Output Distribution Research Articles

Improving Efficiency of Iso-Surface Extraction on Implicit Neural Representations Using Uncertainty Propagation.

Implicit Neural representations (INRs) are widely used for scientific data reduction and visualization by modeling the function that maps a spatial location to a data value. Without any prior knowledge about the spatial distribution of values, we are forced to sample densely from INRs to perform visualization tasks like iso-surface extraction which can be very computationally expensive. Recently, range analysis has shown promising results in improving the efficiency of geometric queries, such as ray casting and hierarchical mesh extraction, on INRs for 3D geometries by using arithmetic rules to bound the output range of the network within a spatial region. However, the analysis bounds are often too conservative for complex scientific data. In this paper, we present an improved technique for range analysis by revisiting the arithmetic rules and analyzing the probability distribution of the network output within a spatial region. We model this distribution efficiently as a Gaussian distribution by applying the central limit theorem. Excluding low probability values, we are able to tighten the output bounds, resulting in a more accurate estimation of the value range, and hence more accurate identification of iso-surface cells and more efficient iso-surface extraction on INRs. Our approach demonstrates superior performance in terms of the iso-surface extraction time on four datasets compared to the original range analysis method and can also be generalized to other geometric query tasks.

Massive components in renewable hydrothermal liquid trigger ultra-high differentially expressed genes and diverse pathways for pathogen control

Hydrothermal liquefaction aqueous phase (HTL-AP) greatly hindered the sustainable development of HTL technology due to its high output and diverse compound distribution. Herein, the antimicrobial behavior, application scenario and acton mechanism of HTL-AP were clarified since an emerging pathogen reduction approach by HTL-AP attracts increasing attention. We studied the molecular cognition and underlying mechanism for phytopathogen control provoked by HTL-AP via multiscale analysis including mycelial morphology, intracellular metabolites and transcriptome. HTL-AP in a very low concentration (only 1.5%) completely inhibited the growth of Botrytis cinerea (B. cinerea) and showed promising potential for seed-borne fungi control. Biochemical analysis revealed that the morphology was significantly changed, the contents of four intracellular compounds were all largely disordered, and activities of six enzymes simultaneously decreased in mycelium after uptake of HTL-AP. Further, the transcriptome analysis revealed the disturbance of the gene expression of B. cinerea in response to HTL-AP stress. Ultra-high differentially expressed genes were enriched, which was significantly distinguished from the reported fungicide agent. HTL-AP mainly acted on metabolic processes of B. cinerea while disruption of genetic information processes and cellular processes were also performed. All four main antimicrobial modes were observed in HTL-AP action, and multiple action pathways of HTL-AP exhibited a synergistic interaction in growth inhibition. The multiscale analysis in this study refreshed the knowledge and cognition of HTL-AP functioned for pathogen control, which was speculated due to the multiple active compounds. HTL-AP showed a high potential for seed-borne fungi control, contributing to the novel renewable and suatainable fungicide agent development and new antimicroial target discovery.

Information entropy of the generalized beta distribution

The output distribution of statistical variables characterizes the level of uncertainty of a complex system, the state of which is given by probabilistic changes in internal relationships. Information entropy is an effective tool for analysing the distribution of data in complex systems. Subfamilies of generalized beta distributions of the first and second types includes many simple distributions as special cases. These subfamilies are often used to model the output state of the system by distributions of random variables. There are conditions in the paper, that are imposed on the parameters of the generalized beta distribution to obtain relationships with simpler types. The paper contains an expression for calculating the information entropy, the generalized beta distribution, which includes distributions of the first and second kind as special cases. Expressions of information entropies for the most famous subfamilies of generalized beta distribution also are given.

(Invited) Benchmarking and Predicting the Risks of Commercial Li-Ion Cells Undergoing Thermal Runaway

The performance of commercial Li-ion batteries increases year after year. New mechanical designs of cells as well as changing electrolyte and active material compositions continually push performance boundaries forward. With such changes, the risks associated with thermal runaway of cells change too and a challenge persists in recording and benchmarking risks to determine whether increased performance comes at the expense of increased risk in the event of thermal runaway. The Battery Failure Databank provides a record of thermal and mass ejection behaviors of past and present commercial cells and provides a valuable resource for benchmarking behaviors and determining the predictability of risks associated with thermal runaway.A Fractional Thermal Runaway Calorimeter (FTRC), developed by the NASA Johnson Space Center in collaboration with the National Renewable Energy Laboratory (NREL), distinctly measures heat emitted from the body of commercial cells and heat that is ejected from the cell. The FTRC also facilitates in-situ high-speed radiography to link phenomena occurring inside the cell with external thermal measurements. The FTRC was used for all tests recorded in the Battery Failure Databank and high-speed radiographs accompany each thermal dataset. Having thermal, mass ejection, and internal dynamics behaviors from hundreds commercial cells under mechanical and thermal abuse conditions facilitates statistical analyses of cell behaviors and evaluation of the efficacy of machine learning methods for predicting risks associated with thermal runaway.Using data from the Battery Failure Databank, the following three topics will be covered in this talk: Correlations between heat generation and mass ejection: The total heat output from cells showed a strong correlation with the quantity of material ejected. An explanation for this based on distinct heat measurements from ejected and non-ejected materials will be discussed. Potential causes of outlier cells that produce exceptionally high heat: Upon conducting numerous repeat tests for each cell, outlier cells that produce exceptionally high quantities of heat were observed. High-speed radiography data revealed that internal dynamic phenomena can lead to extreme variations in thermal and ejection behavior observed externally. The predictability of thermal runaway outcomes using machine learning methods and limited data: With limited data on thermal behavior, mass ejection, and cell specifications, the accuracy of zero- and one-shot approaches to predicting the variation and distribution of heat output during thermal runaway of a new cell type, based on training data in the Battery Failure Databank, will be discussed. The analyses and open-access resources provided with this work are expected to provide a foundation for benchmarking the behavior and predictability of risks associated with thermal runaway of past and present commercial Li-ion cells. In addition to providing a valuable resource for designing safe battery systems, it is expected that this data will be imperative as we evaluate next generation cell designs and assess their respective failure mechanisms and associated risks.

The Trend of Research on Design for Healthy Ageing: A Visual Analysis Using VOSviewer and CiteSpace

Background: Based on the research needs of Design for healthy ageing, policy support visualizes and analyzes the output distribution, research hotspots, and cutting-edge trends of Design for healthy ageing related literature. Research Aim: In order to better carry out research in the field of design for healthy ageing segmentation, we use core data-bases to explore the progress of design for healthy ageing area research at home and abroad from a macro perspective. Methods: The method uses the Web of Science core col-lection database and China National Knowledge Infrastructure (CNKI) database as data sources to export the output distribution, research hotspots, and cutting-edge trend visualization graphs of literature. Results: The results were compared and reviewed with the help of visual literature analysis software VOSviewer and Citespace on relevant literature both domestically and internationally. Conclusions: The time course of research progress on ageing design and the development prospects of ageing design research discipline were summarized. Summarize the research progress and cutting-edge trends in the field, per-spective, and content of ageing design discipline. The conclusion is influenced by policies and the environment, and there are certain similarities and differences in domestic and foreign research. In the context of the sudden global epidemic, the exploration of social par-ticipation in design for the elderly is a common research hotspot. The difference lies in that foreign research focuses on Service design for the elderly, focusing on the health ageing framework of WHO, targeting families, basic nursing services, virtual health and design for healthy ageing service technologies.

The bias on characters’ visual traits in Japanese animation and the misconceived “transnationality” of anime

In the dynamics centred on East Asian cultural output, a special place is occupied by Japan’s production (namely, comics and animation, or manga and anime respectively) and the distribution and widespread consumption of this vast output around the world. 
 Despite the interpolations many anime series or films faced when exported, a specificity of the medium was/is usually recognised by foreign audiences. However, issues often unfold in the reception of anime’s visual codes, which entail problematical aspects in the grasping of the narratives and an underlying dimension of what I shall here call “graphic politics”. Today, the visual-narrative logics of anime characters’ physiognomies, and therefore, the motivations and intentions of their creators, are still largely misinterpreted based on culturally-inflected interpretations; this gives us clues on what the audiences of anime are, what they expect and draw from anime’s stories, and what this means for a global politics of anime as a medium of expression and a creative output. In this article, through the description of visual examples and established, or, at times controversial, scholarship in the field, I discuss the persistence of wide misunderstandings in the cultural politics of anime’s design and its impact on the reception of anime’s intentions globally.
 Among the collateral effects of this misunderstanding, a technical and moral justification to call (or imply as) “anime” animations designed and produced outside of Japan by non-Japanese authors seems to be emerging in the global discourse, thus privileging a fabricated idea of anime as just a “form” over anime as also and mainly a Japanese cultural artefact, in a momentous process of progressive dilution of the Japan-embedded characteristics of the animations made in Japan.

Trip Distribution and Modal Choice in the Taman Mini LRT Station Area

The surrounding Taman Mini LRT station boasts a diverse range of land uses, primarily characterized by residential zones, interspersed with dynamic activity hubs such as tourist attractions, shopping malls, and hospitals. The prevailing issue in this area relates to persistent traffic congestion, stemming from the overreliance on private vehicles, inadequate public transportation infrastructure, disjointed intermodal connections, and the lack of seamless integration between transportation modes and activity centers. This study endeavors to comprehensively analyze pedestrian and vehicular movement in the periphery of the Taman Mini LRT station. This analysis is pivotal in assessing the current mobility landscape. Notably, the intensity of activity within a particular land use directly correlates with its ability to draw vehicular traffic, consequently leading to prolonged waiting times for pedestrians at crosswalks. Employing a four-step model, this research methodically defines pedestrian and vehicular flow within the region. This model incorporates output distribution of trips and origin-destination graphs. Additionally, stated preference techniques are employed to discern respondents’ inclinations when making travel decisions. This involves evaluating key factors like travel time, fares, frequency, accessibility level, comfort, and safety – categories that significantly influence their preferences when selecting between LRT and other transportation modes.

Autostereoscopic 3D Measurement Based on Adaptive Focus Volume Aggregation

Autostereoscopic three-dimensional measuring systems are a kind of portable and fast precision metrology instrument. The systems are based on integral imaging that makes use of a micro-lens array before an image sensor to observe measured parts from multiple perspectives. Since autostereoscopic measuring systems can obtain longitudinal and lateral information within single snapshots rapidly, the three-dimensional profiles of the measured parts can be reconstructed by shape from focus. In general, the reconstruction process consists of data acquisition, pre-processing, digital refocusing, focus measures, and depth estimation. The accuracy of depth estimation is determined by the focus volume generated by focus measure operators which could be sensitive to the noise during digital refocusing. Without prior knowledge and surface information, directly estimated depth maps usually contain severe noise and incorrect representation of continuous surfaces. To eliminate the effects of refocusing noise and take advantage of traditional focus measure methods with robustness, an adaptive focus volume aggregation method based on convolutional neural networks is presented to optimize the focus volume for more accurate depth estimation. Since a large amount of data and ground truth are costly to acquire for model convergence, backpropagation is performed for every sample under an unsupervised strategy. The training strategy makes use of a smoothness constraint and an identical distribution constraint that restricts the difference between the distribution of the network output and the distribution of ideal depth estimation. Experimental results show that the proposed adaptive aggregation method significantly reduces the noise during depth estimation and retains more accurate surface profiles. As a result, the autostereoscopic measuring system can directly recover surface profiles from raw data without any prior information.

LEVEL OF ATTITUDE TOWARDS ONBOARDING ON EMPLOYEES' ORGANIZATIONAL COMMITMENT: BASIS FOR EFFECTIVE HYBRID ONBOARDING PROGRAM

A year-long onboarding procedure is essential for the successful integration of new employees into an organization; it consists of support, resources, and training. Psychological attachment to the organization, organizational commitment, and employee loyalty are critical determinants of employee engagement, work output, and leadership distribution. The impact of employee attitudes toward onboarding on organizational commitment and employee retention has been the subject of research, underscoring the criticality of implementing efficient onboarding initiatives. This study employed a descriptive-correlational research design and quantitative methods to examine the relationship between employees’ commitment to the organization and their sentiments regarding their employment. The investigation involved a total of 126 individuals, representing various hierarchical positions and functional divisions within a real estate organization. Respondents praised the orientation program, stating that it provided pertinent and useful information. Organizational commitment was approximately average, and there was a significant correlation between employees’ attitudes toward induction and their organizational commitment level. The findings of this study illustrate the importance of implementing successful induction initiatives in order to cultivate employee dedication to the company. It is recommended that employers design customized orientation initiatives that prioritize key elements influencing employee engagement and loyalty, with active employee participation. The study’s findings can be utilized by human resource managers to improve the employee experience and develop retention strategies that are more efficient. This research establishes a foundation for subsequent investigations in the field of Human Resource Management by identifying the factors that contribute to the effectiveness of induction and employee engagement.

Two‐sided productivity heterogeneity, firm boundaries, and assortative matching

AbstractWe consider a market where each firm is created by the combination of two complementary assets that are heterogeneous in their productivity. After assets match endogenously, their owners choose between two ownership structures: centralized organization (integration) and arm's length organization (nonintegration). Our main focus is on the interplay between productivity heterogeneity and firm boundary decisions. When firms choose between distinct ownership structures, the standard single‐crossing condition that guarantees positive assortative matching may fail to hold. We provide a novel condition—the congruent marginal contributions property—which guarantees monotone matching with respect to asset productivity. Furthermore, we provide conditions under which integration at the bottom of the productivity ladder is the market equilibrium; an organizational pattern that has been largely unexplored by the theoretical and empirical literature. We investigate the effect of model primitives on the equilibrium distribution of output. Moreover, our model offers interesting testable implications regarding firm boundary decisions.

LUV Score - a combination of bedside lung ultrasound and velocity-time integral (VTI) to predict mortality risk in STEMI patients

Abstract Background Early risk stratification is essential for in-hospital management of ST-segment–elevation myocardial infarction (STEMI). Development of acute heart failure and pulmonary edema is associated with poorer prognosis in this setting. Velocity–time integral (VTI) estimates stroke volume and cardiac output and has never been tested in acute coronary syndromes. Purpose Our aim was to evaluate the prognostic ability of a novel cardiothoracic ultrasound protocol for hemodynamic assessment with lung ultrasound (LUS) and VTI in patients with STEMI. Methods LUS and VTI were performed within 24h of admission for STEMI. LUS consisted of 8 scanning zones. A LUS combined with VTI (LUV) classification was developed. Receiver operating characteristic (ROC) analyses were performed to assess LUV score with in-hospital mortality, and it was compared with traditional Killip classification. Results From September 2022 and January 2023, 104 consecutive patients were admitted with ST-segment–elevation myocardial infarction. Fifteen patients were excluded from the analysis because were not assessed within 24h of admission. Therefore, 89 patients were included in the final analysis. Mean age was 62 years, 59% were male, 55% had hypertension, 32% had diabetes, 43% was anterior wall myocardial infarction and 16% had Killip 3 or 4 at admission. Overall in-hospital mortality was 7.9% and mortality across LUV categories were 0%, 0%, 8% and 50% for LUV A-D, respectively. A VTI ≥ 14 implied a negative predictive value for in-hospital mortality of 100%. The area under the ROC curve of LUV classification for in-hospital mortality was 0.92 (P=0.001), and Killip classification (0.85, P<0.001; P=0.48 for the difference between curves – Figure 1). Incidences of culprit vessel according to LUV categories are illustrated at Figure 2. There were no left main culprit vessel in our sample. The distribution of Cardiac Output (CO) and Cardiac index (CI) and Cardiac Power Output (CPO) were the following: LUV A: CO = 4.5 (1.2), CI = 4.0 (1.1) CPO = 0.9 (0.3); LUV B CO = 3.8 (0.9) CI = 3.4 (0.8) CPO = 0.7 (0.2); LUV C CO = 3.3 (0.8) CI = 3.0 (0.8) CPO = 0.6 (0.1) ; LUV D CO = 2.9 (0.7) CI = 2.7(0.5) CPO = 0.5(0.1). Conclusions In a cohort of patients with ST-segment–elevation myocardial infarction undergoing primary percutaneous coronary intervention, LUV score provided an excellent AUC for prediction of in-hospital mortality. LUV score is an easy, noninvasive, rapidly acquired, and accurate method for risk stratification in STEMI patients.

Fast Bayesian gravitational wave parameter estimation using convolutional neural networks

ABSTRACT The determination of the physical parameters of gravitational wave events is a fundamental pillar in the analysis of the signals observed by the current ground-based interferometers. Typically, this is done using Bayesian inference approaches which, albeit very accurate, are very computationally expensive. We propose a convolutional neural network approach to perform this task. The convolutional neural network is trained using simulated signals injected in a Gaussian noise. We verify the correctness of the neural network’s output distribution and compare its estimates with the posterior distributions obtained from traditional Bayesian inference methods for some real events. The results demonstrate the ability of the convolutional neural network to produce posterior distributions that are compatible with the traditional methods. Moreover, it achieves a remarkable inference speed, lowering by orders of magnitude the times of Bayesian inference methods, enabling real-time analysis of gravitational wave signals. Despite the observed reduced accuracy in the parameters, the neural network provides valuable initial indications of key parameters of the event such as the sky location, facilitating a multimessenger approach.

Variance-based global sensitivity analysis and uncertainty quantification of the AquaCrop model parameters for basil (Ocimum basilicum L.) under different nitrogen fertilizer rates

Dynamic crop models are powerful tools for evaluating crop responses to alternative management options. These models consist of various input parameters that need calibration before being implemented in a new environment. Sensitivity analysis (SA) has proven to be an efficient method for identifying dominant model parameters. This study aimed to determine influential parameters of the AquaCrop model for basil and also quantify output uncertainty under different nitrogen fertilizer rates. The Sobol’ SA method was employed to compute both first-order and total-order sensitivity indices. Results indicated that normalized water productivity (WP*) and crop coefficient (KcTr,x) were the most influential parameters across all treatments. Furthermore, as fertility stress increased, the interaction effects among parameters decreased. The temporal analysis of model output (biomass) revealed that parameter sensitivities were highly time-dependent. In addition, the uncertainty of predicted biomass was determined using combined violin and box plots. Results demonstrated that the optimal nitrogen fertilizer application rate extended the distribution of model output. In summary, these findings offer valuable insights for model simplification and effective decision-making.

Smoothing of Binary Codes, Uniform Distributions, and Applications.

The action of a noise operator on a code transforms it into a distribution on the respective space. Some common examples from information theory include Bernoulli noise acting on a code in the Hamming space and Gaussian noise acting on a lattice in the Euclidean space. We aim to characterize the cases when the output distribution is close to the uniform distribution on the space, as measured by the Rényi divergence of order α∈(1,∞]. A version of this question is known as the channel resolvability problem in information theory, and it has implications for security guarantees in wiretap channels, error correction, discrepancy, worst-to-average case complexity reductions, and many other problems. Our work quantifies the requirements for asymptotic uniformity (perfect smoothing) and identifies explicit code families that achieve it under the action of the Bernoulli and ball noise operators on the code. We derive expressions for the minimum rate of codes required to attain asymptotically perfect smoothing. In proving our results, we leverage recent results from harmonic analysis of functions on the Hamming space. Another result pertains to the use of code families in Wyner's transmission scheme on the binary wiretap channel. We identify explicit families that guarantee strong secrecy when applied in this scheme, showing that nested Reed-Muller codes can transmit messages reliably and securely over a binary symmetric wiretap channel with a positive rate. Finally, we establish a connection between smoothing and error correction in the binary symmetric channel.

Bibliometric Examination of Global Scientific Research about Carbapenem-Resistant Acinetobacter Baumannii (CRAB).

This review paper presents a comprehensive bibliometric analysis of the global scientific research pertaining to carbapenem-resistant Acinetobacter baumannii (CRAB) from the years 1996 to 2023. The review employs a systematic approach to evaluate the trends, patterns, and collaborative networks within the CRAB research landscape, shedding light on its substantial global health implications. An analysis of the Scopus database reveals that the earliest publication within the CRAB research domain dates back to 1996. By conducting a meticulous examination of publication output, citation trends, author affiliations, and keyword distributions, this paper provides valuable insights into the evolution of research themes and the emergence of new areas of interest concerning CRAB. The findings of this bibliometric analysis prominently feature the most influential author within this field, namely, Higgins PG, who has contributed a remarkable 39 documents to CRAB research. It is noteworthy that China leads in terms of the quantity of published research articles in this domain, whereas the United States occupies the foremost position about citations within the CRAB research sphere. Furthermore, a more profound exploration of the data yields a heightened understanding of the current status of CRAB research, emphasizing potential avenues for future investigations and underscoring the imperative need for collaborative initiatives to address the challenges posed by this antibiotic-resistant pathogen.

A fusion scheme for eliminating input interference induced by spelling errors

Spelling errors are a prevalent form of interference that may result from human handwriting or natural language processing systems, such as optical character recognition. This type of interference presents a challenge for natural language processing systems that rely on context-based embeddings to comprehend the exact semantics of a sentence. The proposed fusion scheme is the main focus of this paper, which aims to correct spelling errors in sentences. The scheme employs both the original input and the masked input. The masked input is acquired by utilizing a detection module to mask any spelling errors present in the original input. By utilizing the masked input, the scheme is capable of learning the real sentence semantic information that is not affected by spelling errors. Utilizing the original input can prevent the loss of input information resulting from masking operations. Finally, the utilization of the Kullback-Leibler divergence is employed to establish concordance between the two output distributions within the framework, consequently facilitating the acquisition of comprehensive input information, all while mitigating the influence of spelling errors. Experiments were conducted on two widely used benchmarks. Compared with previous methods, the approach presented herein exhibited superior performance as it achieved improvements on two benchmarks.

FTG: Score-based black-box watermarking by fragile trigger generation for deep model integrity verification

Deep neural networks (DNNs) are widely used in real-world applications, thanks to their exceptional performance in image recognition. However, their vulnerability to attacks, such as Trojan and data poison, can compromise the integrity and stability of DNN applications. Therefore, it is crucial to verify the integrity of DNN models to ensure their security. Previous research on model watermarking for integrity detection has encountered the issue of overexposure of model parameters during embedding and extraction of the watermark. To address this problem, we propose a novel score-based black-box DNN fragile watermarking framework called fragile trigger generation (FTG). The FTG framework only requires the prediction probability distribution of the final output of the classifier during the watermarking process. It generates different fragile samples as the trigger, based on the classification prediction probability of the target classifier and a specified prediction probability mask to watermark it. Different prediction probability masks can promote the generation of fragile samples in corresponding distribution types. The whole watermarking process does not affect the performance of the target classifier. When verifying the watermarking information, the FTG only needs to compare the prediction results of the model on the samples with the previous label. As a result, the required model parameter information is reduced, and the FTG only needs a few samples to detect slight modifications in the model. Experimental results demonstrate the effectiveness of our proposed method and show its superiority over related work. The FTG framework provides a robust solution for verifying the integrity of DNN models, and its effectiveness in detecting slight modifications makes it a valuable tool for ensuring the security and stability of DNN applications.

Hazard Curves for Reliability Assessment of Strip Footings on Spatially Varying Cohesive Soils

The present study aimed to create a series of hazard curves against maximum total settlement and angular rotation of strip footings for probabilistic shallow foundation design on clays. Random field finite element method (RFEM) was adopted with elasto-plastic clay-like soil behavior, deformation modulus (Ed) and shear strength parameters (c and ) were employed as random field inputs. Parameters were defined and assigned to the analysis models with varying correlation lengths (h, v). Models have been iteratively solved one thousand times, and output distributions of maximum settlement and angular rotations were recorded. Probability density functions (PDF) were fitted to the outputs, and probability of failure (Pf) for footing deformation limits was subsequently estimated. Proposed hazard curves for two anisotropy and three variability categories were developed employing the estimated Pfs. The method proposed has been validated using an independent database of in-situ results, and a worked example was provided to illustrate the implementation of the process. The key contribution of the research is to form hazard curves for shallow foundations considering elasto-plastic soil behavior with the impact of all influencing parameters, respecting the limit values for foundation deformation in the design codes. The proposed technique offers a probabilistic evaluation of strip footings with spatial variation of clayey soils and a valid method for the reliability-based design of foundations in the serviceability limit state.

Flow-Based Spatio-Temporal Structured Prediction of Motion Dynamics.

Conditional Normalizing Flows (CNFs) are flexible generative models capable of representing complicated distributions with high dimensionality and large interdimensional correlations, making them appealing for structured output learning. Their effectiveness in modelling multivariates spatio-temporal structured data has yet to be completely investigated. We propose MotionFlow as a novel normalizing flows approach that autoregressively conditions the output distributions on the spatio-temporal input features. It combines deterministic and stochastic representations with CNFs to create a probabilistic neural generative approach that can model the variability seen in high-dimensional structured spatio-temporal data. We specifically propose to use conditional priors to factorize the latent space for the time dependent modeling. We also exploit the use of masked convolutions as autoregressive conditionals in CNFs. As a result, our method is able to define arbitrarily expressive output probability distributions under temporal dynamics in multivariate prediction tasks. We apply our method to different tasks, including trajectory prediction, motion prediction, time series forecasting, and binary segmentation, and demonstrate that our model is able to leverage normalizing flows to learn complicated time dependent conditional distributions.

Optimize configuration of multi-energy storage system in a standalone microgrid

Aiming at the integrated energy microgrid, an important part of the energy internet, this paper constructs a multi-energy storage system optimization configuration model of the integrated energy microgrid in an independent mode, and proposes a configuration method that includes the rated power and capacity of the storage system and the heat storage system. The storage system model includes the estimation of battery life during heating and non-heating periods. The model takes economy as the index, and considers the relevant constraints of thermoelectric coupling of thermoelectric units, including thermal and electrical balance, unit climb, energy storage system and self-sufficiency probability, etc., and uses a The bacterial colony chemotaxis (BCC) algorithm model based on unit output and energy storage system power distribution strategy to solve the problem. The operation characteristics of cogeneration units equipped with energy storage system are discussed. The results show that the proposed multi-energy storage system configuration method has significant economic and environmental benefits in both heating and non-heating periods, and promotes the uptake of wind power.