arXiv subjects

Hang Fan

Publications and source records attributed to Hang Fan.

24 records · Page 2Linked to original sources

arXiv2025

Inductive-Associative Meta-learning Pipeline with Human Cognitive Patterns for Unseen Drug-Target Interaction Prediction

Significant differences in protein structures hinder the generalization of existing drug-target interaction (DTI) models, which often rely heavily on pre-learned binding principles or detailed annotations. In contrast, BioBridge designs an Inductive-Associative pipeline inspired by the workflow of scientists who base their accumulated expertise on drawing insights into novel drug-target pairs from weakly related references. BioBridge predicts novel drug-target interactions using limited sequence data, incorporating multi-level encoders with adversarial training to accumulate transferable binding principles. On these principles basis, BioBridge employs a dynamic prototype meta-learning framework to associate insights from weakly related annotations, enabling robust predictions for previously unseen drug-target pairs. Extensive experiments demonstrate that BioBridge surpasses existing models, especially for unseen proteins. Notably, when only homologous protein binding data is available, BioBridge proves effective for virtual screening of the epidermal growth factor receptor and adenosine receptor, underscoring its potential in drug discovery.

cs.LG↗

arXiv2025

Satellite Observations Guided Diffusion Model for Accurate Meteorological States at Arbitrary Resolution

Accurate acquisition of surface meteorological conditions at arbitrary locations holds significant importance for weather forecasting and climate simulation. Due to the fact that meteorological states derived from satellite observations are often provided in the form of low-resolution grid fields, the direct application of spatial interpolation to obtain meteorological states for specific locations often results in significant discrepancies when compared to actual observations. Existing downscaling methods for acquiring meteorological state information at higher resolutions commonly overlook the correlation with satellite observations. To bridge the gap, we propose Satellite-observations Guided Diffusion Model (SGD), a conditional diffusion model pre-trained on ERA5 reanalysis data with satellite observations (GridSat) as conditions, which is employed for sampling downscaled meteorological states through a zero-shot guided sampling strategy and patch-based methods. During the training process, we propose to fuse the information from GridSat satellite observations into ERA5 maps via the attention mechanism, enabling SGD to generate atmospheric states that align more accurately with actual conditions. In the sampling, we employed optimizable convolutional kernels to simulate the upscale process, thereby generating high-resolution ERA5 maps using low-resolution ERA5 maps as well as observations from weather stations as guidance. Moreover, our devised patch-based method promotes SGD to generate meteorological states at arbitrary resolutions. Experiments demonstrate SGD fulfills accurate meteorological states downscaling to 6.25km.

cs.LG↗

arXiv2023

Electric Vehicle Sales Forecasting Model Considering Green Premium: A Chinese Market-based Perspective

"Green Premiums" which means the difference in cost between emissions-emitting technology and zero-emissions or emissions-reducing technology is significant for those renewable energy technology to address the climate change challenge facing the world in this century. China's Electrical Vehicles (EVs) industry is the first to cross the green premium into the commercialization stage, prompting its market size to exceed that of the US and EU combined, making it the most inspiring case in global carbon reduction practices. This study, which is based on first-hand data from industry research and innovatively constructs a multi-factor green premium model for EVs based on Total Cost of Ownership (TCO) analysis, finds that EVs currently have a higher green premium than Internal Combustion Engine Vehicles (ICEVs) and is expected that short-range EVs will be the first to achieve parity in acquisition costs by 2025 and long-range EVs by 2030. Further, this paper constructs a generalized Bass diffusion model considering the green premium, selects the time series data of EVs diffusion in the Chinese market from 2010-2021, and uses a genetic algorithm to fit the parameters to predict the EVs market penetration in the next ten years under different scenarios. The model prediction results show that EVs are successful innovative diffusion products and the market penetration rate depends largely on their green premium. The Chinese EVs market may experience a slowdown or even a decline in growth in the short term, but will maintain high growth in the medium to long term, with annual sales expected to reach 10.77 million units by 2030 and a penetration rate of about 39%.

eess.SY↗

arXiv2023

Privacy Preserving Ultra-Short-term Wind Power Prediction Based on Secure Multi Party Computation

Mining the spatial and temporal correlation of wind farm output data is beneficial for enhancing the precision of ultra-short-term wind power prediction. However, if the wind farms are owned by separate entities, they may be reluctant to share their data directly due to privacy concerns as well as business management regulation policies. Although cryptographic approaches have been designed to protect privacy in the process of data sharing, it is still a challenging problem to encrypt the original data while extracting the nonlinear relationship among multiple wind farms in the machine learning process. This paper presents pwXGBoost, a technique based on the machine learning tree model and secure multi-party computation (SMPC) that can successfully extract complicated relationships while preserving data privacy. A maximum mean discrepancy (MMD) based scheme is proposed to effectively choose adjacent candidate wind farms to participate in the collaborative model training, therefore improving the accuracy and reducing the burden of data acquisition. The proposed method was evaluated on real world data collected from a cluster of wind farms in Inner Mongolia, China, demonstrating that it is capable of achieving considerable efficiency and performance improvements while preserving privacy

cs.CR↗

arXiv2021

Ab initio determination of ultrahigh thermal conductivity in ternary compounds

Discovering new materials with ultrahigh thermal conductivity has been a critical research frontier and driven by many important technological applications ranging from thermal management to energy science. Here we have rigorously investigated the fundamental lattice vibrational spectra in ternary compounds and determined the thermal conductivity using a predictive ab initio approach. Phonon transport in B-X-C (X = N, P, As) groups is systematically quantified with different crystal structures and high-order anharmonicity involving a four-phonon process. Our calculation found an ultrahigh room-temperature thermal conductivity through strong carbon-carbon bonding up to 2100 W/mK beyond most common materials and the recently discovered boron arsenide. This study provides fundamental insight into the atomistic design of thermal conductivity and opens up opportunities in new materials searching towards complicated compound structures. DOI: 10.1103/PhysRevB.103.L041203

cond-mat.mtrl-sci↗

arXiv2019

Scale- and Context-Aware Convolutional Non-intrusive Load Monitoring

Non-intrusive load monitoring addresses the challenging task of decomposing the aggregate signal of a household's electricity consumption into appliance-level data without installing dedicated meters. By detecting load malfunction and recommending energy reduction programs, cost-effective non-intrusive load monitoring provides intelligent demand-side management for utilities and end users. In this paper, we boost the accuracy of energy disaggregation with a novel neural network structure named scale- and context-aware network, which exploits multi-scale features and contextual information. Specifically, we develop a multi-branch architecture with multiple receptive field sizes and branch-wise gates that connect the branches in the sub-networks. We build a self-attention module to facilitate the integration of global context, and we incorporate an adversarial loss and on-state augmentation to further improve the model's performance. Extensive simulation results tested on open datasets corroborate the merits of the proposed approach, which significantly outperforms state-of-the-art methods.

eess.SP↗