (correlations are distorted estimates of exposure-response and misleading). (4) An incomplete input data table was published (no transparent reporting, no replication possible for the reader). The quantitative synthesis by Gebel (In Arch Toxicol 86(7):995-1007, 2012) does not fulfil the usual requirements of a scientific quantitative review and should be replaced by an appropriate meta-analysis.

Realtime facial animation with on-the-fly correctives

We introduce a real-time and calibration-free facial performance capture framework based on a sensor with video and depth input. In this framework, we develop an adaptive PCA model using shape correctives that adjust on-the-fly to the actor's expressions through incremental PCA-based learning. Since the fitting of the adaptive model progressively improves during the performance, we do not require an extra capture or training session to build this model. As a result, the system is highly deployable and easy to use: it can faithfully track any individual, starting from just a single face scan of the subject in a neutral pose. Like many real-time methods, we use a linear subspace to cope with incomplete input data and fast motion. To boost the training of our tracking model with reliable samples, we use a well-trained 2D facial feature tracker on the input video and an efficient mesh deformation algorithm to snap the result of the previous step to high frequency details in visible depth map regions. We show that the combination of dense depth maps and texture features around eyes and lips is essential in capturing natural dialogues and nuanced actor-specific emotions. We demonstrate that using an adaptive PCA model not only improves the fitting accuracy for tracking but also increases the expressiveness of the retargeted character.

Inaccuracy, uncertainty and the space-time permutation scan statistic.

The space-time permutation scan statistic (STPSS) is designed to identify hot (and cool) spots of space-time interaction within patterns of spatio-temporal events. While the method has been adopted widely in practice, there has been little consideration of the effect inaccurate and/or incomplete input data may have on its results. Given the pervasiveness of inaccuracy, uncertainty and incompleteness within spatio-temporal datasets and the popularity of the method, this issue warrants further investigation. Here, a series of simulation experiments using both synthetic and real-world data are carried out to better understand how deficiencies in the spatial and temporal accuracy as well as the completeness of the input data may affect results of the STPSS. The findings, while specific to the parameters employed here, reveal a surprising robustness of the method's results in the face of these deficiencies. As expected, the experiments illustrate that greater degradation of input data quality leads to greater variability in the results. Additionally, they show that weaker signals of space-time interaction are those most affected by the introduced deficiencies. However, in stark contrast to previous investigations into the impact of these input data problems on global tests of space-time interaction, this local metric is revealed to be only minimally affected by the degree of inaccuracy and incompleteness introduced in these experiments.

Constrained least-squares solution and regularization in inverse boundary element analysis of photoelastic models involving contact

Existing work by the present team has involved the development of an inverse boundary element approach for fitting unknown boundary conditions to full-field stress data obtained using photoelasticity, treating the displacements on the unknown region as the solution variables. However, the recovered boundary conditions sometimes show unrealistic features such as negative contact pressures or shear tractions which exceed realistic frictional values; noisy or incomplete input data make these problems worse and can make the results oscillatory. The work described here exploits available constrained least-squares techniques in order to express the contact conditions as linear inequality constraints upon the displacement solution. A variant of Tikhonov regularization is also used to penalize against oscillatory traction distributions on the unknown boundary. The chosen implementation, solved using the LSSOL algorithm, can handle the issue of rigid-body motion without the need for manual imposition of restraints. The technique is illustrated using simulated and real examples, demonstrating that the technique correctly reconstructs the individual principal stresses.

A distributed problem‐solving framework for probabilistic software effort estimation

AbstractDistributed problem‐solving (DPS) systems use a framework of human organizational notions and principles of intelligent systems to solve complex problems. Human organizational notions are used to decompose a complex problem into sub‐problems that can be solved using intelligent systems. The solutions of these sub‐problems are combined to solve the original complex problem. In this paper, we propose a DPS system for probabilistic estimation of software development effort. Using a real‐world software engineering dataset, we compare the performance of the DPS system with a neural network (NN) and show that the performance of the DPS system is equal to or better than that of the NN with the additional benefits of modularity, probabilistic estimates, greater interpretability, flexibility and capability to handle incomplete input data.

Statistically adjusted engineering (SAE) modeling of metered roof-top photovoltaic (PV) output: California evidence

Abstract Accurate hourly photovoltaic (PV) output data are useful for engineering design, cost-effectiveness evaluation, rate design, system operation, transmission planning, risk management, and policy analysis. However, a large sample of hourly metered PV data is seldom available, and engineering simulation is often the only practical means to obtain hourly PV output. Based on an analysis of net energy metering (NEM) funded by the California Public Utilities Commission (CPUC), this paper presents statistically adjusted engineering (SAE) modeling of metered output of 327 roof-top PV installations in California for the 12-month period of January–December 2008. The key findings are: (a) the metered PV output is on an average 80–90% of simulated performance; and (b) the simulated data have useful information for accurately predicting metered PV performance. Plausible causes for (a) include incomplete input data for PV simulation, occasional failures in metered data recording, and less than ideal conditions for PV performance in the real world.

Combining local features for robust nose location in 3D facial data

Due to the wide use of human face images, it is significant to locate facial feature points. In this paper, we focus on 3D facial data and propose a novel method to solve a specific problem, i.e., locating the nose tip by one hierarchical filtering scheme combining local features. Based on the detected nose tip, we further estimate the nose ridge by a newly defined curve, the Included Angle Curve (IAC). The key features of our method are its automated implementation for detection, its ability to deal with noisy and incomplete input data, its invariance to rotation and translation, and its adaptability to different resolutions. The experimental results from different databases show the robustness and feasibility of the proposed method.

Use of an artificial neural network (ANN) for classifying nursing care needed, using incomplete input data.

In German nursing insurance, the act of classifying the client into four categories of disability is based on legally defined distinct criteria. When classifying deceased persons it is often impossible to collect all the required information. We aimed to determine the ability of an artificial neural network (ANN) to calculate the category of disability, to investigate the response of the ANN to input items of different nature, quantity and data quality, and to estimate the minimum number of training data required. The investigation was conducted as a retrospective observational study. The analysis was based on routine records of 14000 adult clients of the nursing insurance. Several ANNs were trained, varying nature, number and quality of the input items as well as the size of the training data set. Each ANN's classification competence was tested on independent validation data, judging the ANN's conformance to the result of the individual expert assessment, using kappa statistics. Fed with all 30 input items available, the net classified 80% of cases correctly (weighted kappa = 0.78). Using three input items, weighted kappa was 0.63. Severe misclassification (deviation by more than one category in either direction) ranged between 0.2% (all 30 input items) and 3.7% (3/30 items). The less complete the individual input items were, the less accurate was the net's estimate. A 20% rate of missing values was well tolerated. A training set comprising 500 cases was adequate. The input item set inherits redundancy. The ANN's ability to correctly respond to subsets of input items makes it a powerful tool in quality control. In the categorization of deceased persons when only an incomplete input item set is available, the ANN can achieve satisfactory results.

Neural Networks in Neurotologic Expert Systems

Artificial intelligence donates new possibilities to neurotologic research. Neural networks are a computer-based reasoning method which can be applied in expert systems created for clinical decision support. Neural networks have been used in medical imaging, in medical signal processing and to analyze both clinical and laboratory data. Principally, neural networks simulate the function of the brain. They have to be taught to make correct decisions from the input data. This learning process can be either supervised or unsupervised. The decision making is based on mathematical transformations and it occurs on a hidden level. Calculations are made on parallel manner and the decision making simulates pattern recognition method. Neural networks suit well in medical problems which cannot be defined in simple rules. A drawback of neural networks is that the decisions are irrational and cannot be motivated to the user. Another problem is neural networks difficulty to handle incomplete input data, i.e., how to define some default or expected values for unknown input parameters. In a complex medical area, which would require multilayered neural networks, the neural networks require a large amount of solved cases for the learning process. In our experience neural networks seem not suitable for diagnosing vertigo and a better choice would be either case-based reasoning or possibly genetic algorithms or a combination of these.

Iterative algorithm for image filtering utilizing image- and noise-related information

Filtering of noise-corrupted images is an important problem in image processing. We propose several iterative algorithms for image filtering that are based on the minimization of the penalty functional describing the properties of both image and noise data. Applications of the proposed approach to image estimation from the ensemble of the noisy estimates, incomplete noisy input data, and the impulse noise ensemble are described. The demonstrated simulation results indicate that the proposed approach is applicable to some important image-filtering probems.

Time-constrained reasoning under uncertainty

Dynamic classification problems present unique challenges beyond those of more traditionalstatic knowledge-based systems. Uncertain and incomplete input data, unpredictable event sequences, and critical time and resource constraints require new approaches and techniques for automated reasoning. Our work toward addressing these complex requirements has concentrated on developing an integrated software architecture which supports the knowledge engineering process from development to deployment. The approach we are using to deal with real-time issues in the deployment environment involves the use of a fast knowledge representation scheme, efficient forward and backward chaining mechanisms, and a meta-controller which handles asynchronous inputs, prioritized task requests, and hard performance deadlines.