Iskanje po katalogu digitalne knjižnice

Opis: Hyperspectral anomaly detection has attracted extensive interests for its wide use in military and civilian fields, and three main categories of detection methods have been developed successively over past few decades, including statistical model-based, representation-based, and deep-learning-based methods. Most of these algorithms are essentially trying to construct proper background profiles, which describe the characteristics of background and then identify the pixels that do not conform to the profiles as anomalies. Apparently, the crucial issue is how to build an accurate background profile; however, the background profiles constructed by existing methods are not accurate enough. In this article, a novel and universal background purification framework with extended morphological attribute profiles is proposed. It explores the spatial characteristic of image and removes suspect anomaly pixels from the image to obtain a purified background. Moreover, three detectors with this framework covering different categories are also developed. The experiments implemented on four real hyperspectral images demonstrate that the background purification framework is effective, universal, and suitable. Furthermore, compared with other popular algorithms, the detectors with the framework perform well in terms of accuracy and efficiency.
Ključne besede: detectors, anomaly detection, image reconstruction, hyperspectral imaging, training, optics, dictionaries, background purification, extended attribute profile, sparse representation, stacked autoencoder
Objavljeno v DKUM: 19.08.2024; Ogledov: 76; Prenosov: 7
Celotno besedilo (5,36 MB)
Gradivo ima več datotek! Več...

Ključne besede: woody vegetation landscape features, change detection, segmentation neural network, cyclic aerial photography, digital orthophoto
Objavljeno v DKUM: 23.05.2024; Ogledov: 171; Prenosov: 10
Celotno besedilo (6,12 MB)
Gradivo ima več datotek! Več...

Opis: One of the most important problems in complex networks is the location of nodes that are essential or play a main role in the network. Nodes with main local roles are the centers of real communities. Communities are sets of nodes of complex networks and are densely connected internally. Choosing the right nodes as seeds of the communities is crucial in determining real communities. We propose a new centrality measure named density-based entropy centrality for the local identification of the most important nodes. It measures the entropy of the sum of the sizes of the maximal cliques to which each node and its neighbor nodes belong. The proposed centrality is a local measure for explaining the local influence of each node, which provides an efficient way to locally identify the most important nodes and for community detection because communities are local structures. It can be computed independently for individual vertices, for large networks, and for not well-specified networks. The use of the proposed density-based entropy centrality for community seed selection and community detection outperforms other centrality measures.
Ključne besede: networks, undirected graphs, community detection, node centrality, label propagation
Objavljeno v DKUM: 06.02.2024; Ogledov: 333; Prenosov: 21
Celotno besedilo (707,65 KB)
Gradivo ima več datotek! Več...

Opis: This paper presents a solution to a limitation of wireless power transfer that arises when using two D-shaped transmitter and receiver coils. Double D, or DD, coils are well known to have a polar, directional magnetic field, which increases the misalignment tolerance in one of the directions. The misalignment tolerance is nonsymmetric, and it is significantly better in one of the directions, which can also be considered a shortcoming. An additional shortcoming of the DD coil is that it is dependent on the rotation around the z-axis, due to the directional magnetic field. This is not a problem when using classic planar spiral coils, which do not generate a directional magnetic field. Therefore, DD coils are not suitable for applications in which the z-axis orientation is not determined and fixed to specific angle and direction. This paper presents a unique design of a transmitter coil, based on a double DD coil. The transmitter coil consists of two DD coils which are perpendicular to each other. The proposed transmitter structure can excite the receiver DD coil in a way that the efficiency of the power transfer is the highest, regardless of the orientation. The proposed transmitter structure can, therefore, solve the problem with rotation of a single DD coil. The proposed system structure was tested on the small-scale experimental setup
Ključne besede: coil rotation, orientation detection, DD coils, IPT
Objavljeno v DKUM: 20.12.2023; Ogledov: 326; Prenosov: 19
Celotno besedilo (5,32 MB)
Gradivo ima več datotek! Več...

Opis: This paper assesses the fault-detection capabilities of modern deep-learning models. It highlights that a naive deep-learning approach optimized for accuracy is unsuitable for learning fault-detection models from time-series data. Consequently, out-of-the-box deep-learning strategies may yield impressive accuracy results but are ill-equipped for real-world applications. The paper introduces a methodology for estimating fault-detection delays when no oracle information on fault occurrence time is available. Moreover, the paper presents a straightforward approach to implicitly achieve the objective of minimizing fault-detection delays. This approach involves using pseudo-multi-objective deep optimization with data windowing, which enables the utilization of standard deep-learning methods for fault detection and expanding their applicability. However, it does introduce an additional hyperparameter that needs careful tuning. The paper employs the Tennessee Eastman Process dataset as a case study to demonstrate its findings. The results effectively highlight the limitations of standard loss functions and emphasize the importance of incorporating fault-detection delays in evaluating and reporting performance. In our study, the pseudo-multi-objective optimization could reach a fault-detection accuracy of 95% in just a fifth of the time it takes the best naive approach to do so.
Ključne besede: artificial neural networks, deep learning, fault detection, accuracy, multi-objective optimization
Objavljeno v DKUM: 30.11.2023; Ogledov: 356; Prenosov: 25
Celotno besedilo (478,93 KB)
Gradivo ima več datotek! Več...