Search

Event prediction aims to forecast the time and type of a future event based on a historical event sequence. Despite its significance, several challenges exist, including the irregularity of time intervals between consecutive events, the existence of cycles, periodicity, and multi-scale event interactions, as well as the high computational costs for long event sequences. Existing neural temporal point processes (TPPs) methods do not capture the multi-scale nature of event interactions, which is common in many real-world applications such as clinical event data. To address these issues, we propose the cross-temporal-scale transformer (XTSFormer), designed specifically for irregularly timed event data. Our model comprises two vital components: a novel Feature-based Cycle-aware Time Positional Encoding (FCPE) that adeptly captures the cyclical nature of time, and a hierarchical multi-scale temporal attention mechanism. These scales are determined by a bottom-up clustering algorithm. Extensive experiments on several real-world datasets show that our XTSFormer outperforms several baseline methods in prediction performance.

Fairness-awareness has emerged as an essential building block for the responsible use of artificial intelligence in real applications. In many cases, inequity in performance is due to the change in distribution over different regions. While techniques have been developed to improve the transferability of fairness, a solution to the problem is not always feasible with no samples from the new regions, which is a bottleneck for pure data-driven attempts. Fortunately, physics-based mechanistic models have been studied for many problems with major social impacts. We propose SimFair, a physics-guided fairness-aware learning framework, which bridges the data limitation by integrating physical-rule-based simulation and inverse modeling into the training design. Using temperature prediction as an example, we demonstrate the effectiveness of the proposed SimFair in fairness preservation., Comment: Accepted to AAAI 2024 (preprint)

Hsu et al. (2022) proposed a cryptographic scheme within the public key infrastructure to bolster the security of smart grid meters. Their proposal involved developing the Certificate Management over CMS mechanism to establish Simple Certificate Enrollment Protocol and Enrollment over Secure Transport protocol. Additionally, they implemented Online Certificate Status Protocol (OCSP) services to independently query the status of certificates. However, their implementation featured a single OCSP server handling all query requests. Considering the typical scenario in smart grid PKI environments with over tens of thousands of end-meters, we introduced a Hybrid Online Certificate Status Protocol mechanism. This approach decreases demand of query resources from the client to OCSP servers collaborating with Certificate Revocation Lists. Our simulations, mimicking meter behavior, demonstrated increased efficiency, creating a more robust architecture tailored to the smart grid meter landscape., Comment: 8 pages, 7 figures

The concept of Digital Twin (DT) is increasingly applied to systems on different levels of abstraction across domains, to support monitoring, analysis, diagnosis, decision making and automated control. Whilst the interest in applying DT is growing, the definition of DT is unclear, neither is there a clear pathway to develop DT to fully realise its capacities. In this paper, we revise the concept of DT and its categorisation. We propose a DT maturity matrix, based on which we propose a model-based DT development methodology. We also discuss how model-based tools can be used to support the methodology and present our own supporting tool. We report our preliminary findings with a discussion on a case study, in which we use our proposed methodology and our supporting tool to develop an extensible DT platform for the assurance of Electrical and Electronics systems of space launch vehicles.

The deployment of Large Language Models (LLMs) for code debugging (e.g., C and Python) is widespread, benefiting from their ability to understand and interpret intricate concepts. However, in the semiconductor industry, utilising LLMs to debug Register Transfer Level (RTL) code is still insufficient, largely due to the underrepresentation of RTL-specific data in training sets. This work introduces a novel framework, Make Each Iteration Count (MEIC), which contrasts with traditional one-shot LLM-based debugging methods that heavily rely on prompt engineering, model tuning, and model training. MEIC utilises LLMs in an iterative process to overcome the limitation of LLMs in RTL code debugging, which is suitable for identifying and correcting both syntax and function errors, while effectively managing the uncertainties inherent in LLM operations. To evaluate our framework, we provide an open-source dataset comprising 178 common RTL programming errors. The experimental results demonstrate that the proposed debugging framework achieves fix rate of 93% for syntax errors and 78% for function errors, with up to 48x speedup in debugging processes when compared with experienced engineers. The Repo. of dataset and code: https://anonymous.4open.science/r/Verilog-Auto-Debug-6E7F/.

Accurate and timely mapping of flood extent from high-resolution satellite imagery plays a crucial role in disaster management such as damage assessment and relief activities. However, current state-of-the-art solutions are based on U-Net, which can-not segment the flood pixels accurately due to the ambiguous pixels (e.g., tree canopies, clouds) that prevent a direct judgement from only the spectral features. Thanks to the digital elevation model (DEM) data readily available from sources such as United States Geological Survey (USGS), this work explores the use of an elevation map to improve flood extent mapping. We propose, EvaNet, an elevation-guided segmentation model based on the encoder-decoder architecture with two novel techniques: (1) a loss function encoding the physical law of gravity that if a location is flooded (resp. dry), then its adjacent locations with a lower (resp. higher) elevation must also be flooded (resp. dry); (2) a new (de)convolution operation that integrates the elevation map by a location sensitive gating mechanism to regulate how much spectral features flow through adjacent layers. Extensive experiments show that EvaNet significantly outperforms the U-Net baselines, and works as a perfect drop-in replacement for U-Net in existing solutions to flood extent mapping., Comment: Accepted at the International Joint Conference on Artificial Intelligence (IJCAI, 2024)

Conventional mixed-criticality systems (MCS)s are designed to terminate the execution of less critical tasks in exceptional situations so that the timing properties of more critical tasks can be preserved. Such a strategy can be controversial and has proven difficult to implement in practice, as it can lead to hazards and reduced functionality due to the absence of the discarded tasks. To mitigate this issue, the imprecise mixed-critically system model (IMCS) has been proposed. In such a model, instead of completely dropping less-critical tasks, these tasks are executed as much as possible through the use of decreased computation precision. Although IMCS could effectively improve the survivability of the less-critical tasks, it also introduces three key drawbacks - run-time computation errors, real-time performance degradation, and lack of flexibility. In this paper, we present a novel IMCS framework, which can (i) mitigate the computation errors caused by imprecise computation; (ii) achieve real-time performance near to that of a conventional MCS; (iii) enhance system-level throughput; and (iv) provide flexibility for run-time configuration. We describe the design details of HIART-MCS, and then present the corresponding theoretical analysis and optimisation method for its run-time configuration. Finally, HIART-MCS is evaluated against other MCS frameworks using a variety of experimental metrics.

All systems rely on inputs and outputs (I/Os) to perceive and interact with their surroundings. In safety-critical systems, it is important to guarantee both the performance and time-predictability of I/O operations. However, with the continued growth of architectural complexity in modern safety-critical systems, satisfying such real-time requirements has become increasingly challenging due to complex I/O transaction paths and extensive hardware contention. In this paper, we present a new NoC-based Predictable I/O system framework (NPRC-I/O) which reduces this contention and ensures the performance and timepredictability of I/O operations. Specifically, NPRC-I/O contains a programmable I/O command controller (NPRC-CC) and a runtime reconfigurable NoC (RNoC), which provides the capability to adjust I/O transaction paths at run-time. Using this flexibility, we construct an end-to-end transmission latency analysis and an optimisation engine that produces configurations for NPRCI/ O and the I/O traffic in a given system. The constructed analysis and optimisation engine guarantee the timing of all hard realtime traffic while reducing the deadline misses of soft real-time traffic and overall transmission latency.

Deep neural networks (DNNs) have achieved tremendous success in making accurate predictions for computer vision, natural language processing, as well as science and engineering domains. However, it is also well-recognized that DNNs sometimes make unexpected, incorrect, but overconfident predictions. This can cause serious consequences in high-stake applications, such as autonomous driving, medical diagnosis, and disaster response. Uncertainty quantification (UQ) aims to estimate the confidence of DNN predictions beyond prediction accuracy. In recent years, many UQ methods have been developed for DNNs. It is of great practical value to systematically categorize these UQ methods and compare their advantages and disadvantages. However, existing surveys mostly focus on categorizing UQ methodologies from a neural network architecture perspective or a Bayesian perspective and ignore the source of uncertainty that each methodology can incorporate, making it difficult to select an appropriate UQ method in practice. To fill the gap, this paper presents a systematic taxonomy of UQ methods for DNNs based on the types of uncertainty sources (data uncertainty versus model uncertainty). We summarize the advantages and disadvantages of methods in each category. We show how our taxonomy of UQ methodologies can potentially help guide the choice of UQ method in different machine learning problems (e.g., active learning, robustness, and reinforcement learning). We also identify current research gaps and propose several future research directions., Comment: 39 pages, 14 figures

Bitcoin-NG is an extensible blockchain protocol based on the same trust model as Bitcoin. It divides each epoch into one Key-Block and multiple Micro-Blocks, effectively improving transaction processing capacity. Bitcoin-NG adopts a special incentive mechanism (i.e., the transaction fees in each epoch are split to the current and next leader) to maintain its security. However, there are some limitations to the existing incentive analysis of Bitcoin-NG in recent works. First, the incentive division method of Bitcoin-NG only includes some specific mining attack strategies of adversary, while ignoring more stubborn attack strategies. Second, once adversaries find a whale transaction, they will deviate from honest mining strategy to obtain extra reward. In this paper, we are committed to solving these two limitations. First, we propose a novel mining strategy named Greedy-Mine attack. Then, we formulate a Markov Decision Process (MDP) model to analyze the competition of honest miners and adversaries. Furthermore, we analysis the extra reward of adversaries and summarize the mining power proportion range required for malicious adversaries to launch Greedy-Mine to obtain extra returns. Finally, we make a backward-compatibility progressive modification to Bitcoin-NG protocol that would raise the threshold of propagation factor from 0 to 1. Meanwhile, we get the winning condition of adversaries when adopting Greedy-Mine, compared with honest mining. Simulation and experimental results indicate that Bitcoin-NG is not incentive compatible, which is vulnerable to Greedy-Mine attack., Comment: 20 pages, 12 figurs

Mining attacks allow adversaries to obtain a disproportionate share of the mining reward by deviating from the honest mining strategy in the Bitcoin system. Among them, the most well-known are selfish mining (SM), block withholding (BWH), fork after withholding (FAW) and bribery mining. In this paper, we propose two novel mining attacks: bribery semi-selfish mining (BSSM) and bribery stubborn mining (BSM). Both of them can increase the relative extra reward of the adversary and will make the target bribery miners suffer from the bribery miner dilemma. All targets earn less under the Nash equilibrium. For each target, their local optimal strategy is to accept the bribes. However, they will suffer losses, comparing with denying the bribes. Furthermore, for all targets, their global optimal strategy is to deny the bribes. Quantitative analysis and simulation have been verified our theoretical analysis. We propose practical measures to mitigate more advanced mining attack strategies based on bribery mining, and provide new ideas for addressing bribery mining attacks in the future. However, how to completely and effectively prevent these attacks is still needed on further research., Comment: 26 pages, 16 figures, 3 tables

Although neural networks have made remarkable advancements in various applications, they require substantial computational and memory resources. Network quantization is a powerful technique to compress neural networks, allowing for more efficient and scalable AI deployments. Recently, Re-parameterization has emerged as a promising technique to enhance model performance while simultaneously alleviating the computational burden in various computer vision tasks. However, the accuracy drops significantly when applying quantization on the re-parameterized networks. We identify that the primary challenge arises from the large variation in weight distribution across the original branches. To address this issue, we propose a coarse & fine weight splitting (CFWS) method to reduce quantization error of weight, and develop an improved KL metric to determine optimal quantization scales for activation. To the best of our knowledge, our approach is the first work that enables post-training quantization applicable on re-parameterized networks. For example, the quantized RepVGG-A1 model exhibits a mere 0.3% accuracy loss. The code is in https://github.com/NeonHo/Coarse-Fine-Weight-Split.git, Comment: 23 pages

Morphological profiling is a valuable tool in phenotypic drug discovery. The advent of high-throughput automated imaging has enabled the capturing of a wide range of morphological features of cells or organisms in response to perturbations at the single-cell resolution. Concurrently, significant advances in machine learning and deep learning, especially in computer vision, have led to substantial improvements in analyzing large-scale high-content images at high-throughput. These efforts have facilitated understanding of compound mechanism-of-action (MOA), drug repurposing, characterization of cell morphodynamics under perturbation, and ultimately contributing to the development of novel therapeutics. In this review, we provide a comprehensive overview of the recent advances in the field of morphological profiling. We summarize the image profiling analysis workflow, survey a broad spectrum of analysis strategies encompassing feature engineering- and deep learning-based approaches, and introduce publicly available benchmark datasets. We place a particular emphasis on the application of deep learning in this pipeline, covering cell segmentation, image representation learning, and multimodal learning. Additionally, we illuminate the application of morphological profiling in phenotypic drug discovery and highlight potential challenges and opportunities in this field., Comment: 44 pages, 5 figure, 5 tables

Deep learning for Earth imagery plays an increasingly important role in geoscience applications such as agriculture, ecology, and natural disaster management. Still, progress is often hindered by the limited training labels. Given Earth imagery with limited training labels, a base deep neural network model, and a spatial knowledge base with label constraints, our problem is to infer the full labels while training the neural network. The problem is challenging due to the sparse and noisy input labels, spatial uncertainty within the label inference process, and high computational costs associated with a large number of sample locations. Existing works on neuro-symbolic models focus on integrating symbolic logic into neural networks (e.g., loss function, model architecture, and training label augmentation), but these methods do not fully address the challenges of spatial data (e.g., spatial uncertainty, the trade-off between spatial granularity and computational costs). To bridge this gap, we propose a novel Spatial Knowledge-Infused Hierarchical Learning (SKI-HL) framework that iteratively infers sample labels within a multi-resolution hierarchy. Our framework consists of a module to selectively infer labels in different resolutions based on spatial uncertainty and a module to train neural network parameters with uncertainty-aware multi-instance learning. Extensive experiments on real-world flood mapping datasets show that the proposed model outperforms several baseline methods. The code is available at \url{https://github.com/ZelinXu2000/SKI-HL}., Comment: SIGSPATIAL 2023 (Best Paper Award)

Transformers are widely used deep learning architectures. Existing transformers are mostly designed for sequences (texts or time series), images or videos, and graphs. This paper proposes a novel transformer model for massive (up to a million) point samples in continuous space. Such data are ubiquitous in environment sciences (e.g., sensor observations), numerical simulations (e.g., particle-laden flow, astrophysics), and location-based services (e.g., POIs and trajectories). However, designing a transformer for massive spatial points is non-trivial due to several challenges, including implicit long-range and multi-scale dependency on irregular points in continuous space, a non-uniform point distribution, the potential high computational costs of calculating all-pair attention across massive points, and the risks of over-confident predictions due to varying point density. To address these challenges, we propose a new hierarchical spatial transformer model, which includes multi-resolution representation learning within a quad-tree hierarchy and efficient spatial attention via coarse approximation. We also design an uncertainty quantification branch to estimate prediction confidence related to input feature noise and point sparsity. We provide a theoretical analysis of computational time complexity and memory costs. Extensive experiments on both real-world and synthetic datasets show that our method outperforms multiple baselines in prediction accuracy and our model can scale up to one million points on one NVIDIA A100 GPU. The code is available at \url{https://github.com/spatialdatasciencegroup/HST}., Comment: Accepted in NeurIPS 2023

With the advancement of GPS, remote sensing, and computational simulations, large amounts of geospatial and spatiotemporal data are being collected at an increasing speed. Such emerging spatiotemporal big data assets, together with the recent progress of deep learning technologies, provide unique opportunities to transform society. However, it is widely recognized that deep learning sometimes makes unexpected and incorrect predictions with unwarranted confidence, causing severe consequences in high-stake decision-making applications (e.g., disaster management, medical diagnosis, autonomous driving). Uncertainty quantification (UQ) aims to estimate a deep learning model's confidence. This paper provides a brief overview of UQ of deep learning for spatiotemporal data, including its unique challenges and existing methods. We particularly focus on the importance of uncertainty sources. We identify several future research directions for spatiotemporal data., Comment: Oral presentation in UDM-KDD'23

With advancements in GPS, remote sensing, and computational simulation, an enormous volume of spatiotemporal data is being collected at an increasing speed from various application domains, spanning Earth sciences, agriculture, smart cities, and public safety. Such emerging geospatial and spatiotemporal big data, coupled with recent advances in deep learning technologies, foster new opportunities to solve problems that have not been possible before. For instance, remote sensing researchers can potentially train a foundation model using Earth imagery big data for numerous land cover and land use modeling tasks. Coastal modelers can train AI surrogates to speed up numerical simulations. However, the distinctive characteristics of spatiotemporal big data pose new challenges for deep learning technologies. This vision paper introduces various types of spatiotemporal big data, discusses new research opportunities in the realm of deep learning applied to spatiotemporal big data, lists the unique challenges, and identifies several future research needs.

Temporal graph neural networks (TGNNs) have been widely used for modeling time-evolving graph-related tasks due to their ability to capture both graph topology dependency and non-linear temporal dynamic. The explanation of TGNNs is of vital importance for a transparent and trustworthy model. However, the complex topology structure and temporal dependency make explaining TGNN models very challenging. In this paper, we propose a novel explainer framework for TGNN models. Given a time series on a graph to be explained, the framework can identify dominant explanations in the form of a probabilistic graphical model in a time period. Case studies on the transportation domain demonstrate that the proposed approach can discover dynamic dependency structures in a road network for a time period.

High-performance traffic flow prediction model designing, a core technology of Intelligent Transportation System, is a long-standing but still challenging task for industrial and academic communities. The lack of integration between physical principles and data-driven models is an important reason for limiting the development of this field. In the literature, physics-based methods can usually provide a clear interpretation of the dynamic process of traffic flow systems but are with limited accuracy, while data-driven methods, especially deep learning with black-box structures, can achieve improved performance but can not be fully trusted due to lack of a reasonable physical basis. To bridge the gap between purely data-driven and physics-driven approaches, we propose a physics-guided deep learning model named Spatio-Temporal Differential Equation Network (STDEN), which casts the physical mechanism of traffic flow dynamics into a deep neural network framework. Specifically, we assume the traffic flow on road networks is driven by a latent potential energy field (like water flows are driven by the gravity field), and model the spatio-temporal dynamic process of the potential energy field as a differential equation network. STDEN absorbs both the performance advantage of data-driven models and the interpretability of physics-based models, so is named a physics-guided prediction model. Experiments on three real-world traffic datasets in Beijing show that our model outperforms state-of-the-art baselines by a significant margin. A case study further verifies that STDEN can capture the mechanism of urban traffic and generate accurate predictions with physical meaning. The proposed framework of differential equation network modeling may also cast light on other similar applications., Comment: 36th AAAI Conference on Artificial Intelligence (AAAI 2022)

This paper proposes a new data-driven method for predicting water temperature in stream networks with reservoirs. The water flows released from reservoirs greatly affect the water temperature of downstream river segments. However, the information of released water flow is often not available for many reservoirs, which makes it difficult for data-driven models to capture the impact to downstream river segments. In this paper, we first build a state-aware graph model to represent the interactions amongst streams and reservoirs, and then propose a parallel learning structure to extract the reservoir release information and use it to improve the prediction. In particular, for reservoirs with no available release information, we mimic the water managers' release decision process through a pseudo-prospective learning method, which infers the release information from anticipated water temperature dynamics. For reservoirs with the release information, we leverage a physics-based model to simulate the water release temperature and transfer such information to guide the learning process for other reservoirs. The evaluation for the Delaware River Basin shows that the proposed method brings over 10\% accuracy improvement over existing data-driven models for stream temperature prediction when the release data is not available for any reservoirs. The performance is further improved after we incorporate the release data and physical simulations for a subset of reservoirs.

Spatiotemporal data mining aims to discover interesting, useful but non-trivial patterns in big spatial and spatiotemporal data. They are used in various application domains such as public safety, ecology, epidemiology, earth science, etc. This problem is challenging because of the high societal cost of spurious patterns and exorbitant computational cost. Recent surveys of spatiotemporal data mining need update due to rapid growth. In addition, they did not adequately survey parallel techniques for spatiotemporal data mining. This paper provides a more up-to-date survey of spatiotemporal data mining methods. Furthermore, it has a detailed survey of parallel formulations of spatiotemporal data mining.

Global trends in tropospheric nitrogen dioxide (NO2) have changed dramatically in the past decade. Here, we investigate tropospheric NO2 variabilities over United States, Europe, and E. China in 2005–2018 to explore the mechanisms governing the variation of this critical pollutant. We found large uncertainties in the trends of anthropogenic nitrogen oxides (NOx) emissions, for example, the reductions of NOx emissions, derived with different approaches and data sets, are in the range of 35%–50% over the United States and 15%–45% over Europe in 2005–2018. By contrast, the analysis in this work indicates declines of anthropogenic NOx emissions by about 40% and 25% over the United States and Europe, respectively, in 2005–2018, and about 20% over E. China in 2012–2018. However, the shift of major NOx sources from power generation to industrial and transportation sectors has led to noticeable diminishing effects in emission controls. Furthermore, satellite measurements exhibit the influence of NO2 background levels over the United States and Europe, which offset the impacts of anthropogenic emission declines, resulting in flatter trends of tropospheric NO2 over the United States and Europe. Our analysis further reveals underestimation of background NO2 by chemical transport models, which can lead to inaccurate interpretations of satellite measurements. We use surface in-situ NO2 observations to diagnose the satellite-observed NO2 trends and find top-down NOx emissions over urban grids represent the changes in anthropogenic NOx emissions better. This work highlights the importance of comprehensive applications of different analysis approaches to better characterizing atmospheric composition evolution.

This study aims to investigate the membrane and diffusion behavior of a novel vertical cutoff wall backfill comprised of reactive magnesium-activated slag, bentonite and sand (referred as MSBS backfill) for the containment of heavy metals in groundwater. The MSBS backfill specimens were subjected to a series of multi-stage chemico-osmotic tests using Pb(NO3)2 and Zn(NO3)2 solutions at different concentrations. Chemico-osmotic efficiency coefficient, effective diffusion coefficient, and retardation factor of the backfills were computed. For computing chemico-osmotic efficiency coefficient, the theoretical chemico-osmotic pressure differences were computed using both van't Hoff equation and water activity method. The results showed that the MSBS backfill exhibited semipermeable membrane behavior in tested solutions. The chemico-osmotic efficiency coefficients of the backfills decreased, whereas effective diffusion coefficients of heavy metal cations remained nearly constant, and retardation factors of heavy metal cations increased slightly with the increase of metal concentration. For the range of concentrations of Zn(NO3)2 in this study, the maximum percent error of theoretical chemico-osmotic pressure difference calculated using van't Hoff equation relative to that calculated using water activity method was 14.4%. A comparative assessment of reported chemico-osmotic efficiency coefficient, effective diffusion coefficient, and retardation factor values for various soil-bentonite backfills and geosynthetic clay liners with those for MSBS backfill was performed. Overall, the results are useful to assess containment performance of MSBS vertical cutoff walls at metal-contaminated groundwater sites. © 2021

Weakly supervised object localization (WSOL) relaxes the requirement of dense annotations for object localization by using image-level classification masks to supervise its learning process. However, current WSOL methods suffer from excessive activation of background locations and need post-processing to obtain the localization mask. This paper attributes these issues to the unawareness of background cues, and propose the background-aware classification activation map (B-CAM) to simultaneously learn localization scores of both object and background with only image-level labels. In our B-CAM, two image-level features, aggregated by pixel-level features of potential background and object locations, are used to purify the object feature from the object-related background and to represent the feature of the pure-background sample, respectively. Then based on these two features, both the object classifier and the background classifier are learned to determine the binary object localization mask. Our B-CAM can be trained in end-to-end manner based on a proposed stagger classification loss, which not only improves the objects localization but also suppresses the background activation. Experiments show that our B-CAM outperforms one-stage WSOL methods on the CUB-200, OpenImages and VOC2012 datasets.

This study aims to investigate the membrane and diffusion behavior of a novel vertical cutoff wall backfill comprised of reactive magnesium-activated slag, bentonite and sand (referred as MSBS backfill) for the containment of heavy metals in groundwater. The MSBS backfill specimens were subjected to a series of multi-stage chemico-osmotic tests using Pb(NO3)2 and Zn(NO3)2 solutions at different concentrations. Chemico-osmotic efficiency coefficient, effective diffusion coefficient, and retardation factor of the backfills were computed. For computing chemico-osmotic efficiency coefficient, the theoretical chemico-osmotic pressure differences were computed using both van't Hoff equation and water activity method. The results showed that the MSBS backfill exhibited semipermeable membrane behavior in tested solutions. The chemico-osmotic efficiency coefficients of the backfills decreased, whereas effective diffusion coefficients of heavy metal cations remained nearly constant, and retardation factors of heavy metal cations increased slightly with the increase of metal concentration. For the range of concentrations of Zn(NO3)2 in this study, the maximum percent error of theoretical chemico-osmotic pressure difference calculated using van't Hoff equation relative to that calculated using water activity method was 14.4%. A comparative assessment of reported chemico-osmotic efficiency coefficient, effective diffusion coefficient, and retardation factor values for various soil-bentonite backfills and geosynthetic clay liners with those for MSBS backfill was performed. Overall, the results are useful to assess containment performance of MSBS vertical cutoff walls at metal-contaminated groundwater sites. © 2021

Purpose: Deep neural networks (DNNs) have been widely applied in medical image classification, benefiting from its powerful mapping capability among medical images. However, these existing deep learning-based methods depend on an enormous amount of carefully labeled images. Meanwhile, noise is inevitably introduced in the labeling process, degrading the performance of models. Hence, it's significant to devise robust training strategies to mitigate label noise in the medical image classification tasks. Methods: In this work, we propose a novel Bayesian statistics guided label refurbishment mechanism (BLRM) for DNNs to prevent overfitting noisy images. BLRM utilizes maximum a posteriori probability (MAP) in the Bayesian statistics and the exponentially time-weighted technique to selectively correct the labels of noisy images. The training images are purified gradually with the training epochs when BLRM is activated, further improving classification performance. Results: Comprehensive experiments on both synthetic noisy images (public OCT & Messidor datasets) and real-world noisy images (ANIMAL-10N) demonstrate that BLRM refurbishes the noisy labels selectively, curbing the adverse effects of noisy data. Also, the anti-noise BLRM integrated with DNNs are effective at different noise ratio and are independent of backbone DNN architectures. In addition, BLRM is superior to state-of-the-art comparative methods of anti-noise. Conclusions: These investigations indicate that the proposed BLRM is well capable of mitigating label noise in medical image classification tasks., Comment: 10 pages, 11 figures

The Mg[sbnd]Al, Ca[sbnd]Al, Zn[sbnd]Al and Mg[sbnd]Fe layered double hydroxides intercalated by sodium dodecyl sulfate was prepared by a co-precipitation method. These materials were characterized by elemental analysis, Powder X-ray diffraction (XRD) and N2 physical adsorption and desorption. Adsorption of CO2 on the samples was investigated by thermogravimetric analysis at 30 °C under 1 bar. The samples had a CO2 adsorption capacity in the range of 0.35–0.58 mmol/g. Ca[sbnd]Al layered double hydroxide intercalated by sodium dodecyl sulfate (SDS) had the highest CO2 adsorption capacity. The layered structures were analyzed by using quantum chemical calculation methods. The simulation results showed that CO2 adsorption capacity was correlated to the ELUMO and the density of Lowest Unoccupied Molecular Orbital (LUMO). The higher ELUMO and density of LUMO orbitals promoted the formation of O-H…O hydrogen bonds, which leaded to the higher CO2 adsorption capacity.

The Mg[sbnd]Al, Ca[sbnd]Al, Zn[sbnd]Al and Mg[sbnd]Fe layered double hydroxides intercalated by sodium dodecyl sulfate was prepared by a co-precipitation method. These materials were characterized by elemental analysis, Powder X-ray diffraction (XRD) and N2 physical adsorption and desorption. Adsorption of CO2 on the samples was investigated by thermogravimetric analysis at 30 °C under 1 bar. The samples had a CO2 adsorption capacity in the range of 0.35–0.58 mmol/g. Ca[sbnd]Al layered double hydroxide intercalated by sodium dodecyl sulfate (SDS) had the highest CO2 adsorption capacity. The layered structures were analyzed by using quantum chemical calculation methods. The simulation results showed that CO2 adsorption capacity was correlated to the ELUMO and the density of Lowest Unoccupied Molecular Orbital (LUMO). The higher ELUMO and density of LUMO orbitals promoted the formation of O-H…O hydrogen bonds, which leaded to the higher CO2 adsorption capacity.

The Mg[sbnd]Al, Ca[sbnd]Al, Zn[sbnd]Al and Mg[sbnd]Fe layered double hydroxides intercalated by sodium dodecyl sulfate was prepared by a co-precipitation method. These materials were characterized by elemental analysis, Powder X-ray diffraction (XRD) and N2 physical adsorption and desorption. Adsorption of CO2 on the samples was investigated by thermogravimetric analysis at 30 °C under 1 bar. The samples had a CO2 adsorption capacity in the range of 0.35–0.58 mmol/g. Ca[sbnd]Al layered double hydroxide intercalated by sodium dodecyl sulfate (SDS) had the highest CO2 adsorption capacity. The layered structures were analyzed by using quantum chemical calculation methods. The simulation results showed that CO2 adsorption capacity was correlated to the ELUMO and the density of Lowest Unoccupied Molecular Orbital (LUMO). The higher ELUMO and density of LUMO orbitals promoted the formation of O-H…O hydrogen bonds, which leaded to the higher CO2 adsorption capacity.

The Mg[sbnd]Al, Ca[sbnd]Al, Zn[sbnd]Al and Mg[sbnd]Fe layered double hydroxides intercalated by sodium dodecyl sulfate was prepared by a co-precipitation method. These materials were characterized by elemental analysis, Powder X-ray diffraction (XRD) and N2 physical adsorption and desorption. Adsorption of CO2 on the samples was investigated by thermogravimetric analysis at 30 °C under 1 bar. The samples had a CO2 adsorption capacity in the range of 0.35–0.58 mmol/g. Ca[sbnd]Al layered double hydroxide intercalated by sodium dodecyl sulfate (SDS) had the highest CO2 adsorption capacity. The layered structures were analyzed by using quantum chemical calculation methods. The simulation results showed that CO2 adsorption capacity was correlated to the ELUMO and the density of Lowest Unoccupied Molecular Orbital (LUMO). The higher ELUMO and density of LUMO orbitals promoted the formation of O-H…O hydrogen bonds, which leaded to the higher CO2 adsorption capacity.

Given a user-specified minimum degree threshold $\gamma$, a $\gamma$-quasi-clique is a subgraph $g=(V_g,E_g)$ where each vertex $v\in V_g$ connects to at least $\gamma$ fraction of the other vertices (i.e., $\lceil \gamma\cdot(|V_g|-1)\rceil$ vertices) in $g$. Quasi-clique is one of the most natural definitions for dense structures useful in finding communities in social networks and discovering significant biomolecule structures and pathways. However, mining maximal quasi-cliques is notoriously expensive. In this paper, we design parallel algorithms for mining maximal quasi-cliques on G-thinker, a recent distributed framework targeting divide-and-conquer graph mining algorithms that decomposes the mining into compute-intensive tasks to fully utilize CPU cores. However, we found that directly using G-thinker results in the straggler problem due to (i) the drastic load imbalance among different tasks and (ii) the difficulty of predicting the task running time and the time growth with task-subgraph size. We address these challenges by redesigning G-thinker's execution engine to prioritize long-running tasks for mining, and by utilizing a novel timeout strategy to effectively decompose the mining workloads of long-running tasks to improve load balancing. While this system redesign applies to many other expensive dense subgraph mining problems, this paper verifies the idea by adapting the state-of-the-art quasi-clique algorithm, Quick, to our redesigned G-thinker. We improve Quick by integrating new pruning rules, and fixing some missed boundary cases that could lead to missed results. Extensive experiments verify that our new solution scales well with the number of CPU cores, achieving 201$\times$ runtime speedup when mining a graph with 3.77M vertices and 16.5M edges in a 16-node cluster., Comment: Guimu Guo and Da Yan are parallel first authors; this is the full version of our PVLDB 2021 paper with the same title

Recovering sharp video sequence from a motion-blurred image is highly ill-posed due to the significant loss of motion information in the blurring process. For event-based cameras, however, fast motion can be captured as events at high time rate, raising new opportunities to exploring effective solutions. In this paper, we start from a sequential formulation of event-based motion deblurring, then show how its optimization can be unfolded with a novel end-to-end deep architecture. The proposed architecture is a convolutional recurrent neural network that integrates visual and temporal knowledge of both global and local scales in principled manner. To further improve the reconstruction, we propose a differentiable directional event filtering module to effectively extract rich boundary prior from the stream of events. We conduct extensive experiments on the synthetic GoPro dataset and a large newly introduced dataset captured by a DAVIS240C camera. The proposed approach achieves state-of-the-art reconstruction quality, and generalizes better to handling real-world motion blur., Comment: Accepted to CVPR 2020

With the advancement of GPS and remote sensing technologies, large amounts of geospatial and spatiotemporal data are being collected from various domains, driving the need for effective and efficient prediction methods. Given spatial data samples with explanatory features and targeted responses (categorical or continuous) at a set of locations, the problem aims to learn a model that can predict the response variable based on explanatory features. The problem is important with broad applications in earth science, urban informatics, geosocial media analytics and public health, but is challenging due to the unique characteristics of spatiotemporal data, including spatial and temporal autocorrelation, spatial heterogeneity, temporal non-stationarity, limited ground truth, and multiple scales and resolutions. This paper provides a systematic review on principles and methods in spatial and spatiotemporal prediction. We provide a taxonomy of methods categorized by the key challenge they address. For each method, we introduce its underlying assumption, theoretical foundation, and discuss its advantages and disadvantages. Our goal is to help interdisciplinary domain scientists choose techniques to solve their problems, and more importantly, to help data mining researchers to understand the main principles and methods in spatial and spatiotemporal prediction and identify future research opportunities.

Convolutional neural networks (CNNs) are becoming increasingly deeper, wider, and non-linear because of the growing demand on prediction accuracy and analysis quality. The wide and deep CNNs, however, require a large amount of computing resources and processing time. Many previous works have studied model pruning to improve inference performance, but little work has been done for effectively reducing training cost. In this paper, we propose ClickTrain: an efficient and accurate end-to-end training and pruning framework for CNNs. Different from the existing pruning-during-training work, ClickTrain provides higher model accuracy and compression ratio via fine-grained architecture-preserving pruning. By leveraging pattern-based pruning with our proposed novel accurate weight importance estimation, dynamic pattern generation and selection, and compiler-assisted computation optimizations, ClickTrain generates highly accurate and fast pruned CNN models for direct deployment without any extra time overhead, compared with the baseline training. ClickTrain also reduces the end-to-end time cost of the pruning-after-training method by up to 2.3X with comparable accuracy and compression ratio. Moreover, compared with the state-of-the-art pruning-during-training approach, ClickTrain provides significant improvements both accuracy and compression ratio on the tested CNN models and datasets, under similar limited training time., Comment: 12 pages, 15 figures, 2 tables, published by ICS'21

In recent years, deep learning techniques (e.g., U-Net, DeepLab) have achieved tremendous success in image segmentation. The performance of these models heavily relies on high-quality ground truth segment labels. Unfortunately, in many real-world problems, ground truth segment labels often have geometric annotation errors due to manual annotation mistakes, GPS errors, or visually interpreting background imagery at a coarse resolution. Such location errors will significantly impact the training performance of existing deep learning algorithms. Existing research on label errors either models ground truth errors in label semantics (assuming label locations to be correct) or models label location errors with simple square patch shifting. These methods cannot fully incorporate the geometric properties of label location errors. To fill the gap, this paper proposes a generic learning framework based on the EM algorithm to update deep learning model parameters and infer hidden true label locations simultaneously. Evaluations on a real-world hydrological dataset in the streamline refinement application show that the proposed framework outperforms baseline methods in classification accuracy (reducing the number of false positives by 67% and reducing the number of false negatives by 55%).

Spatial classification with limited feature observations has been a challenging problem in machine learning. The problem exists in applications where only a subset of sensors are deployed at certain spots or partial responses are collected in field surveys. Existing research mostly focuses on addressing incomplete or missing data, e.g., data cleaning and imputation, classification models that allow for missing feature values or model missing features as hidden variables in the EM algorithm. These methods, however, assume that incomplete feature observations only happen on a small subset of samples, and thus cannot solve problems where the vast majority of samples have missing feature observations. To address this issue, we recently proposed a new approach that incorporates physics-aware structural constraint into the model representation. Our approach assumes that a spatial contextual feature is observed for all sample locations and establishes spatial structural constraint from the underlying spatial contextual feature map. We design efficient algorithms for model parameter learning and class inference. This paper extends our recent approach by allowing feature values of samples in each class to follow a multi-modal distribution. We propose learning algorithms for the extended model with multi-modal distribution. Evaluations on real-world hydrological applications show that our approach significantly outperforms baseline methods in classification accuracy, and the multi-modal extension is more robust than our early single-modal version especially when feature distribution in training samples is multi-modal. Computational experiments show that the proposed solution is computationally efficient on large datasets.

Semi-supervised learning aims to learn prediction models from both labeled and unlabeled samples. There has been extensive research in this area. Among existing work, generative mixture models with Expectation-Maximization (EM) is a popular method due to clear statistical properties. However, existing literature on EM-based semi-supervised learning largely focuses on unstructured prediction, assuming that samples are independent and identically distributed. Studies on EM-based semi-supervised approach in structured prediction is limited. This paper aims to fill the gap through a comparative study between unstructured and structured methods in EM-based semi-supervised learning. Specifically, we compare their theoretical properties and find that both methods can be considered as a generalization of self-training with soft class assignment of unlabeled samples, but the structured method additionally considers structural constraint in soft class assignment. We conducted a case study on real-world flood mapping datasets to compare the two methods. Results show that structured EM is more robust to class confusion caused by noise and obstacles in features in the context of the flood mapping application.

Given a 3D surface defined by an elevation function on a 2D grid as well as non-spatial features observed at each pixel, the problem of surface segmentation aims to classify pixels into contiguous classes based on both non-spatial features and surface topology. The problem has important applications in hydrology, planetary science, and biochemistry but is uniquely challenging for several reasons. First, the spatial extent of class segments follows surface contours in the topological space, regardless of their spatial shapes and directions. Second, the topological structure exists in multiple spatial scales based on different surface resolutions. Existing widely successful deep learning models for image segmentation are often not applicable due to their reliance on convolution and pooling operations to learn regular structural patterns on a grid. In contrast, we propose to represent surface topological structure by a contour tree skeleton, which is a polytree capturing the evolution of surface contours at different elevation levels. We further design a graph neural network based on the contour tree hierarchy to model surface topological structure at different spatial scales. Experimental evaluations based on real-world hydrological datasets show that our model outperforms several baseline methods in classification accuracy.

Flood extent mapping plays a crucial role in disaster management and national water forecasting. In recent years, high-resolution optical imagery becomes increasingly available with the deployment of numerous small satellites and drones. However, analyzing such imagery data to extract flood extent poses unique challenges due to the rich noise and shadows, obstacles (e.g., tree canopies, clouds), and spectral confusion between pixel classes (flood, dry) due to spatial heterogeneity. Existing machine learning techniques often focus on spectral and spatial features from raster images without fully incorporating the geographic terrain within classification models. In contrast, we recently proposed a novel machine learning model called geographical hidden Markov tree that integrates spectral features of pixels and topographic constraints from Digital Elevation Model (DEM) data (i.e., water flow directions) in a holistic manner. This paper evaluates the model through case studies on high-resolution aerial imagery from the National Oceanic and Atmospheric Administration (NOAA) National Geodetic Survey together with DEM. Three scenes are selected in heavily vegetated floodplains near the cities of Grimesland and Kinston in North Carolina during Hurricane Matthew floods in 2016. Results show that the proposed hidden Markov tree model outperforms several state of the art machine learning algorithms (e.g., random forests, gradient boosted model) by an improvement of F-score (the harmonic mean of the user's accuracy and producer's accuracy) from around 70% to 80% to over 95% on our datasets.

Limited research has been conducted on the contributions of local and nonlocal emission sources to ambient fine particulate matter (PM2.5) and ozone (O3) and their associated mortality. In this study, we estimated the total mortality resulting from long-term PM2.5 and O3 exposures in California in 2012 using multiple concentration response functions (CRFs) and attributed the estimated mortality to different emission groups. The point estimates of PM2.5-associated mortality in California ranged from 12,700 to 26,700, of which 53% were attributable to in-state anthropogenic emissions. Based on new epidemiological evidence, we estimated that O3 could be associated with up to 13,700 deaths from diseases of both the respiratory and cardiovascular systems in California. In addition, 75% of the ambient O3 in California was due to distant emissions outside the western United States, leading to 92% of the O3-associated mortality. Overall, distant emissions lead to greater mortality burdens of air pollution in California than local anthropogenic emissions.

Limited research has been conducted on the contributions of local and nonlocal emission sources to ambient fine particulate matter (PM2.5) and ozone (O3) and their associated mortality. In this study, we estimated the total mortality resulting from long-term PM2.5 and O3 exposures in California in 2012 using multiple concentration response functions (CRFs) and attributed the estimated mortality to different emission groups. The point estimates of PM2.5-associated mortality in California ranged from 12,700 to 26,700, of which 53% were attributable to in-state anthropogenic emissions. Based on new epidemiological evidence, we estimated that O3 could be associated with up to 13,700 deaths from diseases of both the respiratory and cardiovascular systems in California. In addition, 75% of the ambient O3 in California was due to distant emissions outside the western United States, leading to 92% of the O3-associated mortality. Overall, distant emissions lead to greater mortality burdens of air pollution in California than local anthropogenic emissions.

Peritoneal dissemination is the most frequent metastatic route of ovarian cancer. However, due to the high heterogeneity in ovarian cancer, most conventional studies lack parental tumor controls relevant to metastases and, thus, it is difficult to trace the molecular changes of cancer cells along with the selection by the abdominal microenvironment. Here, we established an in vivo mouse peritoneal dissemination scheme that allowed us to select more aggressive sublines from parental ovarian cancer cells, including A2780 and SKOV-3. Microarray and gene profiling analyses indicated that autophagy-related genes were enriched in selected malignant sublines. Detection of LC3-II, p62 and autophagic puncta demonstrated that these malignant variants were more sensitive to autophagic induction when exposed to diverse stress conditions, such as high cell density, starvation and drug treatment. As compared with parental A2780, the selected variant acquired the ability to grow better under high-density stress; however, this effect was reversed by addition of autophagic inhibitors or knockdown of ATG5. When analyzing the clinical profiles of autophagy-related genes identified to be enriched in malignant A2780 variant, 73% of them had prognostic significance for the survival of ovarian cancer patients. Taken together, our findings indicate that an increase in autophagic potency among ovarian cancer cells is crucial for selection of metastatic colonies in the abdominal microenvironment. In addition, the derived autophagic gene profile can not only predict prognosis well but can also be potentially applied to precision medicine for identifying those ovarian cancer patients suitable for taking anti-autophagy cancer drugs.

As the world's fifth-largest economy, California has committed to reduce its greenhouse gas (GHG) emissions by 80% below 1990 levels by 2050. While previous studies have shown that GHG reductions could synergistically decrease air pollutant emissions and protect public health, limited research has been conducted to compare the health cobenefits of different technology pathways toward deep decarbonization. Using an integrated approach that combines energy and emission technology modeling, high-resolution chemical transport simulation, and health impact assessment, we find that achievement of the 80% GHG reduction target would bring substantial air quality and health cobenefits. The cobenefits, however, highly depend on the selected technology pathway largely because of California's relatively clean energy structure. Compared with the business-as-usual levels, a decarbonization pathway that focuses on electrification and clean renewable energy is estimated to reduce concentrations of fine particulate matter (PM2.5) by 18-37% in major metropolitan areas of California and subsequently avoid about 12 100 (9600-14 600) premature deaths. In contrast, only a quarter of such health cobenefits, i.e., 2800 (2300-3400) avoided deaths, can be achieved through a pathway focusing more on combustible renewable fuels. After subtracting the cost, the net monetized benefit of the electrification-focused pathway still exceeds that of the renewable fuel-focused pathway, indicating that a cleaner but more expensive decarbonization pathway may be more preferable in California.

Limited research has been conducted on the contributions of local and nonlocal emission sources to ambient fine particulate matter (PM2.5) and ozone (O3) and their associated mortality. In this study, we estimated the total mortality resulting from long-term PM2.5 and O3 exposures in California in 2012 using multiple concentration response functions (CRFs) and attributed the estimated mortality to different emission groups. The point estimates of PM2.5-associated mortality in California ranged from 12,700 to 26,700, of which 53% were attributable to in-state anthropogenic emissions. Based on new epidemiological evidence, we estimated that O3 could be associated with up to 13,700 deaths from diseases of both the respiratory and cardiovascular systems in California. In addition, 75% of the ambient O3 in California was due to distant emissions outside the western United States, leading to 92% of the O3-associated mortality. Overall, distant emissions lead to greater mortality burdens of air pollution in California than local anthropogenic emissions. © 2019 The Authors

We use a hybrid deep learning model to predict June-July-August (JJA) daily maximum 8-h average (MDA8) surface ozone concentrations in the US. A set of meteorological fields from the ERA-Interim reanalysis as well as monthly mean NO$_x$ emissions from the Community Emissions Data System (CEDS) inventory are selected as predictors. Ozone measurements from the US Environmental Protection Agency (EPA) Air Quality System (AQS) from 1980 to 2009 are used to train the model, whereas data from 2010 to 2014 are used to evaluate the performance of the model. The model captures well daily, seasonal and interannual variability in MDA8 ozone across the US. Feature maps show that the model captures teleconnections between MDA8 ozone and the meteorological fields, which are responsible for driving the ozone dynamics. We used the model to evaluate recent trends in NO$_x$ emissions in the US and found that the trend in the EPA emission inventory produced the largest negative bias in MDA8 ozone between 2010-2016. The top-down emission trends from the Tropospheric Chemistry Reanalysis (TCR-2), which is based on satellite observations, produced predictions in best agreement with observations. In urban regions, the trend in AQS NO$_2$ observations provided ozone predictions in agreement with observations, whereas in rural regions the satellite-derived trends produced the best agreement. In both rural and urban regions the EPA trend resulted in the largest negative bias in predicted ozone. Our results suggest that the EPA inventory is overestimating the reductions in NO$_x$ emissions and that the satellite-derived trend reflects the influence of reductions in NO$_x$ emissions as well as changes in background NO$_x$. Our results demonstrate the significantly greater predictive capability that the deep learning model provides over conventional atmospheric chemical transport models for air quality analyses.

Each year, around 6 million car accidents occur in the U.S. on average. Road safety features (e.g., concrete barriers, metal crash barriers, rumble strips) play an important role in preventing or mitigating vehicle crashes. Accurate maps of road safety features is an important component of safety management systems for federal or state transportation agencies, helping traffic engineers identify locations to invest on safety infrastructure. In current practice, mapping road safety features is largely done manually (e.g., observations on the road or visual interpretation of streetview imagery), which is both expensive and time consuming. In this paper, we propose a deep learning approach to automatically map road safety features from streetview imagery. Unlike existing Convolutional Neural Networks (CNNs) that classify each image individually, we propose to further add Recurrent Neural Network (Long Short Term Memory) to capture geographic context of images (spatial autocorrelation effect along linear road network paths). Evaluations on real world streetview imagery show that our proposed model outperforms several baseline methods., Comment: 17 pages, 16 figures, 3 tables

Ground and satellite observations show that air pollution regulations in the United States (US) have resulted in substantial reductions in emissions and corresponding improvements in air quality over the last several decades. However, large uncertainties remain in evaluating how recent regulations affect different emission sectors and pollutant trends. Here we show a significant slowdown in decreasing US emissions of nitrogen oxides (NOx) and carbon monoxide (CO) for 2011–2015 using satellite and surface measurements. This observed slowdown in emission reductions is significantly different from the trend expected using US Environmental Protection Agency (EPA) bottom-up inventories and impedes compliance with local and federal agency air-quality goals. We find that the difference between observations and EPA’s NOx emission estimates could be explained by: (i) growing relative contributions of industrial, area, and off-road sources, (ii) decreasing relative contributions of on-road gasoline, and (iii) slower than expected decreases in on-road diesel emissions.

In this technical note we compare silica gel grains and quartz sand as sediment media for vegetation root growth in laboratory experiments for ecohydrology and ecohydraulics. Silica gel grains become quite transparent when saturated with water. This would be useful in order to non-invasively observe the rate of growth of plant roots and plan parallel laboratory experiments made in more typical sand sediments. In this work, we compare the results of preliminary tests conducted using quartz sand with the same grain size distribution of silica gel grains. We show that the complex microstructure of silica gel grains seems to influence the evaporation and, in turn, plant growth dynamics. The potential and limitations of the use of silica grains are accordingly discussed in light of more detailed experiments

Flood extent mapping plays a crucial role in disaster management and national water forecasting. Unfortunately, traditional classification methods are often hampered by the existence of noise, obstacles and heterogeneity in spectral features as well as implicit anisotropic spatial dependency across class labels. In this paper, we propose geographical hidden Markov tree, a probabilistic graphical model that generalizes the common hidden Markov model from a one dimensional sequence to a two dimensional map. Anisotropic spatial dependency is incorporated in the hidden class layer with a reverse tree structure. We also investigate computational algorithms for reverse tree construction, model parameter learning and class inference. Extensive evaluations on both synthetic and real world datasets show that proposed model outperforms multiple baselines in flood mapping, and our algorithms are scalable on large data sizes.

I/O virtualization enables time and space multiplexing of I/O devices, by mapping multiple logical I/O devices upon a smaller number of physical devices. However, due to the existence of additional virtualization layers, requesting an I/O from a guest virtual machine requires complicated sequences of operations. This leads to I/O performance losses, and makes precise timing of I/O operations unpredictable. This paper proposes a hardware I/O virtualization system, termed the Virtualized Complicated Device Controller (VCDC). This I/O system allows user applications to access and operate I/O devices directly from guest VMs, and bypasses the guest OS, the Virtual Machine Monitor (VMM) and low layer I/O drivers. We show that the VCDC efficiently reduces the software overhead and enhances the I/O performance and timing predictability. Furthermore, VCDC also exhibits good scalability that can handle I/O requests from variable number of CPUs in a system.