检索结果-内蒙古大学图书馆

A machine learning-based study of multifactor susceptibility and risk control of induced seismicity in unconventional reservoirs

引用

Petroleum Science 2023年第4期20卷 2232-2243页

作者： Gang Hui Zhang-Xin Chen Hai Wang Zhao-Jie Song Shu-Hua Wang Hong-Liang Zhang Dong-Mei Zhang Fei Gu National Key Laboratory of Petroleum Resources and Engineering China University of PetroleumBeijing102249PR China Department of Chemical and Petroleum Engineering University of CalgaryCalgaryABT2N1N4Canada Eastern Institute for Advanced Study Ningbo315200ZhejiangPR China Computer Modeling Group Ltd.Calgary ABT2L2M1Canada CNOOC Research Institute Beijing100028PR China China University of Geoscience(Wuhan) Wuhan430074HubeiPR China Research Institute of Petroleum Exploration and Development Beijing10083PR China

A comprehensive dataset from 594 fracturing wells throughout the Duvernay Formation near Fox Creek, Alberta, is collected to quantify the influences of geological, geomechanical, and operational features on the distribution and magnitude of hydraulic fracturing-induced seismicity. An integrated machine learning-based investigation is conducted to systematically evaluate multiple factors that contribute to induced seismicity. Feature importance indicates that a distance to fault, a distance to basement, minimum principal stress, cumulative fluid injection, initial formation pressure, and the number of fracturing stages are among significant model predictors. Our seismicity prediction map matches the observed spatial seismicity, and the prediction model successfully guides the fracturing job size of a new well to reduce seismicity risks. This study can apply to mitigating potential seismicity risks in other seismicity-frequent regions.

关键词： Induced seismicity Hydraulic fracturing Seismicity susceptibility Risk control Machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Multi-View Clustering via View-Specific Representation and Global Graph

Deep Multi-View Clustering via View-Specific Representation ...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Jingyu Pu Chenhang Cui Yazhou Ren Zichen Wen Tianyi Wu Xiaorong Pu Lifang He School of Computer Science and Engineering University of Electronic Science and Technology of China School of Computer Science and Engineering Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Department of Computer Science and Engineering Lehigh University Bethlehem USA

ISBN: (数字)9798350359145

ISBN: (纸本)9798350359152

Multi-view clustering can improve clustering performance by leveraging the complementary information from multiview data and has garnered growing interest. Despite significant advancements has been established in this field, most existing methods primarily concentrate on learning the latent representation, neglecting the latent graph that typically reveals relationships between different instances. To address this limitation, this paper presents a new framework of Deep Multi-View Clustering via View-specific Representation and Global Graph (DVGMVC) to address the aforementioned issue. Our method leverages the latent graph of each view to enhance representation quality and incorporates a global graph that combines discriminative information to enhance the performance of deep embedded clustering. Specifically, we employ autoencoders to learn embedded features and construct latent graphs from each view. Subsequently, a weighted two-layer plain residual network refines the latent feature using topological information derived from the latent graphs. As various views adhere to the same foundational cluster structure across multiple views, DVGMVC merges the embedded features of all views to create a unified feature. By leveraging the Graph Convolutional Network (GCN) module, which exploits information from both the latent graphs and the global graph generated from the global feature, a unified embedded feature is generated to capture comprehensive topological information among samples. This unified embedded feature is then employed to generate pseudo labels in a self-supervised manner, guiding unified embedding learning and clustering. In a self-supervised manner, such pseudo-label information guides unified embedding learning and clustering. In-depth experiments on public datasets has proven the state-of-the-art clustering effectiveness of our proposed method.

关键词： Clustering methods Learning (artificial intelligence) Task analysis Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Autonomous Low Power Energy Management Bridge for Industry IoT Application 21

Autonomous Low Power Energy Management Bridge for Industry I...

引用

21st International Conference on Micro and Nanotechnology for Power Generation and Energy Conversion Applications, PowerMEMS 2022

作者： Yamamoto, Koki Utsumi, Shion Fujita, Takayuki Ebara Corporation Technologies R&D and Intellectual Property Division Japan University of Hyogo Department of Electrical Engineering and Computer Science Japan University of Hyogo Advanced Medical Engineering Research Institute Japan

ISBN: (纸本)9781665493062

This work reported the autonomous battery-less power management system for the IoT (Internet of Things) application that is based on thermoelectrical energy harvesting and power management IC (PMIC). In the proposed design for targeting IoT, the bridge part that transmits the signal from the local area network e.g., Wi-Fi or BLE (Bluetooth® low energy) to the long-range protocol is essential to optimization. It is focused on the collaboration with the LPWA (Low Power Wide Area) network and BLE protocol to realize them, the programmed system controls the power management system. Lastly, the design indicated the possibility to utilize the autonomous system in IoT applications as a monitoring system in the industry with TEG (Thermoelectric Generator) harvesting. Especially, the temperature difference of about 8.6 degrees Celsius could drive the IoT utility with charging time every 3 hours 40 minutes when hot-starting from capacitance energy that should be semi-permanently utilized are evaluated. The work described that it could be effectively utilized to expand the IoT applications as close to easily and at a low cost. © 2022 IEEE.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Muslim-Violence Bias Persists in Debiased GPT Models

arXiv

引用

arXiv 2023年

作者： Hemmatian, Babak Baltaji, Razan Varshney, Lav R. Beckman Institute for Advanced Science and Technology University of Illinois Urbana-Champaign United States Department of Electrical and Computer Engineering

Abid et al. (2021) showed a tendency in GPT-3 to generate mostly violent completions when prompted about Muslims, compared with other religions. Two pre-registered replication attempts found few violent completions and only a weak anti-Muslim bias in the more recent InstructGPT, fine-tuned to eliminate biased and toxic outputs. However, more pre-registered experiments showed that using common names associated with the religions in prompts increases several-fold the rate of violent completions, revealing a significant second-order anti-Muslim bias. ChatGPT showed a bias many times stronger regardless of prompt format, suggesting that the effects of debiasing were reduced with continued model development. Our content analysis revealed religion-specific themes containing offensive stereotypes across all experiments. Our results show the need for continual de-biasing of models in ways that address both explicit and higher-order associations. © 2023, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Organic-Perovskite Bilayer Color Conversion Media for Full-Color Displays

Organic-Perovskite Bilayer Color Conversion Media for Full-C...

引用

International Conference on Display Technology, 2024

作者： Liu, Siyang Ting Tam, Bryan Siu Zhu, Mingchao Ye, Fanghao Yan Yeung, Fion Sze Li, Guijun Dong, Shou-Cheng State Key Laboratory of Advanced Displays and Optoelectronics Technologies Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Kowloon Hong Kong Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province Shenzhen University Shenzhen China Institute for Advanced Study Hong Kong University of Science and Technology Kowloon Hong Kong Co. Ltd. Suzhou China

Color conversion media (CCM) are crucial for realizing cost-effective, high-resolution micro-LED and OLED displays. In this work, we developed green and red organic-perovskite bilayer CCM that combine the PLQY and color purity of perovskite quantum dots (PeQDs) and the strong blue absorption of perylene-based organic emitters. The bilayer with thickness of 300 nm showed over 99% blue absorption and PLQY of 77% and 61% for green and red CCM, respectively. © 2024 John Wiley and Sons Inc. All rights reserved.

关键词： Perovskite

来源：评论

学校读者我要写书评

暂无评论

Robust Beamfocusing Against Positioning Errors Over Sub-Terahertz LOS Channels

Robust Beamfocusing Against Positioning Errors Over Sub-Tera...

引用

Asilomar Conference on Signals, Systems & computers

作者： Sota Uchimura Koji Ishibashi Josep M. Jornet The Advanced Wireless and Communication Research Center (AWCC) The University of Electro-Communications Department of Electrical and Computer Engineering & Institute for the Wireless Internet of Things Northeastern University

ISBN: (数字)9798350354058

ISBN: (纸本)9798350354065

We consider a robust hybrid beamfocusing scheme against statistical and norm-bounded positioning errors to improve a total system data rates in sub-terahertz (THz) communications systems. In particular, an ergodic sum rate maximization problem is formulated, where the objective function consists of the expectation of spectral efficiencies over positioning errors. The expected values are approximated by Jensen's inequality and Taylor approximation, which enable a joint transmit and receive beamfocusing design by deterministic convex optimization approaches. Numerical results confirm that the proposed robust approach achieves higher data rates than conventional non-robust approaches and a singular value decomposition (SVD) beamfocusing with perfect positioning information.

关键词： computers Closed-form solutions Spectral efficiency Linear programming Convex functions Optimization Terahertz communications Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Outage-Minimization Power and Spectrum Allocation for Terahertz Communications Systems

Outage-Minimization Power and Spectrum Allocation for Terahe...

引用

Asilomar Conference on Signals, Systems & computers

作者： Sota Uchimura Koji Ishibashi Josep Miquel Jornet The Advanced Wireless and Communication Research Center (AWCC) The University of Electro-Communications Department of Electrical and Computer Engineering Institute for the Wireless Internet of Things Northeastern University

ISBN: (数字)9798350354058

ISBN: (纸本)9798350354065

We propose joint transmit power and spectrum allocation schemes for terahertz (THz) communication systems with multi-connectivity technologies to overcome random path blockage effects and molecular absorption losses. The proposed approaches focus on quality of service (QoS) guarantees for instantaneous throughput fluctuated by the blockage dynamics and enhancement of the average total system throughput over time. To this end, a sum-of-outage-probability minimization problem and a geometric mean maximization problem for the throughput are formulated for the former and latter concepts, respectively. Moreover, a regularized sum-of-outage-probability minimization problem in which a regularizer suppresses throughput losses is formulated to deal with both the QoS requirement and the throughput enhancement. Stochastic learning and convex optimization mechanism are introduced to solve those problem. Numerical results confirm that the proposed approaches show the better tradeoff between the outage probability and the total system throughput than the conventional approaches.

关键词： Fluctuations Absorption Quality of service Probability Throughput Minimization Propagation losses Power system reliability Resource management Terahertz communications

来源：评论

学校读者我要写书评

暂无评论

Securing Smart Grids: Deep Reinforcement Learning Approach for Detecting Cyber-Attacks

Securing Smart Grids: Deep Reinforcement Learning Approach f...

引用

International Conference on Smart Communications and Networking (SmartNets)

作者： Ahmed T. El-Toukhy Islam Elgarhy Mahmoud M. Badr Mohamed Mahmoud Mostafa M. Fouda Mohamed I. Ibrahem Fathi Amsaad Department of Electrical and Computer Engineering Tennessee Tech. University Cookeville TN USA Department of Electrical Engineering Faculty of Engineering Al-Azhar University Cairo Egypt Department of Computer Systems Faculty of Computer and Information Sciences Ain Shams University Egypt Department of Network and Computer Security: Cybersecurity SUNY Polytechnic Institute Utica NY USA Department of Electrical Engineering Faculty of Engineering at Shoubra Benha University Cairo Egypt Department of Electrical and Computer Engineering Idaho State University Pocatello ID USA Center for Advanced Energy Studies (CAES) Idaho Falls ID USA School of Computer and Cyber Sciences Augusta University Augusta GA USA Department of Computer Science and Engineering Wright State University Dayton OH USA

ISBN: (数字)9798350385328

ISBN: (纸本)9798350385335

Smart meters (SMs) are deployed in smart power grids to monitor customer power consumption and facilitate energy management. However, fraudulent customers can compromise these SMs to manipulate power readings and engage in electricity theft cyber-attacks, resulting in reduced electricity bills. While various machine learning approaches have been employed for detecting such attacks, the potential of reinforcement learning (RL) remains unexplored. To bridge this gap, we propose a deep reinforcement learning (DRL) approach that leverages RL's adapt-ability to dynamic cyber-attacks and consumption patterns. This approach integrates exploration and exploitation mechanisms, enabling optimal decision-making. In this study, we present our approach in two scenarios. Firstly, we develop comprehensive detection models using deep Q networks (DQN) and double deep Q networks (DDQN) with various deep neural network architectures. Secondly, we address the challenges of defending against newly launched cyber-attacks. Extensive experimentation provides strong evidence of the effectiveness of our DRL approach in improving the detection of electricity theft cyber-attacks, as well as its capacity to efficiently adapt and defend against newly launched cyber-attacks.

关键词： Adaptation models Power demand Electricity Power system dynamics Detectors Deep reinforcement learning Smart meters

来源：评论

学校读者我要写书评

暂无评论

Scattering exceptional point in the visible

引用

Light(Science & Applications) 2023年第10期12卷 2228-2235页

作者： Tao He Zhanyi Zhang Jingyuan Zhu Yuzhi Shi Zhipeng Li Heng Wei Zeyong Wei Yong Li Zhanshan Wang Cheng-Wei Qiu Xinbin Cheng MOE Key Laboratory of Advanced Micro-Structured Materials Shanghai 200092China Institute of Precision Optical Engineering School of Physics Science and EngineeringTongji UniversityShanghai 200092China Shanghai Institute of Intelligent Science and Technology Tongji UniversityShanghai 200092China Shanghai Frontiers Science Center of Digital Optics Shanghai 200092China Shanghai Professional Technical Service Platform for Full-Spectrum and High-Performance Optical Thin Film Devices and Applications Shanghai 200092China Department of Electronic Science and Technology Tongji UniversityShanghai 201804China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore Institute of Acoustics School of Physics Science and EngineeringTongji UniversityShanghai 200092China

Exceptional point (EP) is a special degeneracy of non-Hermitian systems. One-dimensional transmission systems operating at EPs are widely studied and applied to chiral conversion and sensing. Lately, two-dimensional systems at EPs have been exploited for their exotic scattering features, yet so far been limited to only the non-visible waveband. Here, we report a universal paradigm for achieving a high-efficiency EP in the visible by leveraging interlayer loss to accurately control the interplay between the lossy structure and scattering lightwaves. A bilayer framework is demonstrated to reflect back the incident light from the left side ( | r_(−1) | >0.999) and absorb the incident light from the right side ( | r_(+1) | < 10^(–4)). As a proof of concept, a bilayer metasurface is demonstrated to reflect and absorb the incident light with experimental efficiencies of 88% and 85%, respectively, at 532 nm. Our results open the way for a new class of nanoscale devices and power up new opportunities for EP physics.

关键词： visible exceptional incident

来源：评论

学校读者我要写书评

暂无评论

Do We Run Large-scale Multi-Robot Systems on the Edge? More Evidence for Two-Phase Performance in System Size Scaling

Do We Run Large-scale Multi-Robot Systems on the Edge? More ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jonas Kuckling Robin Luckey Viktor Avrutin Andrew Vardy Andreagiovanni Reina Heiko Hamann Department of Computer and Information Science University of Konstanz Konstanz Germany Centre for the Advanced Study of Collective Behaviour University of Konstanz Germany Institute of Computer Engineering University of Lübeck Lübeck Germany Institute for Systems Theory and Automatic Control University of Stuttgart Stuttgart Germany Department of Computer Science and the Department of Electrical and Computer Engineering Memorial University of Newfoundland St. John’s Canada IRIDIA Université Libre de Bruxelles Brussels Belgium

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

With increasing numbers of mobile robots arriving in real-world applications, more robots coexist in the same space, interact, and possibly collaborate. Methods to provide such systems with system size scalability are known, for example, from swarm robotics. Example strategies are self-organizing behavior, a strict decentralized approach, and limiting the robot-robot communication. Despite applying such strategies, any multi-robot system breaks above a certain critical system size (i.e., number of robots) as too many robots share a resource (e.g., space, communication channel). We provide additional evidence based on simulations, that at these critical system sizes, the system performance separates into two phases: nearly optimal and minimal performance. We speculate that in real-world applications that are configured for optimal system size, the supposedly high-performing system may actually live on borrowed time as it is on a transient to breakdown. We provide two modeling options (based on queueing theory and a population model) that may help to support this reasoning.

关键词： Limiting System performance Space communications Scalability Sociology Swarm robotics Mobile robots

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：