Performance Evaluation Indicator (PEI): A new paradigm to evaluate the competence of machine learning classifiers in predicting rockmass conditions

To illustrate an unprejudiced comparison among machine learning classifiers established on proprietary databases, and to guarantee the validity and robustness of these classifiers, a Performance Evaluation Indicator (PEI) and the corresponding failure criterion are proposed in this study. Three types of machine learning classifiers, including the strictly binary classifier, the normal multiclass classifier and the misclassification cost-sensitive classifier, are trained on four datasets recorded from a water drainage TBM project. The results indicate that: (1) the PEI successfully compares the competence of classifiers under different scenarios by isolating the effects of different overlapping-degree of rockmass classes, and (2) the cost-sensitive algorithm is warranted to classify rockmasses when the ratio of inter-class classes is more than 8:1. The contributions of this research are to fill the gap in performance evaluations of a classifier for imbalanced training data, and to identify the best situation to apply this classifier.     

Power-to-hydrogen and hydrogen-to-X energy systems for the industry of the future in Europe

The EU is promoting hydrogen as enabling energy carrier that may account for up to 20% of energy and especially fulfill between 20% and 50% of transportation demands and between 5% and 20% of industrial needs. To ensure the success of this shift, Power-to-Hydrogen and Hydrogen-to-X technologies have attracted significant interest because they transform renewable power directly into green hydrogen, via water electrolysis, which can be stored and transferred more readily than other fuels for several end-uses. The present paper aims to discuss the role of such technologies in the current and future energy systems, with a specific reference to the European scenario. The main energy sectors where hydrogen could play an important role will be discussed, such as transportation, power generation, manufacturing sectors, refining and agriculture, with a focus on potential technological integration and synergies, providing a guideline for industrial players up to 2050 with a discussion about technology maturity by presenting short-term/long-term roadmaps.     

A holistic approach for tightly coupled reconfigurable parallel processors

New standards in signal, multimedia, and network processing for embedded electronics are characterized by computationally intensive algorithms, high flexibility due to the swift change in specifications. In order to meet demanding challenges of increasing computational requirements and stringent constraints on area and power consumption in fields of embedded engineering, there is a gradual trend towards coarse-grained parallel embedded processors. Furthermore, such processors are enabled with dynamic reconfiguration features for supporting time- and space-multiplexed execution of the algorithms. However, the formidable problem in efficient mapping of applications (mostly loop algorithms) onto such architectures has been a hindrance in their mass acceptance. In this paper we present (a) a highly parameterizable, tightly coupled, and reconfigurable parallel processor architecture together with the corresponding power breakdown and reconfiguration time analysis of a case study application, (b) a retargetable methodology for mapping of loop algorithms, (c) a co-design framework for modeling, simulation, and programming of such architectures, and (d) loosely coupled communication with host processor.     

An in situ heating study of hydrogen-containing adsorbates on polycrystalline diamond surfaces using elastic recoil detection

Elastic recoil detection (ERD) was used to measure the concentration of hydrogen on as-deposited, heated, and air-exposed polycrystalline diamond films in order to relate the surface peak often observed in ERD spectra to the thermodynamic behavior of hydrogen on the surface of polycrystalline diamond. A surface peak corresponding to an enhanced hydrogen surface concentration was observed on all as-deposited samples. When each sample was heated in vacuum, the enhanced surface concentration decreased with increasing temperature and completely disappeared at 400°C, at which the surface concentration was equal to the bulk concentration. The surface and bulk concentrations remained the same for the duration of the heating process (129 h), however, the enhanced surface concentration reappeared when the heated samples were exposed to air, suggesting that the enhanced ERD peak is comprised primarily of weakly-bonded hydrogen-containing adsorbates such as water. By accounting for surface roughness of the samples and examining the temperature-dependent behavior of the surface peak, the thickness of the enhanced surface layer was determined to be in accordance with results reported by others using nuclear reaction analysis and much less than the thickness predicted by ERD simulation software.