Selective and Adaptive Incremental Transfer Learning with Multiple Datasets for Machine Fault Diagnosis

The visions of Industry 4.0 and 5.0 have reinforced the industrial environment.They have also made artificial intelligence incorporated as a major facilitator.Diagnosing machine faults has become a solid foundation for automatically recognizing machine failure,and thus timely maintenance can ensure safe operations.Transfer learning is a promising solution that can enhance the machine fault diagnosis model by borrowing pre-trained knowledge from the source model and applying it to the target model,which typically involves two datasets.In response to the availability of multiple datasets,this paper proposes using selective and adaptive incremental transfer learning(SA-ITL),which fuses three algorithms,namely,the hybrid selective algorithm,the transferability enhancement algorithm,and the incremental transfer learning algorithm.It is a selective algorithm that enables selecting and ordering appropriate datasets for transfer learning and selecting useful knowledge to avoid negative transfer.The algorithm also adaptively adjusts the portion of training data to balance the learning rate and training time.The proposed algorithm is evaluated and analyzed using ten benchmark datasets.Compared with other algorithms from existing works,SA-ITL improves the accuracy of all datasets.Ablation studies present the accuracy enhancements of the SA-ITL,including the hybrid selective algorithm(1.22%-3.82%),transferability enhancement algorithm(1.91%-4.15%),and incremental transfer learning algorithm(0.605%-2.68%).These also show the benefits of enhancing the target model with heterogeneous image datasets that widen the range of domain selection between source and target domains.

A Study on the Influence of Luminance L* in the L*a*b* Color Space during Color Segmentation

In this paper an evaluation of the influence of luminance L* at the L*a*b* color space during color segmentation is presented. A comparative study is made between the behavior of segmentation in color images using only the Euclidean metric of a* and b* and an adaptive color similarity function defined as a product of Gaussian functions in a modified HSI color space. For the evaluation synthetic images were particularly designed to accurately assess the performance of the color segmentation. The testing system can be used either to explore the behavior of a similarity function (or metric) in different color spaces or to explore different metrics (or similarity functions) in the same color space. From the results is obtained that the color parameters a* and b* are not independent of the luminance parameter L* as one might initially assume.

Tripartite Entanglement Measures of Generalized GHZ State in Uniform Acceleration

Using the single-mode approximation,we study entanglement measures including two independent quantities;i.e.,negativity and von Neumann entropy for a tripartite generalized Greenberger-Horne-Zeilinger(GHZ)state in noninertial frames.Based on the calculated negativity,we study the whole entanglement measures named as the algebraic average π3-tangle and geometric average Π3-tangle.We find that the difference between them is very small or disappears with the increase of the number of accelerated qubits.The entanglement properties are discussed from one accelerated observer and others remaining stationary to all three accelerated observers.The results show that there will always exist entanglement,even if acceleration r arrives to infinity.The degree of entanglement for all 1-1 tangles are alwa.ys equal to zero,but 1-2 tangles always decrease with the acceleration parameter r.We notice that the von Neumann entropy increases with the number of the accelerated observers and SκΙζΙ(κ,ζ∈(A,B,C)) first increases and then decreases with the acceleration parameter r.This implies that the subsystem ρκΙζΙ is first more disorder and then the disorder will be reduced as the acceleration parameter r increases.Moreover,it is found that the von Neumann entropies SABCI,SABICI and SAIBICI always decrease with the controllable angle θ,while the entropies of the bipartite subsystems S2-2non(two accelerated qubits),S2-1non(one accelerated qubit) and S2-0non(without accelerated qubit) first increase with the angle θ and then decrease with it.

Optical Fiber Torsion Sensor with Mechanically Induced Long Period Fiber Gratings in Rare-Earth Doped Fibers

In this work wavelength sensitivity in mechanically induced long period fiber gratings (MLPFG) is analyzed. This analysis is first carried out both in standard single-mode fiber SMF-28 and in Er-doped fibers. The mechanical analysis for both types of fibers under different torsion conditions is presented. In order to apply the torsion one of the fiber ends is fixed while torsion is applied on the other end. A MLPFG whose period is 503 μm is used to press the fiber after torsion is applied. This allows for micro curvatures to be formed on the fiber, which in turn generates a periodical index perturbation on it. Here, it was noted that the sensitive wavelength shift of the rejection bands is bigger for Er-doped fibers. For a torsion of 6 turns applied to 10 cm of doped fiber the wavelength peaks can be moved up to 25 nm, which is longer to what was detected on standard fibers. Therefore, by using Er-doped fibers to monitor torsion on structures will give more sensitive and accurate results than using standard fibers. These results can be employed for sensing applications, especially for small to medium size structures, which can be mechanical, civil or aeronautics.

Quasi-normal modes,emission rate,and shadow of charged AdS black holes with perfect fluid dark matter

In this study,we comprehensively investigated charged AdS black holes surrounded by a distinct form of dark matter.In particular,we focused on key elements including the Hawking temperature,quasi-normal modes(QNMs),emission rate,and shadow.We first calculated the Hawking temperature,thereby identifying critical values such as the critical radius and maximum temperature of the black hole,essential for determining its phase transition.Further analysis focused on the QNMs of charged AdS black holes immersed in perfect fluid dark matter(PFDM)within the massless scalar field paradigm.Employing the Wentzel-Kramers-Brillouin(WKB)method,we accurately derived the frequencies of these QNMs.Additionally,we conducted a meticulous assessment of how the intensity of the PFDM parameterαinfluences the partial absorption cross sections of the black hole,along with a detailed study of the frequency variation of the energy emission rate.The pivotal role of geodesics in understanding astrophysical black hole characteristics is highlighted.Specifically,we examined the influence of the dark matter parameter on photon evolution by computing the shadow radius of the black hole.Our findings distinctly demonstrate the significant impact of the PFDM parameterαon the boundaries of this shadow,providing crucial insights into its features and interactions.We also provide profound insights into the intricate dynamics between a charged AdS black hole,novel dark matter,and various physical phenomena,elucidating their interplay and contributing valuable knowledge to the understanding of these cosmic entities.

A graph-based representation of knowledge for managing land administration data from distributed agencies–A case study of Colombia

Multiple efforts have been performed worldwide around diverse aspects of land administra-tion.However,land administration data and systems’notorious heterogeneity remains a longstanding challenge to develop a harmonized vision.In this sense,the traditional Spatial Data Infrastructures adoption is not enough to overcome this challenge since data sources’heterogeneity implies needs related to harmonization interoperability,sharing,and integration in land administration development.This paper proposes a graph-based represen-tation of knowledge for integrating multiple and heterogeneous data sources(tables,shape-files,geodatabases,and WFS services)belonging to two Colombian agencies within a decentralized land administration scenario.These knowledge graphs are developed on an ontology-based knowledge representation using national and international standards for land administration.Our approach aims to prevent data isolation,enable cross-datasets integration,accomplish machine-processable data,and facilitate the reuse and exploitation of multi-jurisdictional datasets in a single approach.A real case study demonstrates the applicability of the land administration data cycle deployed.

BOOK REVIEW

Book review for‘Manual of Digital Earth’,edited by Huadong Guo,Michael F.Goodchild,and Alessandro Annoni,Singapore,Springer,2020,852 pages,ISBN 978-981-32-9914-6,https://doi.org/10.1007/978-981-32-9915-3 The concept of Digital Earth(DE),first coined in Al Gore’s book entitled‘Earth in the Balance’(Gore 1992),was initially envisioned as a multiresolution and three-dimensional representation of the planet that would make it possible to discover,visualize and make sense of large amounts of geo-referenced information on physical and social environments(Gore 1999).