Search

Data processing in robotics is currently challenged by the effective building of multimodal and common representations. Tremendous volumes of raw data are available and their smart management is the core concept of multimodal learning in a new paradigm for data fusion. Although several techniques for building multimodal representations have been proven successful, they have not yet been analyzed and compared in a given production setting. This paper explored three of the most common techniques, (1) the late fusion, (2) the early fusion, and (3) the sketch, and compared them in classification tasks. Our paper explored different types of data (modalities) that could be gathered by sensors serving a wide range of sensor applications. Our experiments were conducted on Amazon Reviews, MovieLens25M, and Movie-Lens1M datasets. Their outcomes allowed us to confirm that the choice of fusion technique for building multimodal representation is crucial to obtain the highest possible model performance resulting from the proper modality combination. Consequently, we designed criteria for choosing this optimal data fusion technique. [ABSTRACT FROM AUTHOR]

The effectiveness of the hydraulic fracturing procedure is crucially dependent on the stage of fracture planning and design. Forecasting fracture behavior in rock formations characterized by non-uniform toughness is a serious challenge. In the present paper, a planar-3D model considering the rock's non-uniform fracture toughness has been developed for the uneven propagation of a hydraulic fracture. The series of numerical experiments were designed to study the effect of inhomogenous fracture toughness. The results show that the fracture toughness contract significantly controls the overall direction of fracture propagation, and a combination of toughness contrast and the proportion between the pay zone and barrier zone determine the fracture profile: from almost circular with or without a pair of narrow wedges when the proportion is small to almost rectangular otherwise. This paper also discusses the process of cleaning a fracture from hydraulic fracturing fluid by oil. Using numerical modeling on the basis of the constructed mathematical model, a relationship is established between the quality of hydraulic fracture cleaning and the geometrical parameters of the fracture and the region filled with the hydraulic fracturing fluid. The results of numerical experiments show that while fracturing fluid is more viscous than oil, the length of the fracture has a greater influence on the cleaning process than the viscosity of the fracturing fluid. [ABSTRACT FROM AUTHOR]

The aim of predictive maintenance, within the field of prognostics and health management (PHM), is to identify and anticipate potential issues in the equipment before these become serious. The main challenge to be addressed is to assess the amount of time a piece of equipment will function effectively before it fails, which is known as remaining useful life (RUL). Deep learning (DL) models, such as Deep Convolutional Neural Networks (DCNN) and Long Short-Term Memory (LSTM) networks, have been widely adopted to address the task, with great success. However, it is well known that these kinds of black box models are opaque decision systems, and it may be hard to explain their outputs to stakeholders (experts in the industrial equipment). Due to the large number of parameters that determine the behavior of these complex models, understanding the reasoning behind the predictions is challenging. This paper presents a critical and comparative revision on a number of explainable AI (XAI) methods applied on time series regression models for PM. The aim is to explore XAI methods within time series regression, which have been less studied than those for time series classification. This study addresses three distinct RUL problems using three different datasets, each with its own unique context: gearbox, fast-charging batteries, and turbofan engine. Five XAI methods were reviewed and compared based on a set of nine metrics that quantify desirable properties for any XAI method. One of the metrics introduced in this study is a novel metric. The results show that Grad-CAM is the most robust method, and that the best layer is not the bottom one, as is commonly seen within the context of image processing. [ABSTRACT FROM AUTHOR]

The phenomenon of firms grouping together has been extensively researched and is commonly known as industrial clusters. There are various ways to categorize these clusters, and in this paper, we adopt Markusen's classification, which identifies four distinct types of industrial districts: the Marshallian/Italianate type, the hub-and-spoke type, the satellite industrial platforms, and the state-anchored clusters. Adding to Markusen's typology, we will also try to delineate these two clusters' "European Aspects". We will examine if they have developed any "inter-European" synergy/ies with other entities (clusters, companies, E.U. institutions, etc.) of the E.U. ecosystem. The creation of such synergies includes the creation of technology innovation and interpersonal networks to serve as conduits for the diffusion of knowledge and exchange of information, the development of innovation initiatives between the entities of the technological ecosystem of the E.U. defense industry, and the creation of tangible "knowledge links". The aim of this study is to investigate which of the four types of industrial clusters described by Markusen the French Aerospace Valley cluster of the Midi-Pyrénées and Acquitaine regions and the Andalucia Aerospace cluster belong to. [ABSTRACT FROM AUTHOR]

Underground mining safety risk increases with the more complicated geological conditions in deep strata, so coal mines turn to the upper limit mining of shallow coal seams under the Cenozoic strata. Nevertheless, coal mines in the Northern China coalfield are mainly covered by thicker loose sandy layers with more abundant water. The analysis of overburdened strata deformation properties is essential for safe, efficient, and environmentally friendly production. This paper discusses the deformation and migration of overburdened strata through mechanical analysis, numerical and physical similar simulations, and in situ field measurement. A thorough understanding of overburdened strata deformation induced by mining has been obtained, and the results are as follows: The immediate roof first collapses to form the caved zone accompanied by the first weighting, and the fractured zone and bending deformation zone begin to develop in sequence; the separation layer is observed during the period of fracture development. However, the occurrence of the bending deformation subsidence results in the closure of the separation space; the ratio of fractured and mining height is quantified to 14.4:1.0 by the comparative analysis. The results may serve as technical evidence to support the mining safety of the study area and other coal mines with similar geological conditions. [ABSTRACT FROM AUTHOR]

Energy communities (ECs), intended as collective action initiatives in the energy field involving citizens' participation, have been gaining relevance for the past decades as an alternative way to organize the energy chain to challenge the incumbent system. With Europe's recently adopted Clean Energy Package, ECs found a formal recognition by the European Union as potential actors of the transition of the energy system towards a wider and more decentralized use of renewable sources. Although the potential role of ECs in the transition is therefore hardly questionable, a thorough comprehension of the enabling factors that might foster their diffusion and scaling up is still lacking. Through a comparative analysis of the evolutionary trajectories in six EU countries regarding their energy systems, their regulatory frameworks and their historical evolution of ECs, namely through the example of cooperative models, this paper aims at providing some preliminary evidence about the factors and dynamics that seem to have played, and may play, a role in hampering or facilitating EC model diffusion. Attention is therefore specifically paid to three dimensions of analysis referring to: the energy mix and market structure; the institutional and policy landscape; the wider social attitudes towards environmental issues and cooperation among citizens. In addition to providing a wide comparison of different EU countries, the paper shows that the historical evolution pathways have to be carefully taken into account to understand what might trigger ECs exploitation in the EU. [ABSTRACT FROM AUTHOR]

The analytical model of a permanent magnet eddy current coupler (PMECC) is mainly used for evaluation of its characteristics and the initial optimization of design. Based on the equivalent magnetic circuit method, this paper carries out analytical modeling for four typical PMECCs composed of surface-mounted and interior permanent magnet, slotted and non-slotted conductor rotors, which provides a theoretical basis for the subsequent research in this paper. The basic electromagnetic characteristics of the PMECCs are investigated by the established analytical model. Simultaneously, the analytical results about permeance, flux density, torque and power are verified by FEA simulation. The analysis results show that the slotted CR will obtain a much higher power density, and the iron loss mainly exists in the CRs. In addition, the analytical and FEA results agree well, which proves the reliability of the proposed, nearly unified analytical model. [ABSTRACT FROM AUTHOR]

UAVs—unmanned aerial vehicles—facilitate data acquisition at temporal and spatial scales that still remain unachievable for traditional remote sensing platforms. However, current legal frameworks that regulate UAVs present significant barriers to research and development. To highlight the importance, impact, and diversity of UAV regulations, this paper provides an exploratory investigation of UAV regulations on the global scale. For this, the methodological approach consists of a research synthesis of UAV regulations, including a thorough literature review and a comparative analysis of national regulatory frameworks. Similarities and contrasting elements in the various national UAV regulations are explored including their statuses from the perspectives of past, present, and future trends. Since the early 2000s, countries have gradually established national legal frameworks. Although all UAV regulations have one common goal—minimizing the risks to other airspace users and to both people and property on the ground—the results reveal distinct variations in all the compared variables. Furthermore, besides the clear presence of legal frameworks, market forces such as industry design standards and reliable information about UAVs as public goods are expected to shape future developments. [ABSTRACT FROM AUTHOR]

Multidimensional crisis phenomena (financial–economic, environmental and social), plaguing the international community, especially in the last 30 years, have intensified resentment towards traditional models of growth and socio-economic development. The European Commission has placed the idea of a green economy (GE) at the heart of the Europe 2020 strategy. This paper presents an assessment of the implementation of the green economy assumptions in EU countries in 2018, taking 2010 as the base year. Using taxonomic methods, a synthetic evaluation index (GEI—Green Economy Index) was constructed based on a multi-criterion set of 27 indicators. This paper attempts to answer the following questions: How green are the European economies? What are the main challenges in this context? The average value of the index for the EU countries decreased in the studied years from 0.3423 to 0.3294, which can be interpreted as a slowdown in the greening processes. The key recommendations for the upcoming years include the improvement of energy efficiency indicators, the further increase in the share of renewable energy sources in the energy balance. Moreover, a significant problem continues to be the high percentage of the population at risk of poverty or social exclusion, as well as low CO2 and resource productivity rates. [ABSTRACT FROM AUTHOR]

The rapid and non-destructive monitoring of the canopy leaf nitrogen concentration (LNC) in crops is important for precise nitrogen (N) management. Nowadays, there is an urgent need to identify next-generation bio-physical variable retrieval algorithms that can be incorporated into an operational processing chain for hyperspectral satellite missions. We assessed six retrieval algorithms for estimating LNC from canopy reflectance of winter wheat in eight field experiments. These experiments represented variations in the N application rates, planting densities, ecological sites and cultivars and yielded a total of 821 samples from various places in Jiangsu, China over nine consecutive years. Based on the reflectance spectra and their first derivatives, six methods using different numbers of wavelengths were applied to construct predictive models for estimating wheat LNC, including continuum removal (CR), vegetation indices (VIs), stepwise multiple linear regression (SMLR), partial least squares regression (PLSR), artificial neural networks (ANNs), and support vector machines (SVMs). To assess the performance of these six methods, we provided a systematic evaluation of the estimation accuracies using the six metrics that were the coefficients of determination for the calibration (R2 C) and validation (R2V) sets, the root mean square errors of prediction (RMSEP) for the calibration and validation sets, the ratio of prediction to deviation (RPD), the computational efficiency (CE) and the complexity level (CL). The following results were obtained: (1) For the VIs method, SAVI(R1200, R705) produced a more accurate estimation of the LNC than other indices, with R2C, R2V, RMSEP, RPD and CE values of 0.844, 0.795, 0.384, 2.005 and 0.10 min, respectively; (2) For the SMLR, PLSR, ANNs and SVMs methods, the SVMs using the first derivative canopy spectra (SVM-FDS) offered the best accuracy in terms of R2C, R2V, RMSEP, RPD, and CE, at 0.96, 0.78, 0.37, 2.02, and 21.17, respectively; (3) The PLSR-FDS, ANN-OS and SVM-FDS methods yield similar accuracies if the CE and CL are not considered, however, ANNs and SVMs performed better on calibration set than the validation set which indicate that we should take more caution with the two methods for over-fitting. Except PLS method, the performance for most methods did not enhance when the spectrum were operated by the first derivative. Moreover, the evaluation of the robustness demonstrates that SVM method may be better suited than the other methods to cope with potential confounding factors for most varieties, ecological site and growth stage; (4) The prediction accuracy was found to be higher when more wavelengths were used, though at the cost of a lower CE. The findings are of interest to the remote sensing community for the development of improved inversion schemes for hyperspectral applications concerning other types of vegetation. The examples provided in this paper may also serve to illustrate the advantages and shortcomings of empirical hyperspectral models for mapping important vegetation biophysical properties of other crops. [ABSTRACT FROM AUTHOR]

This paper discusses the issue of analyzing the development of cross-border tourism infrastructure in the borderlands of countries with diversified administrative divisions and spatial databases, which hinders the use of national statistical units for comparative research. As an example, the ability to use the square grid and kernel density estimation methods for the analysis and spatial visualization of the level of tourism infrastructure development is studied for the Orlickie and Bystrzyckie Mountains, located in the Polish–Czech border area. To synthetically assess and compare the level of diversity, the methodology used in the Human Development Index was adapted using selected component indicators calculated for a square grid clipped to the boundaries of the area under study. This analysis enabled us to quantify the asymmetry in the development of tourism infrastructure in the borderlands via the calculation of the synthetic infrastructure development index. This index is 1.29 times higher in the Czech than in the Polish border area. However, the spatial concentration analysis of infrastructure shows that the diversity in the study area can be assessed as higher than the results using the average density indicators. This paper also discusses the benefits and problems associated with using the square grid method for the representation and analysis of heterogeneous data on tourism infrastructure in two neighboring national states. [ABSTRACT FROM AUTHOR]

Decision support systems (DSS) are currently developing rapidly and are increasingly used in various fields. More often, those systems are inseparable from information-based systems and computer systems. Therefore, from a methodical point of view, the algorithms implemented in the DSS play a critical role. In this aspect, multi-criteria decision support (MCDA) methods are widely used. As research progresses, many MCDA methods and algorithms for the objective identification of the significance of individual criteria of the MCDA models were developed. In this paper, an analysis of available objective methods for criteria weighting is presented. Additionally, the authors presented the implementation of the system that provides easy and accessible weight calculations for any decision matrix with the possibility of comparing results of different weighting methods. The results of weighting methods were compared using carefully selected similarity coefficients to emphasise the correlation of the resulting weights. The performed research shows that every method should provide distinctive weights considering input data, emphasising the importance of choosing the correct method for a given multi-criteria decision support model and DSS. [ABSTRACT FROM AUTHOR]

Adsorption refrigeration systems are promising, sustainable solutions for many cooling applications. The operating range and the performance of an adsorption cooling cycle are strongly dependent on the properties of adsorbents, adsorbates, and bed coatings. Therefore, further research and analysis may lead to improved performance of adsorption coolers. In this paper, studies on working pairs using natural refrigerants and the properties of adsorbent coatings were reviewed. The selected working pairs were then thermodynamically characterised and ranked in terms of refrigerant evaporation temperature values. This was found to be a key parameter affecting the applicability of a given adsorbent/adsorbate pair and the value of SCP (Specific Cooling Power), COP (Coefficient of Performance) parameters, which are now commonly used comparison criteria of adsorption chillers. In the analysis of the coating studies, the focus was on the effect of individual parameters on the performance of the cooling system and the effect of using coated beds compared to packed beds. It was found that a fundamental problem in comparing the performance of different cooling systems is the use of different operating conditions during the tests. Therefore, the analysis compares the performance of the systems along with the most important thermodynamic cycle parameters for the latest studies. [ABSTRACT FROM AUTHOR]

Electric machines with high torque density are needed in many applications, such as electric vehicles, electric robotics, electric ships, electric aircraft, etc. and they can avoid planetary gears thus reducing manufacturing costs. This paper presents a novel axial-radial flux permanent magnet (ARFPM) machine with high torque density. The proposed ARFPM machine integrates both axial-flux and radial-flux machine topologies in a compact space, which effectively improves the copper utilization of the machine. First, the radial rotor can balance the large axial forces on axial rotors and prevent them from deforming due to the forces. On the other hand, the machine adopts Halbach-array permanent magnets (PMs) on the rotors to suppress air-gap flux density harmonics. Also, the Halbach-array PMs can reduce the total attracted force on axial rotors. The operational principle of the ARFPM machine was investigated and analyzed. Then, 3D finite-element analysis (FEA) was conducted to show the merits of the ARFPM machine. Demonstration results with different parameters are compared to obtain an optimal structure. These indicated that the proposed ARFPM machine with Halbach-array PMs can achieve a more sinusoidal back electromotive force (EMF). In addition, a comparative analysis was conducted for the proposed ARFPM machine. The machine was compared with a conventional axial-flux permanent magnet (AFPM) machine and a radial-flux permanent magnet (RFPM) machine based on the same dimensions. This showed that the proposed ARFPM machine had the highest torque density and relatively small torque ripple. [ABSTRACT FROM AUTHOR]

In this paper, the historical power load data from the National Electricity Market (Australia) is used to analyze the characteristics and regulations of electricity (the average value of every eight hours). Then, considering the inverse of Euclidean distance as the weight, this paper proposes a novel short-term load forecasting model based on the weighted k-nearest neighbor algorithm to receive higher satisfied accuracy. In addition, the forecasting errors are compared with the back-propagation neural network model and the autoregressive moving average model. The comparison results demonstrate that the proposed forecasting model could reflect variation trend and has good fitting ability in short-term load forecasting. [ABSTRACT FROM AUTHOR]

This paper conducts a comparative analysis of deep models in biometrics using scalogram of electrocardiogram (ECG). A scalogram is the absolute value of the continuous wavelet transform coefficients of a signal. Since biometrics using ECG signals are sensitive to noise, studies have been conducted by transforming signals into a frequency domain that is efficient for analyzing noisy signals. By transforming the signal from the time domain to the frequency domain using the wavelet, the 1-D signal becomes a 2-D matrix, and it could be analyzed at multiresolution. However, this process makes signal analysis morphologically complex. This means that existing simple classifiers could perform poorly. We investigate the possibility of using the scalogram of ECG as input to deep convolutional neural networks of deep learning, which exhibit optimal performance for the classification of morphological imagery. When training data is small or hardware is insufficient for training, transfer learning can be used with pretrained deep models to reduce learning time, and classify it well enough. In this paper, AlexNet, GoogLeNet, and ResNet are considered as deep models of convolutional neural network. The experiments are performed on two databases for performance evaluation. Physikalisch-Technische Bundesanstalt (PTB)-ECG is a well-known database, while Chosun University (CU)-ECG is directly built for this study using the developed ECG sensor. The ResNet was 0.73%—0.27% higher than AlexNet or GoogLeNet on PTB-ECG—and the ResNet was 0.94%—0.12% higher than AlexNet or GoogLeNet on CU-ECG. [ABSTRACT FROM AUTHOR]

In this paper, the aggregate index of green performance of agriculture (Agri-Environmental Index (AEI)) was proposed and empirically verified. For this purpose, a taxonomic method was used, i.e., the linear ordering method, which allows for the construction of a synthetic metric for the assessment of performance. Based on 16 agri-environmental indicators from the Organization for Economic Cooperation and Development (OECD) and Eurostat database, green performance indexes were constructed for 20 European countries. The constructed indexes are based on the multi-line impact of agriculture on the environment, with a particular focus on energy issues. During the analyses, answers to the following research questions were sought: Is the AEI an appropriate tool for evaluating the green performance of agriculture? What is the overall situation in this matter in EU countries? Which areas in terms of the impact of agriculture on the environment require remedial actions? The results of surveys show that the level of green performance in countries is still low (an average of 0.3069). The article indicates the areas that require special attention in the context of continuation of greening processes in the agricultural sector. [ABSTRACT FROM AUTHOR]

The use of compensation networks increases the power transfer capability of inductive power transfer (IPT) systems in the battery charging process of electric vehicles (EVs). Among the proposed topologies, the Series-Series (SS) and the LCC networks are currently in widespread use in wireless battery chargers based on IPT systems. This paper focuses on the study of the behavior of both compensation topologies when they are detuned due to the tolerances of their components. To compare their performances, a Monte-Carlo analysis was carried out using Simulink and MATLAB. The tolerance values, assigned independently to each component, fall within a [ − 20 , 20] % range according to a normal distribution. Histograms and scatter plots were used for comparison purposes. The analysis reveals that the LCC network allows a tighter control over the currents that flow through the magnetic coupler coils. Moreover, it was found that the increments in those currents can be limited to some extent by selecting capacitors featuring low tolerance values in the LCC compensation. Nevertheless, the SS network remains an appropriate choice if size and cost are essential constraints in a given design. [ABSTRACT FROM AUTHOR]

A complex neutrosophic set is a useful model to handle indeterminate situations with a periodic nature. This is characterized by truth, indeterminacy, and falsity degrees which are the combination of real-valued amplitude terms and complex-valued phase terms. Hypergraphs are objects that enable us to dig out invisible connections between the underlying structures of complex systems such as those leading to sustainable development. In this paper, we apply the most fruitful concept of complex neutrosophic sets to theory of hypergraphs. We define complex neutrosophic hypergraphs and discuss their certain properties including lower truncation, upper truncation, and transition levels. Furthermore, we define T-related complex neutrosophic hypergraphs and properties of minimal transversals of complex neutrosophic hypergraphs. Finally, we represent the modeling of certain social networks with intersecting communities through the score functions and choice values of complex neutrosophic hypergraphs. We also give a brief comparison of our proposed model with other existing models. [ABSTRACT FROM AUTHOR]

Based on the mirror image method and superposition principle, an analytical model of seepage field for symmetrical underwater tunnels is proposed. The condition is assumed as two-dimensional steady water inflow into symmetrical and horizontal underwater tunnels in a fully saturated, homogeneous, isotropic, and semi-infinite aquifer. Analytical solutions of pore water distribution and water inflow into tunnels are obtained. Two different boundary conditions at the perimeter of symmetrical tunnels are considered, constant total hydraulic head and constant water pressure. Taking the subsea tunnels of Xiamen Xiang’an in China as an example, comparisons between analytical solutions and numerical solutions are analyzed in the case of zero water pressure at the perimeter of symmetrical tunnels. The results show that the analytical solutions for pore pressure distribution and water inflow match well with the numerical solutions and that the relative deviations are all in an acceptable range. The solutions derived from the analytical model in this paper can analyze the steady seepage field of symmetrical underwater tunnels accurately and reasonably. [ABSTRACT FROM AUTHOR]