Search

Tight sandstone reservoirs have extremely low porosity and permeability. Bedding-parallel fractures (BPFs) contribute prominently to the storage and seepage capability. However, the distribution of BPFs is remarkably heterogeneous, impeding the prediction and modeling of sweet spots. BPFs are controlled fundamentally by laminations, which are widely distributed in lacustrine tight reservoirs and provide most weakness planes. Based on core and thin section data, BPFs of the upper Triassic Chang 7 tight oil reservoir are characterized microscopically. The lamination combination unit, which is defined by distinctive lamination assemblage and relatively stable lamination thickness and space, is utilized as a homogeneous unit to measure the density of lamination and related BPFs. The influence of laminations on BPFs is discussed further. Results show that most bedding-parallel fractures are unfilled, with apertures generally <40 μιτι, mainly <10 μιτι. Larger apertures correlate with low filling degrees. The distribution of BPFs is intricately controlled by lamination type, density, and thickness. (1) BPFs tend to develop along different types by a priority sequence which reflects their mechanical strength. The development degree of BPFs also depends on the mechanical contrast with adjacent laminations; (2) When controlled by a single type of lamination, the density of BPFs increases with lamination density under a turning point and then decreases; (3) BPFs prefer to develop along the thinner lamination and are usually inside it, while controlled by thick lamination, BPFs tend to extend along the edge. The change in the thickness of laminations leads to a change in the development position of BPFs, indicating that the position of the weak plane controls the development position of BPFs; (4) When multiple types of lamination coexist, the type and thickness of laminations jointly influence the development of BPFs. Plastic thin laminations are conducive to the development of BPFs, while brittle thick laminations are not conducive. When the thickness of the plastic lamination is close to or less than that of the brittle, the influence of lamination type dominates BPFs, while the thickness of the plastic laminations is much larger than the brittle, the influence of lamination thickness will dominate. [ABSTRACT FROM AUTHOR]

One of the problems that are associated to power systems is islanding condition, which must be rapidly and properly detected to prevent any negative consequences on the system's protection, stability, and security. This paper offers a thorough overview of several islanding detection strategies, which are divided into two categories: classic approaches, including local and remote approaches, and modern techniques, including techniques based on signal processing and computational intelligence. Additionally, each approach is compared and assessed based on several factors, including implementation costs, non-detected zones, declining power quality, and response times using the analytical hierarchy process (AHP). The multi-criteria decision-making analysis shows that the overall weight of passive methods (24.7%), active methods (7.8%), hybrid methods (5.6%), remote methods (14.5%), signal processing-based methods (26.6%), and computational intelligent-based methods (20.8%) based on the comparison of all criteria together. Thus, it can be seen from the total weight that hybrid approaches are the least suitable to be chosen, while signal processing-based methods are the most appropriate islanding detection method to be selected and implemented in power system with respect to the aforementioned factors. Using Expert Choice software, the proposed hierarchy model is studied and examined. [ABSTRACT FROM AUTHOR]

Purpose: Automatic surgical phase recognition is crucial for video-based assessment systems in surgical education. Utilizing temporal information is crucial for surgical phase recognition; hence, various recent approaches extract frame-level features to conduct full video temporal modeling. Methods: For better temporal modeling, we propose SlowFast temporal modeling network (SF-TMN) for offline surgical phase recognition that can achieve not only frame-level full video temporal modeling but also segment-level full video temporal modeling. We employ a feature extraction network, pretrained on the target dataset, to extract features from video frames as the training data for SF-TMN. The Slow Path in SF-TMN utilizes all frame features for frame temporal modeling. The Fast Path in SF-TMN utilizes segment-level features summarized from frame features for segment temporal modeling. The proposed paradigm is flexible regarding the choice of temporal modeling networks. Results: We explore MS-TCN and ASFormer as temporal modeling networks and experiment with multiple combination strategies for Slow and Fast Paths. We evaluate SF-TMN on Cholec80 and Cataract-101 surgical phase recognition tasks and demonstrate that SF-TMN can achieve state-of-the-art results on all considered metrics. SF-TMN with ASFormer backbone outperforms the state-of-the-art Swin BiGRU by approximately 1% in accuracy and 1.5% in recall on Cholec80. We also evaluate SF-TMN on action segmentation datasets including 50salads, GTEA, and Breakfast, and achieve state-of-the-art results. Conclusion: The improvement in the results shows that combining temporal information from both frame level and segment level by refining outputs with temporal refinement stages is beneficial for the temporal modeling of surgical phases. [ABSTRACT FROM AUTHOR]

As e-learning platforms gain traction globally, understanding students' perceptions and intentions towards these platforms is paramount, especially within the context of Saudi universities, where e-learning is rapidly emerging as a transformative educational tool for sustainable development. This study examined the influence of different AI-based social learning networks, personal learning portfolios, and personal learning environments on Saudi university students' perceived usefulness and ease of use regarding AI-driven platforms (Blackboard, Moodle, Edmodo, Coursera and edX). Furthermore, the study explored the direct effects of these perceptions on students' satisfaction and intentions to use e-learning. The study also delved into the moderating effects of individual characteristics like readiness for self-directed e-learning, self-efficacy, and personal innovativeness on students' e-learning intentions. A cross-sectional design was employed, collecting self-reported data from a strong sample of Saudi university students using stratified random sampling. The study targeted 500 students from different universities in Saudi Arabia. Results underscored the significant influence of AI-based social learning networks, personal learning portfolios, and personal learning environments on perceived usefulness and ease of use. Both perceived usefulness and ease of use also significantly and positively influenced satisfaction, influencing students' attitudes toward e-learning but not their intention to use it. Student characteristics, especially self-efficacy, showed notable impacts on e-learning intentions. However, their interaction with satisfaction yielded insignificant effects on intentions. [ABSTRACT FROM AUTHOR]