Searcharxiv⌕ Search

arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 1,153 records · Page 64Linked to original sources
arXiv2023

Collaborative Three-Stream Transformers for Video Captioning

As the most critical components in a sentence, subject, predicate and object require special attention in the video captioning task. To implement this idea, we design a novel framework, named COllaborative three-Stream Transformers (COST), to model the three parts separately and complement each other for better representation. Specifically, COST is formed by three branches of transformers to exploit the visual-linguistic interactions of different granularities in spatial-temporal domain between videos and text, detected objects and text, and actions and text. Meanwhile, we propose a cross-granularity attention module to align the interactions modeled by the three branches of transformers, then the three branches of transformers can support each other to exploit the most discriminative semantic information of different granularities for accurate predictions of captions. The whole model is trained in an end-to-end fashion. Extensive experiments conducted on three large-scale challenging datasets, i.e., YouCookII, ActivityNet Captions and MSVD, demonstrate that the proposed method performs favorably against the state-of-the-art methods.

cs.CV↗
arXiv2023

FedALA: Adaptive Local Aggregation for Personalized Federated Learning

A key challenge in federated learning (FL) is the statistical heterogeneity that impairs the generalization of the global model on each client. To address this, we propose a method Federated learning with Adaptive Local Aggregation (FedALA) by capturing the desired information in the global model for client models in personalized FL. The key component of FedALA is an Adaptive Local Aggregation (ALA) module, which can adaptively aggregate the downloaded global model and local model towards the local objective on each client to initialize the local model before training in each iteration. To evaluate the effectiveness of FedALA, we conduct extensive experiments with five benchmark datasets in computer vision and natural language processing domains. FedALA outperforms eleven state-of-the-art baselines by up to 3.27% in test accuracy. Furthermore, we also apply ALA module to other federated learning methods and achieve up to 24.19% improvement in test accuracy.

cs.LG↗
arXiv2023

Energy Efficient Foot-Shape Design for Bipedal Walkers on Granular Terrain

It is important to understand how bipedal walkers balance and walk effectively on granular materials, such as sand and loose dirt, etc. This paper first presents a computational approach to obtain the motion and energy analysis of bipedal walkers on granular terrains and then discusses an optimization method for the robot foot-shape contour design for energy efficiently walking. We first present the foot-terrain interaction characteristics of the intrusion process using the resistive force theory that provides comprehensive force laws. Using human gait profiles, we compute and compare the ground reaction forces and the external work for walking gaits with various foot shapes on granular terrains. A multi-objective optimization problem is finally formulated for the foot contour design considering energy saving and walking efficiency. It is interesting to find out a non-convex foot shape gives the best performance in term of energy and locomotion efficiency on hard granular terrains. The presented work provides an enabling tool to further understand and design efficient and effective bipedal walkers on granular terrains.

cs.RO↗
arXiv2023

Polyimides Crosslinked by Aromatic Molecules and Nanocomposites for High Temperature Capacitive Energy Storage

High temperature polymer-based dielectric capacitors are crucial for application in electronic power systems. However, the storage performance of conventional dielectrics polymer dramatically deteriorates due to the thermal breakdown under concurrent high temperatures and electric fields, and there are hardly reports on the causes of thermal breakdown from the aspects of the high temperature conduction loss and Joule heat dissipation. Herein, a combined strategy of crosslinking and compositing for polyimide-based nanocomposites is proposed, which minimizes the thermal breakdown by significantly inhibiting the high-temperature conduction loss and enhancing the high thermal conductivity. Furthermore, the rationale of the strategy was theoretically and experimentally verified from multiple perspectives. The charge-trapping effect is directly observed and quantitatively probed by Kelvin probe force microscopy with nano level resolution, indicating that the crosslinking network introduces local deep traps and effectively suppresses the charge transport. The thermal conductivity of the nanocomposites inhibits the high temperature thermal breakdown, which is confirmed by phase field simulations. Consequently, the optimized nanocomposites possess an ultra high discharge energy density(Ud) of 5.45 J/cm3 and 3.54 J/cm3 with a charge discharge efficiency, respectively, which outperforms the reported polyimide based dielectric nanocomposites. This work provides a scalable direction for high temperature polymer based capacitors with excellent performance.

physics.app-ph↗
arXiv2023

Community Battery Energy Storage Systems for Enhancing Distribution System Operation: A Multi-objective Optimization Approach

The growing penetration of distributed energy resources (DERs) in distribution networks (DNs) raises new operational challenges, particularly in terms of reliability and voltage regulation. In response to these challenges, we introduce an innovative DN operation framework with multi-objective optimization, leveraging community battery energy storage systems (C-BESS). The proposed framework targets two key operational objectives: first, to minimize voltage deviation, which is a concern for a distribution network service provider (DNSP), and second, to maximize the utilization of DERs on the demand side. Recognizing the conflicting nature of these objectives, we utilize C-BESS to enhance the system's adaptability to dynamically adjust DN operations. The multi-objective optimization problem is solved using the non-dominated sorting genetic algorithm-II (NSGA-II). Case studies using real-world data are conducted to validate the effectiveness of the proposed framework. The results show significant improvements in voltage regulation and DER utilization, demonstrating the potential of C-BESS in enabling more reliable DN operation. Our findings contribute to the ongoing discourse on the role of C-BESS in DN operation enhancement and DER integration.

cs.NI↗
arXiv2023

Deep Reinforcement Learning for Wind and Energy Storage Coordination in Wholesale Energy and Ancillary Service Markets

Wind energy has been increasingly adopted to mitigate climate change. However, the variability of wind energy causes wind curtailment, resulting in considerable economic losses for wind farm owners. Wind curtailment can be reduced using battery energy storage systems (BESS) as onsite backup sources. Yet, this auxiliary role may significantly weaken the economic potential of BESS in energy trading. Ideal BESS scheduling should balance onsite wind curtailment reduction and market bidding, but practical implementation is challenging due to coordination complexity and the stochastic nature of energy prices and wind generation. We investigate the joint-market bidding strategy of a co-located wind-battery system in the spot and Regulation Frequency Control Ancillary Service markets. We propose a novel deep reinforcement learning-based approach that decouples the system's market participation into two related Markov decision processes for each facility, enabling the BESS to absorb onsite wind curtailment while performing joint-market bidding to maximize overall operational revenues. Using realistic wind farm data, we validated the coordinated bidding strategy, with outcomes surpassing the optimization-based benchmark in terms of higher revenue by approximately 25\% and more wind curtailment reduction by 2.3 times. Our results show that joint-market bidding can significantly improve the financial performance of wind-battery systems compared to participating in each market separately. Simulations also show that using curtailed wind generation as a power source for charging the BESS can lead to additional financial gains. The successful implementation of our algorithm would encourage co-location of generation and storage assets to unlock wider system benefits.

eess.SY↗
arXiv2023

Asymmetric metasurface photodetectors for single-shot quantitative phase imaging

The visualization of pure phase objects by wavefront sensing has important applications ranging from surface profiling to biomedical microscopy, and generally requires bulky and complicated setups involving optical spatial filtering, interferometry, or structured illumination. Here we introduce a new type of image sensors that are uniquely sensitive to the local direction of light propagation, based on standard photodetectors coated with a specially designed plasmonic metasurface that creates an asymmetric dependence of responsivity on angle of incidence around the surface normal. The metasurface design, fabrication, and angle-sensitive operation are demonstrated using a simple photoconductive detector platform. The measurement results, combined with computational imaging calculations, are then used to show that a standard camera or microscope based on these metasurface pixels can directly visualize phase objects without any additional optical elements, with state-of-the-art minimum detectable phase contrasts below 10 mrad. Furthermore, the combination of sensors with equal and opposite angular response on the same pixel array can be used to perform quantitative phase imaging in a single shot, with a customized reconstruction algorithm which is also developed in this work. By virtue of its system miniaturization and measurement simplicity, the phase imaging approach enabled by these devices is particularly significant for applications involving space-constrained and portable setups (such as point-of-care imaging and endoscopy) and measurements involving freely moving objects.

physics.optics↗
arXiv2023

3D Printed Multilayer Structures for High Numerical Aperture Achromatic Metalenses

Flat optics consisting of nanostructures of high-refractive-index materials produce lenses with thin form factors that tend to operate only at specific wavelengths. Recent attempts to achieve achromatic lenses uncover a trade-off between the numerical aperture (NA) and bandwidth, which limits performance. Here we propose a new approach to design high NA, broadband and polarization-insensitive multilayer achromatic metalenses (MAM). We combine topology optimization and full wave simulations to inversely design MAMs and fabricate the structures in low-refractive-index materials by two-photon polymerization lithography. MAMs measuring 20 micrometer in diameter operating in the visible range of 400-800 nm with 0.5 NA and 0.7 NA were achieved with efficiencies of up to 42%. We demonstrate broadband imaging performance of the fabricated MAM under white light, and RGB narrowband illuminations. These results highlight the potential of the 3D printed multilayer structures for realizing broadband and multi-functional meta-devices with inverse design.

physics.optics↗
arXiv2023

MARL for Decentralized Electric Vehicle Charging Coordination with V2V Energy Exchange

Effective energy management of electric vehicle (EV) charging stations is critical to supporting the transport sector's sustainable energy transition. This paper addresses the EV charging coordination by considering vehicle-to-vehicle (V2V) energy exchange as the flexibility to harness in EV charging stations. Moreover, this paper takes into account EV user experiences, such as charging satisfaction and fairness. We propose a Multi-Agent Reinforcement Learning (MARL) approach to coordinate EV charging with V2V energy exchange while considering uncertainties in the EV arrival time, energy price, and solar energy generation. The exploration capability of MARL is enhanced by introducing parameter noise into MARL's neural network models. Experimental results demonstrate the superior performance and scalability of our proposed method compared to traditional optimization baselines. The decentralized execution of the algorithm enables it to effectively deal with partial system faults in the charging station.

eess.SY↗
arXiv2023

Hybrid Transformer-RNN Architecture for Household Occupancy Detection Using Low-Resolution Smart Meter Data

Residential occupancy detection has become an enabling technology in today's urbanized world for various smart home applications, such as building automation, energy management, and improved security and comfort. Digitalization of the energy system provides smart meter data that can be used for occupancy detection in a non-intrusive manner without causing concerns regarding privacy and data security. In particular, deep learning techniques make it possible to infer occupancy from low-resolution smart meter data, such that the need for accurate occupancy detection with privacy preservation can be achieved. Our work is thus motivated to develop a privacy-aware and effective model for residential occupancy detection in contemporary living environments. Our model aims to leverage the advantages of both recurrent neural networks (RNNs), which are adept at capturing local temporal dependencies, and transformers, which are effective at handling global temporal dependencies. Our designed hybrid transformer-RNN model detects residential occupancy using hourly smart meter data, achieving an accuracy of nearly 92\% across households with diverse profiles. We validate the effectiveness of our method using a publicly accessible dataset and demonstrate its performance by comparing it with state-of-the-art models, including attention-based occupancy detection methods.

cs.LG↗
arXiv2023

Cross-Entropy-Based Approach to Multi-Objective Electric Vehicle Charging Infrastructure Planning

Pure electric vehicles (PEVs) are increasingly adopted to decarbonize the transport sector and mitigate global warming. However, the inadequate PEV charging infrastructure may hinder the further adoption of PEVs in the large-scale traffic network, which calls for effective planning solutions for the charging station (CS) placement. The deployment of charging infrastructure inevitably increases the load on the associated power distribution network. Therefore, we are motivated to develop a comprehensive multi-objective framework for optimal CS placement in a traffic network overlaid by a distribution network, considering multiple stakeholders' interested factors, such as traffic flow, PEV charging time cost, PEV travel distance, and the reliability of the distribution network. We leverage a cross-entropy-based method to solve the optimal CS placement and evaluate our method in a real-world 183-node traffic network in Chengdu, China, overlaid by a 26-region distribution network. It is demonstrated that our work provides various viable planning options favoring different objectives for the stakeholders' decision-making in practice.

eess.SY↗
arXiv2023

Inter-Rater Uncertainty Quantification in Medical Image Segmentation via Rater-Specific Bayesian Neural Networks

Automated medical image segmentation inherently involves a certain degree of uncertainty. One key factor contributing to this uncertainty is the ambiguity that can arise in determining the boundaries of a target region of interest, primarily due to variations in image appearance. On top of this, even among experts in the field, different opinions can emerge regarding the precise definition of specific anatomical structures. This work specifically addresses the modeling of segmentation uncertainty, known as inter-rater uncertainty. Its primary objective is to explore and analyze the variability in segmentation outcomes that can occur when multiple experts in medical imaging interpret and annotate the same images. We introduce a novel Bayesian neural network-based architecture to estimate inter-rater uncertainty in medical image segmentation. Our approach has three key advancements. Firstly, we introduce a one-encoder-multi-decoder architecture specifically tailored for uncertainty estimation, enabling us to capture the rater-specific representation of each expert involved. Secondly, we propose Bayesian modeling for the new architecture, allowing efficient capture of the inter-rater distribution, particularly in scenarios with limited annotations. Lastly, we enhance the rater-specific representation by integrating an attention module into each decoder. This module facilitates focused and refined segmentation results for each rater. We conduct extensive evaluations using synthetic and real-world datasets to validate our technical innovations rigorously. Our method surpasses existing baseline methods in five out of seven diverse tasks on the publicly available \emph{QUBIQ} dataset, considering two evaluation metrics encompassing different uncertainty aspects. Our codes, models, and the new dataset are available through our GitHub repository: https://github.com/HaoWang420/bOEMD-net .

eess.IV↗
arXiv2023

kTrans: Knowledge-Aware Transformer for Binary Code Embedding

Binary Code Embedding (BCE) has important applications in various reverse engineering tasks such as binary code similarity detection, type recovery, control-flow recovery and data-flow analysis. Recent studies have shown that the Transformer model can comprehend the semantics of binary code to support downstream tasks. However, existing models overlooked the prior knowledge of assembly language. In this paper, we propose a novel Transformer-based approach, namely kTrans, to generate knowledge-aware binary code embedding. By feeding explicit knowledge as additional inputs to the Transformer, and fusing implicit knowledge with a novel pre-training task, kTrans provides a new perspective to incorporating domain knowledge into a Transformer framework. We inspect the generated embeddings with outlier detection and visualization, and also apply kTrans to 3 downstream tasks: Binary Code Similarity Detection (BCSD), Function Type Recovery (FTR) and Indirect Call Recognition (ICR). Evaluation results show that kTrans can generate high-quality binary code embeddings, and outperforms state-of-the-art (SOTA) approaches on downstream tasks by 5.2%, 6.8%, and 12.6% respectively. kTrans is publicly available at: https://github.com/Learner0x5a/kTrans-release

cs.SE↗
arXiv2023

Optimal Bandwidth Selection for DENCLUE Algorithm

In modern day industry, clustering algorithms are daily routines of algorithm engineers. Although clustering algorithms experienced rapid growth before 2010. Innovation related to the research topic has stagnated after deep learning became the de facto industrial standard for machine learning applications. In 2007, a density-based clustering algorithm named DENCLUE was invented to solve clustering problem for nonlinear data structures. However, its parameter selection problem was largely neglected until 2011. In this paper, we propose a new approach to compute the optimal parameters for the DENCLUE algorithm, and discuss its performance in the experiment section.

cs.LG↗
arXiv2023

ChatHaruhi: Reviving Anime Character in Reality via Large Language Model

Role-playing chatbots built on large language models have drawn interest, but better techniques are needed to enable mimicking specific fictional characters. We propose an algorithm that controls language models via an improved prompt and memories of the character extracted from scripts. We construct ChatHaruhi, a dataset covering 32 Chinese / English TV / anime characters with over 54k simulated dialogues. Both automatic and human evaluations show our approach improves role-playing ability over baselines. Code and data are available at https://github.com/LC1332/Chat-Haruhi-Suzumiya .

cs.CL↗
arXiv2023

Promoting $p$-based Hall effects by $p$-$d$-$f$ hybridization in Gd-based dichalcogenides

We conduct a first-principles study of Hall effects in rare-earth dichalcogenides, focusing on monolayers of the H-phase EuX$_2$ and GdX$_2$, where X = S, Se, and Te. Our predictions reveal that all EuX$_2$ and GdX$_2$ systems exhibit high magnetic moments and wide bandgaps. We observe that while in case of EuX$_2$ the $p$ and $f$ states hybridize directly below the Fermi energy, the absence of $f$ and $d$ states of Gd at the Fermi energy results in $p$-like spin-polarized electronic structure of GdX$_2$, which mediates $p$-based magnetotransport. Notably, these systems display significant anomalous, spin, and orbital Hall conductivities. We find that in GdX$_2$ the strength of correlations controls the relative position of $p$, $d$ and $f$-states and their hybridization which has a crucial impact on $p$-state polarization and the anomalous Hall effect, but not the spin and orbital Hall effect. Moreover, we find that the application of strain can significantly modify the electronic structure of the monolayers, resulting in quantized charge, spin and orbital transport in GdTe$_2$ via a strain-mediated orbital inversion mechanism taking place at the Fermi energy. Our findings suggest that rare-earth dichalcogenides hold promise as a platform for topological spintronics and orbitronics.

cond-mat.mes-hall↗
arXiv2023

KMF: Knowledge-Aware Multi-Faceted Representation Learning for Zero-Shot Node Classification

Recently, Zero-Shot Node Classification (ZNC) has been an emerging and crucial task in graph data analysis. This task aims to predict nodes from unseen classes which are unobserved in the training process. Existing work mainly utilizes Graph Neural Networks (GNNs) to associate features' prototypes and labels' semantics thus enabling knowledge transfer from seen to unseen classes. However, the multi-faceted semantic orientation in the feature-semantic alignment has been neglected by previous work, i.e. the content of a node usually covers diverse topics that are relevant to the semantics of multiple labels. It's necessary to separate and judge the semantic factors that tremendously affect the cognitive ability to improve the generality of models. To this end, we propose a Knowledge-Aware Multi-Faceted framework (KMF) that enhances the richness of label semantics via the extracted KG (Knowledge Graph)-based topics. And then the content of each node is reconstructed to a topic-level representation that offers multi-faceted and fine-grained semantic relevancy to different labels. Due to the particularity of the graph's instance (i.e., node) representation, a novel geometric constraint is developed to alleviate the problem of prototype drift caused by node information aggregation. Finally, we conduct extensive experiments on several public graph datasets and design an application of zero-shot cross-domain recommendation. The quantitative results demonstrate both the effectiveness and generalization of KMF with the comparison of state-of-the-art baselines.

cs.LG↗