Explicit Inputs Research Articles

Pushing with Soft Robotic Arms via Deep Reinforcement Learning

Soft robots can adaptively interact with unstructured environments. However, nonlinear soft material properties challenge modeling and control. Learning‐based controllers that leverage efficient mechanical models are promising for solving complex interaction tasks. This article develops a closed‐loop pose/force controller for a dexterous soft manipulator enabling dynamic pushing tasks using deep reinforcement learning. Force tests investigate the mechanical properties of a soft robot module, resulting in orthogonal forces of N. Then, the policy is trained in simulation leveraging a dynamic Cosserat rod model of the soft robot. Domain randomization mitigate the sim‐to‐real gap while careful reward engineering induced pose and force control even without explicit force inputs. Despite the approximate simulation, the sim‐to‐real transfer achieved an average reaching distance of mm (), an average orientation error of rad () and applied pushing forces up to N. Such performance is reasonable for the intended assistive tasks of the manipulator. The experiments uncovered that the soft robot interacting with the environment exhibited torsional and counter‐balancing movements. Although not explicitly enforced, they emerged from the mechanical intelligence of the manipulator. The results demonstrate the potential of soft robotic manipulation via reinforcement learning.

A new Q‐function structure for model‐free adaptive optimal tracking control with asymmetric constrained inputs

SummaryThis article aims to design a model‐free adaptive tracking controller for discrete‐time nonlinear systems with unknown dynamics and asymmetric control constraints. First, a new Q‐function structure is designed by introducing the control input into the tracking error of the next moment, in order to eliminate the final tracking error, avoid the steady control, and ignore the discount factor. Second, via system transformation, a general performance index is developed to overcome the challenge caused by asymmetric constraints of implicit control inputs. By this operation, the constrained tracking problem is converted to an unconstrained optimal tracking problem without the traditional nonquadratic performance function that is only applicable to explicit control inputs. Then, a value‐iteration‐based Q‐learning (VIQL) algorithm is derived to seek the optimal Q‐function and the optimal control policy by using offline data rather than the mathematical model. Next, the convergence, monotonicity, and stability properties of VIQL are investigated to demonstrate that the iterative Q‐function sequence can converge to the optimal Q‐function under ideal conditions. To realize the VIQL algorithm, the critic neural network is employed to approximate the Q‐function. Finally, simulation results and comparative experiments are conducted to demonstrate the validity and effectiveness of the present VIQL scheme.

Speech-Driven Personalized Gesture Synthetics: Harnessing Automatic Fuzzy Feature Inference.

Speech-driven gesture generation is an emerging field within virtual human creation. However, a significant challenge lies in accurately determining and processing the multitude of input features (such as acoustic, semantic, emotional, personality, and even subtle unknown features). Traditional approaches, reliant on various explicit feature inputs and complex multimodal processing, constrain the expressiveness of resulting gestures and limit their applicability. To address these challenges, we present Persona-Gestor, a novel end-to-end generative model designed to generate highly personalized 3D full-body gestures solely relying on raw speech audio. The model combines a fuzzy feature extractor and a non-autoregressive Adaptive Layer Normalization (AdaLN) transformer diffusion architecture (DiTs-based). The fuzzy feature extractor harnesses a fuzzy inference strategy that automatically infers implicit, continuous fuzzy features. These fuzzy features, represented as a unified latent feature, are fed into the AdaLN transformer. The AdaLN transformer introduces a conditional mechanism that applies a uniform function across all tokens, thereby effectively modeling the correlation between the fuzzy features and the gesture sequence. This module ensures a high level of gesture-speech synchronization while preserving naturalness. Finally, we employ the diffusion model to train and infer various gestures. Extensive subjective and objective evaluations on the Trinity, ZEGGS, and BEAT datasets confirm our model's superior performance to the current state-of-the-art approaches. Persona-Gestor improves the system's usability and generalization capabilities, setting a new benchmark in speech-driven gesture synthesis and broadening the horizon for virtual human technology.

Physics-informed neural network reconciles Australian displacements and tectonic stresses

Stress orientation information is invaluable to evaluate active tectonic forces within the Earth’s crust. The global dataset provided by the World Stress Map offers a rich resource of stress indicators, facilitating the calibration of mechanical models to extract complete stress and displacement fields. However, traditional inversion processes are hampered by the manual tuning of geomechanical properties and boundary conditions to reconcile simulations with observations. In this study, we introduce ML-SEISMIC (machine learning for stress estimation integrating satellite image and computational modelling), a physics-informed deep neural network approach to autonomously align stress orientation data with an elastic model. It nearly completely bypasses the need for explicit boundary condition inputs and yields comprehensive distributions of material properties, displacements, and stress tensors. Application of this methodology to Australia, coupled with precise global navigation satellite systems observations, unveils a robust and scale-independent interpolation framework. Additionally, it pinpoints regions where stress orientation reinterpretation is warranted. Our results present a streamlined yet powerful process, offering a substantial leap forward in geodynamic investigations. This approach promises to unify velocity and stress orientation observations with physical models, ushering in a new era of insights into Earth’s dynamic processes.

A Multi-Objective Optimization-Algorithm-Based ANFIS Approach for Modeling Dynamic Customer Preferences with Explicit Nonlinearity

In previous studies, customer preferences were assumed to be static when modeling their preferences based on online reviews. However, in fact, customer preferences for products are dynamic and changing over time. Few research has been conducted to model dynamic customer preferences as the time series data of customer preference are difficult to be obtained. Based on online reviews, an adaptive neuro fuzzy inference system (ANFIS) was introduced to model customer preferences, which can take into account the fuzzy nature of customers’ emotions and the nonlinearity of the model. However, ANFIS is plagued with black box problems, and the nonlinearity of the model cannot be directly demonstrated. To address the above research issues, a multi-objective chaos optimization algorithm (MOCOA)-based ANFIS approach is proposed to generate customer preferences models by using online reviews, which has explicit nonlinear inputs. Firstly, a sentiment analysis approach is used to derive information from online reviews by periods, which is used as the time series data sets of the proposed model. A MOCOA is combined into ANFIS to identify the nonlinear inputs, which include single items, interactive items, and terms of second order and/or higher-order terms. Consequently, the fuzzy rules in ANFIS are expressed in polynomial form, which allows for the explicit representation of the nonlinearity between customer preferences and product attributes. A case study of sweeping robots is used to compare the validation results of the proposed approach with those of ANFIS, subtractive cluster-based ANFIS, fuzzy c-means-based ANFIS, and K-means-based ANFIS. Moreover, the proposed approach provides better performance than the other four approaches in terms of mean relative error and variance of error.

Linking Biodiversity and Human Wellbeing in Systematic Conservation Assessments of Working Landscapes

Systematic land use planning to address environmental impacts does not typically include human health and wellbeing as explicit inputs. We tested the effects of including issues related to human health, ecosystem services, and community wellbeing on the outputs of a standard land use planning process which is primarily focused on environmental variables. We consulted regional stakeholders to identify the health issues that have environmental links in the Sacramento, California region and to identify potential indicators and datasets that can be used to assess and track these issues. Marxan planning software was used to identify efficient land use patterns to maximize both ecological conservation and human health outcomes. Outputs from five planning scenarios were compared and contrasted, resulting in a spatially explicit series of tradeoffs across the scenarios. Total area required to meet imputed goals ranged from 10.4% to 13.4% of the total region, showing somewhat less efficiency in meeting biodiversity goals when health outcomes are included. Additionally, we found 4.8% of residential areas had high greening needs, but this varied significantly across the six counties. The work provides an example of how integrative assessment can help inform management decisions or stakeholder negotiations potentially leading to better management of the production landscapes in food systems.

Hierarchy performance assessment of industrial solid waste utilization - tracking resource recycling and utilization centers in China.

The massive production and accumulation of industrial solid waste (ISW) have led to environmental pollution and natural resource underutilization. China's efforts to build trial industrial waste resource utilization centers provide strong support for sustainable development. However, these centers and the factors driving ISW utilization have yet to be evaluated. This paper utilizes context-dependent data envelopment analysis models without explicit inputs (DEA-WEI) to evaluate the overall utilization performance of 48 industrial waste resource utilization centers in China from 2018 to 2020. It also builds a Tobit model to assess which indicators and waste types affect overall ISW utilization. The results show overall ISW utilization performance of centers in the sample has improved, with the average value falling from 1.7193 in 2018 to 1.5624 in 2020. However, there are clear regional performance gaps, with East China having the highest utilization performance (1.3113) while the Southwest had the lowest (2.2958). Finally, this paper proposes measures to improve the overall utilization of industrial waste resources based on an analysis of the factors driving solid waste utilization.

A Data Envelopment Analysis model for ranking digital development in the countries of the European Union without explicit inputs and common weights analysis

This study aims to rank the 28 countries of the pre-Brexit European Union (EU) based on the five principal dimensions of the Digital Economy and Society Index (DESI). Instead of ranking them according to the European Commission’s scoring model with arbitrary predefined weights, we use more objective ranking methods that rely on the statistical properties of our data set. We establish our rankings using Data Envelopment Analysis (DEA) Without Explicit Inputs (WEI) or DEA-type Composite Indicators (DEA/CI), and we then determine the position of EU member states. The advantage of the DEA/WEI and DEA/CI methods over the traditional DEA is that they can be applied without distortive data transformations even if we only have output criteria (to be maximized). From a methodological point of view, the paper proposes a new method for determining the common weights, where the goodness of efficiency is measured by correlation.

An Algorithm for Solving Zero-Sum Differential Game Related to the Nonlinear H∞ Control Problem

This paper presents an approach for the solution of a zero-sum differential game associated with a nonlinear state-feedback H∞ control problem. Instead of using the approximation methods for solving the corresponding Hamilton–Jacobi–Isaacs (HJI) partial differential equation, we propose an algorithm that calculates the explicit inputs to the dynamic system by directly performing minimization with simultaneous maximization of the same objective function. In order to achieve numerical robustness and stability, the proposed algorithm uses: quasi-Newton method, conjugate gradient method, line search method with Wolfe conditions, Adams approximation method for time discretization and complex-step calculation of derivatives. The algorithm is evaluated in computer simulations on examples of first- and second-order nonlinear systems with analytical solutions of H∞ control problem.

An efficiency curve for evaluating imbalanced classifiers considering intrinsic data characteristics: Experimental analysis

Balancing the accuracy rates of the majority and minority classes is challenging in imbalanced classification. Furthermore, data characteristics have a significant impact on the performance of imbalanced classifiers, which are generally neglected by existing evaluation methods. The objective of this study is to introduce a new criterion to comprehensively evaluate imbalanced classifiers. Specifically, we introduce an efficiency curve that is established using data envelopment analysis without explicit inputs (DEA-WEI), to determine the trade-off between the benefits of improved minority class accuracy and the cost of reduced majority class accuracy. In sequence, we analyze the impact of the imbalanced ratio and typical imbalanced data characteristics on the efficiency of the classifiers. Empirical analyses using 68 imbalanced data reveal that traditional classifiers such as C4.5 and the k-nearest neighbor are more effective on disjunct data, whereas ensemble and undersampling techniques are more effective for overlapping and noisy data. The efficiency of cost-sensitive classifiers decreases dramatically when the imbalanced ratio increases. Finally, we investigate the reasons for the different efficiencies of classifiers on imbalanced data and recommend steps to select appropriate classifiers for imbalanced data based on data characteristics.

Comparison of machine learning algorithms for emulation of a gridded hydrological model given spatially explicit inputs

This study compares the performance of several machine learning algorithms in reproducing the spatial and temporal outputs of the process-based, hydrological model, ParFlow.CLM. Emulators or surrogate models are often used to reduce complexity and simulation times of complex models, and have typically been applied to evaluate parameter sensitivity or for model parameter tuning, without explicit treatment of variation resulting from spatially explicit inputs to the model. Here we present a case study in which we evaluate candidate machine learning algorithms for suitability emulating model outputs given spatially explicit inputs. We find that among random forest, gaussian process, k-nearest neighbors, and deep neural networks, the random forest algorithm performs the best on small training sets, is not as sensitive to hyperparameters chosen for the machine learning model, and can be trained quickly. Although deep neural networks were hypothesized to be able to better capture the potential nonlinear interactions in ParFlow.CLM, they also required more training data and much more refined tuning of hyperparameters to achieve the potential benefits of the algorithm.

Explicit Port-Hamiltonian FEM-Models for Linear Mechanical Systems with Non-Uniform Boundary Conditions

In this contribution, we present how to obtain explicit state space models in port-Hamiltonian form when a mixed finite element method is applied to a linear mechanical system with non-uniform boundary conditions. The key is to express the variational problem based on the principle of virtual power, with both the Dirichlet (velocity) and Neumann (stress) boundary conditions imposed in a weak sense. As a consequence, the formal skew-adjointness of the system operator becomes directly visible after integration by parts, and, after compatible FE discretization, the boundary degrees of freedom of both causalities appear as explicit inputs in the resulting state space model. The rationale behind our formulation is illustrated using a lumped parameter example, and numerical experiments on a one-dimensional rod show the properties of the approach in practice.

Prevailing narratives versus reality of a small and medium town decline in a CEE country

It is a common narrative that small and medium towns of formerly socialist countries of Central and Eastern Europe (CEE) are suffering a substantial decline due to better offerings in bigger metropolitan areas. Focused on Slovakia, this paper presents a methodology for assessing the future viability of small and medium towns, considering different socio-economic, infrastructural, and demographic aspects capturing their desirability. The proposed methodology aggregates different aspects into attributes by means of a data envelopment analysis model with common set of weights without explicit inputs (CSW DEA-WEI), and then converts these attributes into scores in the fashion of a multiple criteria decision analysis (MCDA). The methodology offers a new perspective for rating the viability and sustainability of small and medium towns in the CEE region, and is amenable to adaptations elsewhere. Contrary to popular belief, it is found that small and medium towns remain attractive for life.

Classification of University Departments of Industrial Engineering in Colombia: A DEA Application without Explicit Inputs

The article describes the use and applicability of Data Envelopment Analysis without Explicit Input (DEA-WEI) to evaluate the performance in SaberPRO tests of 82 industrial engineering programs in Colombia during 2016-2018. The results obtained can be used as an instrument to strengthen the quality assurance processes in higher education. As a result of applying the DEA-WEI model, the universities could be classified into five homogeneous groups, each with different characteristics. This grouping can be used as a strategic tool for the higher education institutions since it was possible to identify the other institutions' reference universities. In the current environment, evaluating a university's academic program's performance and its comparison with other universities is an essential issue for students, state control agencies, and universities to improve their indicators for accreditation processes. This classification can serve as a comparative measure of the educational quality offered by each university. In some countries, these classification results serve as a reference for allocating resources by the State for financing infrastructure and research projects. In Colombia, one of the indicators of quality in higher education is the standardized tests called SaberPRO, taken by all students in the last year of any academic program.

OptoSense

Ubiquitous computing requires robust and sustainable sensing techniques to detect users for explicit and implicit inputs. Existing solutions with cameras can be privacy-invasive. Battery-powered sensors require user maintenance, preventing practical ubiquitous sensor deployment. We present OptoSense, a general-purpose self-powered sensing system which senses ambient light at the surface level of everyday objects as a high-fidelity signal to infer user activities and interactions. To situate the novelty of OptoSense among prior work and highlight the generalizability of the approach, we propose a design framework of ambient light sensing surfaces, enabling implicit activity sensing and explicit interactions in a wide range of use cases with varying sensing dimensions (0D, 1D, 2D), fields of view (wide, narrow), and perspectives (egocentric, allocentric). OptoSense supports this framework through example applications ranging from object use and indoor traffic detection, to liquid sensing and multitouch input. Additionally, the system can achieve high detection accuracy while being self-powered by ambient light. On-going improvements that replace Optosense's silicon-based sensors with organic semiconductors (OSCs) enable devices that are ultra-thin, flexible, and cost effective to scale.

Dynamic Performance Evaluation of Blockchain Technologies

In recent years, the rapid development of blockchain technologies have attracted worldwide attention. Its application has been extended to many fields, such as digital finance, supply chain management, and digital asset transactions. For some enterprises and users, how to choose the most effective platform from many blockchains to control costs and share data is an important issue. To comprehensively evaluate the blockchain technologies, we first construct three-level evaluation indicators in terms of technical, market, and popularity indicators. Then, we propose an improved global DEA-Malmquist index without explicit inputs to assess the dynamic performance of blockchain technologies. Finally, we carry out an empirical analysis to evaluate 31 public blockchains’ performance from May 2018 to April 2020. The results indicate that the overall performance of blockchain technologies is basically on the rise. Some blockchain technologies that have not yet received widespread attention have shown good dynamic performance.

JustWalk: A Crowdsourcing Approach for the Automatic Construction of Indoor Floorplans

Mapping and navigation applications are now considered popular services for mobile phones users. However, despite the fact that people spend most of their time indoors, these applications are still limited to indoor spaces due to the lack of large-scale indoor floorplan databases. In this paper, we present JustWalk: a crowd intelligence-based system for the automatic construction of buildings floorplans. JustWalk employs a participatory sensing approach using smartphones that are ubiquitously available with users who visit a building to automatically and transparently construct accurate motion traces. These accurate traces are generated by reducing the errors in the inertial motion traces by using the points of interest in the indoor environment (e.g., elevators and stairs, etc.) for error resetting. The collected traces are then processed by means of different mathematical and image processing techniques to detect the overall floorplan shape as well as higher level semantics such as detecting rooms and corridors shapes along with a variety of points of interest in the environment. In comparison to other approaches, our system depends only on the users walking patterns and motion traces. It does not require any explicit inputs or obtrusive actions (e.g., taking photos). Experimental evaluation of JustWalk using different android phones in three testbeds shows that it achieves high accuracy for the point of interest detection (0.6 percent false positive and 1 percent false negative rates). In addition, the proposed error resetting technique leads to more than 12 times enhancement in the median distance error compared to the state-of-the-art. Moreover, the detailed floorplan can be accurately estimated with a relatively small number of traces. This number is amortized over the number of users visiting the building. Finally, we show that JustWalk has a small energy footprint on cell-phones, and could be generalized to other buildings; highlighting its promise as a ubiquitous indoor mapping service.

Nonlinear Sliding Mode and Distributed Control of Battery Energy Storage and Photovoltaic Systems in AC Microgrids With Communication Delays

This paper proposes a distributed fixed-time multiagent control strategy for the frequency restoration, voltage regulation, state of charge balancing, and proportional reactive power sharing between photovoltaic battery systems distributed in a microgrid with communication time delays. First, the feedback linearization method is applied to find the direct relationships between explicit states and control inputs. Then, based on the model, the distributed fixed-time cooperative control system restores the frequency, regulates the average voltage to the nominal value, and achieves accurate power sharing. For the state of charge balancing, a fixed-time observer is proposed to estimate the average state of charge of a battery using only information from neighbors. Based on the estimated value, a local fixed-time sliding mode control is applied to achieve the balanced state of charge. Due to robustness of the fixed-time control strategy, the balanced state of charge can be maintained despite intermittent photovoltaic generation and variable loads. The Artstein's transformation is applied to ensure the stability of the time delayed system. The dynamic performance is verified with an RTDS Technologies real-time digital simulator, using switching converter models, nonlinear lead-acid battery models, photovoltaic generation, and communication delays in a European benchmark microgrid.

Evaluating the Latent Determinants of Childhood Malnutrition: A Hierarchical Analysis of Nigeria and Kenya

Background: Malnutrition is responsible for 45% of all deaths among children worldwide. Despite a remarkable reduction in global poverty and famines, substantial childhood malnutrition continues to persist. In 2017, acute malnutrition (wasting) menaced over 50 million young children while over 150 million young children suffered from chronic malnutrition (stunting). Intervention organizations increasingly demand data-based decision making with a particular propensity for spatial and hierarchical heterogeneity. Methods: We review 57 disaggregate empirical studies of the determinants of childhood malnutrition in Africa published since 1990. We survey this corpus to identify deficiencies which may impede progress in reducing malnutrition. We develop hierarchical econometric models (four-level random intercept hierarchical generalized logit model), to perform a reanalysis of malnutrition in Kenya and Nigeria employing repeated cross-sectional data from the Demographic and Health Surveys and spatially explicit climatic inputs. We evaluate the responsiveness of malnutrition indicators to latent determinants, judged on the basis of their epidemiological and actionable significance. Findings: Of the 57 studies, we find a heterogenous patchwork of research which neglects countries where malnutrition is most severe. Only three studies interpret and discuss how much factors determine malnutrition with rigorous methodologies, and only 11 studies acknowledge the heterogeneity of social experience and consider how the effects change across and between different hierarchies. In our example reanalysis, we find that 28 to 36 percent of variation in malnutrition outcomes is explained through the hierarchical specification. And the most impactful latent determinants of malnutrition include mother’s education, household wealth, healthcare practices, and climatic stress, each with the capacity to reduce malnutrition prevalence rates by as much as 50%. Interpretation: Geospatial and disaggregated data helps one to understand better who is malnourished as well as where and how to target mitigation efforts at subnational levels. With explicit measurements of how much factors determine malnutrition, intervention organizations and governments may begin to make substantial progress to reduce childhood malnutrition. Funding Statement: The work was supported by the UK Aid from the UK Department for International Development (DFID) (grant numbers. PO 7442). Declaration of Interests: The authors declare no competing interests. Ethics Approval Statement: Not required.

Using Two-layer Minimax Optimization and DEA to Determine Attribute Weights

This study aims to explore a novel method for determining attribute weights, which is a key issue in constructing and analyzing multiple-attribute decision-making (MADM) problems. To this end, a hybrid approach combining the data envelopment analysis (DEA) model without explicit inputs (DEA-WEI) and a two-layer minimax optimization scheme is developed. It is demonstrated that in this approach, the most favorable set of weights is first considered for each alternative or decision-making unit (DMU) and these weight sets are then aggregated to determine the best compromise weights for attributes, with the interests of all DMUs simultaneously considered in a fair manner. This approach is particularly suitable for situations where the preferences of decision-makers (DMs) are either unclear or difficult to acquire. Two case studies are conducted to illustrate the proposed approach and its use for determining weights for attributes in practice. The first case concerns the assessment of research strengths of 24 selected countries using certain measures, and the second concerns the analysis of the performance of 64 selected Chinese universities, where the preferences of DMs are either unknown or ambiguous, but the weights of the attributes should be assigned in a fair and unbiased manner.