A5100773042- Machine Learning and ELM
- Domain Adaptation and Few-Shot Learning
- Data Management and Algorithms
- Advanced Database Systems and Queries
- Recommender Systems and Techniques
- Advanced Graph Neural Networks
- Face and Expression Recognition
- Caching and Content Delivery
- Reservoir Engineering and Simulation Methods
- Enhanced Oil Recovery Techniques
- Topic Modeling
- Hydraulic Fracturing and Reservoir Analysis
- Data Stream Mining Techniques
- Time Series Analysis and Forecasting
- Human Mobility and Location-Based Analysis
- EEG and Brain-Computer Interfaces
- Semantic Web and Ontologies
- Neural Networks and Applications
- Hydrocarbon exploration and reservoir analysis
- Advanced Computational Techniques and Applications
- Anomaly Detection Techniques and Applications
- Peer-to-Peer Network Technologies
- ECG Monitoring and Analysis
- Advanced Memory and Neural Computing
- Text and Document Classification Technologies
Abu Dhabi National Oil (United Arab Emirates)
2025
China National Petroleum Corporation (China)
2025
Northeastern University
2014-2024
Universidad del Noreste
2024
Production optimization is of significance for carbonate reservoirs, directly affecting the sustainability and profitability reservoir development. Traditional physics-based numerical simulations suffer from insufficient calculation accuracy excessive time consumption when performing production optimization. We establish an ensemble proxy-model-assisted framework combining Bayesian random forest (BRF) with particle swarm algorithm (PSO). The BRF method implemented to construct a proxy model...
Recently, maximum reservoir contacting (MRC) wells have attracted more and attention been gradually applied to CO2 WAG injections. During the use of MRC for injections, intelligent completions are commonly considered control breakthroughs. However, design operational completion parameters is a complicated process there no studies on co-optimization processes. This study outlines an approach enhance oil recovery from injection processes through in carbonate reservoir. First, simulation method...
Given a location-based social network, how to find the communities that are highly relevant query users and have top overall scores in multiple attributes according user preferences? Typically, face of such problem setting, we can model network as multi-attributed road-social which each is linked with location information d (≥1) numerical attributes. In practice, preferences (i.e., weights) usually inherently uncertain only be estimated bounded accuracy, because human not able designate...
Brain networks provide essential insights into the diagnosis of functional brain disorders, such as Alzheimer’s disease (AD). Many machine learning methods have been applied to learn from images or in Euclidean space. However, it is still challenging complex network structures and connectivity regions non-Euclidean To address this problem, paper, we exploit study classification perspective graph learning. We propose an aggregator based on extreme (ELM) that boosts aggregation ability...
Driven by the advance of positioning technology and tremendous popularity location-based services, location-record data have become unprecedentedly available. Publishing such is vital importance to advancement a wide spectrum applications, as marketing analysis, targeted advertising, urban planning. However, collection may pose considerable threats individuals privacy. Local differential privacy (LDP) has recently emerged strong standard for collecting sensitive information from users. Due...
Classification over data streams is a crucial task of explosive social stream mining and computing. Efficient learning techniques provide high-quality services in the aspect content distribution event browsing. Due to concept drift evolution streams, classification performance degrades drastically time. Many existing methods utilize supervised unsupervised strategies. However, strategies require labeled emerging records update classifiers, which unfeasible work practical applications....
Maintaining the dynamical microwave synchronization between a target and its background is key to electromagnetical invisibility in real environment. Herein, we introduce an archetypical paradigm for ultraelastic films of graphene-functionalized ionic gel with tunable microwave-absorbing behaviors. Inspired by local structural changes during wing-spreading process vespertilionids, experimental finite element simulations have revealed that proper shape changing 3D wrinkled structure...
Structural holes" is a conception proposed by sociologist Ronald Burt [1], which refer to the absence of ties between two parts network. in this paper, we develop and new called generalized structural communities social network an effective algorithm find them. We believe that holes play key role many aspects on networks, such as communication communities, diffusion innovation, information spreading. prove problem finding NP-complete, propose heuristic these holes. Experiments both synthetic...
The efficient development of oil reservoirs mainly depends on the comprehensive optimization subsurface fluid flow process. As an intelligent analysis technique, artificial intelligence provides a novel solution to multi-objective (MOO) problems. In this study, agent model based Transformer framework with assistance particle swarm (MOPSO) algorithm has been utilized optimize gas flooding injection–production parameters in well pattern Middle East. Firstly, 10 types surveillance data covering...