Search

Microfluidic paper-based analytical devices ($\mu $ PADs) are a clean-room free, cost-effective, and self-pumping flow-based rapid prototyping technique, which is compatible with a varying range of fluids. Until now, $\mu $ PADs have been primarily fabricated using crayons, and plotting-machine and solid-ink printers. These devices can be easily employed for various detection schemes, such as electrical, electrochemical, and optical. The presence of a capillary effect in the chromatograph paper has made $\mu $ PADs independent of a passive device, such as pumps and valves. In this paper, an alternative and a novel method is proposed to achieve the $\mu $ PADs effortlessly using a 3-D printer (3DP), which has many advantages over the existing methods. For creating hydrophobic barriers for microchannel walls, polycaprolactone (PCL) filament was used with fused-deposition modeling (FDM) 3DP. PCL filaments were deposited on the chromatography paper followed by heating for determining the overall dimension and depth of the microchannel at which PCL melts and penetrates into this paper. The $\mu $ PADs are characterized and optimized for two parameters. First, fabrication parameters, such as heating temperature and time duration, were used for the creation of the hydrophobic barrier using a hot air oven. Second, the microchannel parameters, such as microchannel width, boundary thickness, chromatography paper grade, and microchannel source shape (rectangular, triangular, and circular) were used for the fluid-flow by measuring the time taken by fluid to travel a fixed length of the microchannel. After rigorous analysis, it was found that for the creation of the hydrophobic barrier, $\mu $ PADs heated between temperature 120°C to 150°C require 30 min. Under optimized conditions for the fluid flow, the chromatography paper grade 1441 with a triangular source microchannel was found to be best. This paper provides an alternate, simple, and optimized method toward the development of the application-specific $\mu $ PADs, such as the micro-viscometer, which, in turn, can be widely used to monitor various types of fluids including human bodily fluids. [ABSTRACT FROM AUTHOR]

In this paper, we investigate a very challenging task of automatically generating presentation slides for academic papers. The generated presentation slides can be used as drafts to help the presenters prepare their formal slides in a quicker way. A novel system called PPSGen is proposed to address this task. It first employs the regression method to learn the importance scores of the sentences in an academic paper, and then exploits the integer linear programming (ILP) method to generate well-structured slides by selecting and aligning key phrases and sentences. Evaluation results on a test set of 200 pairs of papers and slides collected on the web demonstrate that our proposed PPSGen system can generate slides with better quality. A user study is also illustrated to show that PPSGen has a few evident advantages over baseline methods. [ABSTRACT FROM PUBLISHER]

As one of the most important unit in the papermaking industry, the high consistency (HC) refining system is confronted with challenges such as improving pulp quality, energy saving, and emissions reduction in its operation processes. In this correspondence, an optimal operation of HC refining system is presented using nonlinear multiobjective model predictive control strategies that aim at set-point tracking objective of pulp quality, economic objective, and specific energy (SE) consumption objective, respectively. First, a set of input and output data at different times are employed to construct the subprocess model of the state process model for the HC refining system, and then the Wiener-type model can be obtained through combining the mechanism model of Canadian Standard Freeness and the state process model that determines their structures based on Akaike information criterion. Second, the multiobjective optimization strategy that optimizes both the set-point tracking objective of pulp quality and SE consumption is proposed simultaneously, which uses NSGA-II approach to obtain the Pareto optimal set. Furthermore, targeting at the set-point tracking objective of pulp quality, economic objective, and SE consumption objective, the sequential quadratic programming method is utilized to produce the optimal predictive controllers. Finally, the simulation results demonstrate that the proposed methods can make the HC refining system provide a better performance of set-point tracking of pulp quality when these predictive controllers are employed. In addition, while the optimal predictive controllers orienting with comprehensive economic objective and SE consumption objective, it has been shown that they have significantly reduced the energy consumption. [ABSTRACT FROM AUTHOR]

Chemical mechanical planarization (CMP) is vital for ensuring chip fabrication uniformity at nanometer scales. The emergence of a series of phenomenological CMP process models (Stine et al., 1997; Gbondo-Tugbawa, 2002; Xie, 2007; Vasilev, 2011) suggests that the existing model upgrade approach is largely based on a change in phenomenological model assumptions, demanding deep insights into complex process mechanisms and protracted period for accuracy improvements. To tackle this issue, this paper proposes a decoupling regression strategy for model upgrades. This strategy employs a data-driven approach to enhance the coupling relationships within the model, facilitating continuous improvement of simulation accuracy based on the existing model. It is capable of achieving improvements in model accuracy even in scenarios where modelers lack insight into complex process mechanisms. We validate our method by upgrading the Density Step Height (DSH) model to the Extend-DSH model to address poor erosion predictions at the 28nm node. Comparing model predictions with silicon data reveals that the Extend-DSH model aligns better with the measured data, reducing the root mean square error from 159.31Å to 6.89Å and increasing the coefficient of determination from -0.83561 to 0.6058, showcasing the effectiveness of the proposed chip-level CMP model upgrade method grounded in the decoupling regression strategy. [ABSTRACT FROM AUTHOR]

We present the results of a comprehensive multi-pass analysis of visualization paper keywords supplied by authors for their papers published in the IEEE Visualization conference series (now called IEEE VIS) between 1990–2015. From this analysis we derived a set of visualization topics that we discuss in the context of the current taxonomy that is used to categorize papers and assign reviewers in the IEEE VIS reviewing process. We point out missing and overemphasized topics in the current taxonomy and start a discussion on the importance of establishing common visualization terminology. Our analysis of research topics in visualization can, thus, serve as a starting point to (a) help create a common vocabulary to improve communication among different visualization sub-groups, (b) facilitate the process of understanding differences and commonalities of the various research sub-fields in visualization, (c) provide an understanding of emerging new research trends, (d) facilitate the crucial step of finding the right reviewers for research submissions, and (e) it can eventually lead to a comprehensive taxonomy of visualization research. One additional tangible outcome of our work is an online query tool (http://keyvis.org/) that allows visualization researchers to easily browse the 3952 keywords used for IEEE VIS papers since 1990 to find related work or make informed keyword choices. [ABSTRACT FROM PUBLISHER]

Monitoring topographic variations in the engineered surface is crucial for quality engineers since the change in the surface finish is closely related to the performance of products. However, several challenging issues such as the existence of spatial autocorrelation within the surface, and changes of topographic features such as position and shape of peaks and valleys across defect-free surfaces make it difficult to monitor variations in the surface. In addition, existing monitoring approaches fail to detect local changes in the surface. In this article, we present a new approach for monitoring topographic variations in surfaces. We develop a residual-based separation deviation (RBSD) model to effectively identify local surface changes. Residuals are obtained through the fit surface prediction model, which characterizes the generic behavior of defect-free surfaces, and binarized by the RBSD model to distinguish the defective region where residuals are autocorrelated. A spatial randomness-based monitoring statistic is introduced to evaluate binary patterns in order to detect surface anomalies. Numerical simulation and a case study of the coated paper surface monitoring are provided to demonstrate the effectiveness of the proposed approach. Note to Practitioners—An increasing number of optical measuring instruments provide quality engineers with surface topographic data of the product, and enable precise and accurate inspection of surface variations during the manufacturing process. However, spatial and arbitrary geometric features on topographic data often make monitoring the surface changes a challenging task. This article proposes a new monitoring approach for detecting topographic variations in the surface. We mathematically characterize the generic behavior of the surface under the normal process, and present a surface segmentation model to detect local variations in the surface. In practice, our approach is applicable to real-life paper surface variations monitoring. The proposed approach is expected to provide a new idea to practitioners who work on surface topography inspection in various fields as well as the pulp industry. [ABSTRACT FROM AUTHOR]

This paper is devoted to electric arc furnace (EAF) modeling using a random differential equation based on the power balance equation. The proposed approach broadens and improves the model through the introduction of stochastic processes in place of existing coefficients. The paper presents a method which enables the estimation of EAF model coefficients with the help of measurement data - voltage and current waveforms recorded during the melting stage of an EAF work cycle. The estimation process is conducted with a Monte Carlo method and genetic algorithm, which is applied iteratively to each of the defined frames of the input signal. The estimated coefficients have been analyzed with respect to their time variability as well as the probability distributions of their values and increments. The results have been extensively visualized. Next, the identification of the stochastic processes representing the model coefficients has been carried out. Based on the previous results and autocorrelation functions, the density functions and parameters of discrete-time stochastic processes were identified. The paper presents solutions validated with statistical tests. [ABSTRACT FROM AUTHOR]

The scientific world is becoming more open to the public and fellow researchers. Open access publishing is becoming accepted, even if some publishers are resisting. The next step is the open code and data paradigm, which was briefly discussed in the "From the Editor" column in the November 2018 issue of IEEE Signal Processing Magazine (SPM) [1]. In this column, I follow up on this topic by sharing my experiences, best practices, and thoughts about reproducible research. [ABSTRACT FROM AUTHOR]

The semi-supervised face recognition problem has become a popular research topic in recent years. However, one common and important situation, in which the unlabeled data is shallow, has rarely been considered in most existing works. In this paper, shallow data means there are only few images per identity. In the unlabeled shallow situation, the existing semi-supervised face recognition methods generally do not work well. Thus, how to effectively utilize the unlabeled shallow face data for improving face recognition performance is an important issue. In this paper, we propose a novel semi-supervised face recognition method, namely VirFace $^{\infty} $ , to enhance the face recognition performance effectively with the unlabeled shallow data. VirFace $^{\infty} $ consists of VirClass and VirDistribution components. In VirClass, we inject the unlabeled data as virtual classes into the feature space to enlarge the inter-class distance. In VirDistribution, we predict the distribution of each virtual class, namely virtual distribution, and then enhance the inter-class discriminativeness by enlarging the distances between the labeled features and the virtual distributions. To the best of our knowledge, we are among the first to tackle the face recognition problem on unlabeled shallow face data. Extensive experiments demonstrate the superiority of our proposed method. [ABSTRACT FROM AUTHOR]

Recognition of aggressive driving behavior helps future research and practices in Intelligent Transport Systems. This paper tries to briefly explain the concepts related to aggressive driving behavior and introduces a system integrated with a novel machine learning algorithm for the recognition of trip-based aggressive driving behavior. The algorithm is a Gaussian Mixture Model (GMM) structured with Factor Analysis (FA), and Hierarchical Clustering (HC): common factors were extracted using FA, which is further applied to HC and GMM in the recognition of trip-based aggressive driving. The system is applied in a case study using data from the Shanghai Naturalistic Driving Study, for simulating data collection using the Advanced Driving Assistance System (ADAS) system in a real-traffic situation. Three behavior types (cautious, regular, and aggressive driving) were successfully clustered. For validity, the real aggressive driving behavior records were extracted based on the video, and the proposed system was compared with existing recognition methods. Results indicate that the accuracy of aggressive driving recognition of the system is higher than others (accuracy = 87%). This paper provides a reference in defining and determining aggressive driving, and a robust system for aggressive driving behavior recognition along with the trained algorithm, which can be used in real-world applications for improving driving safety with the applications in ADAS systems, auto-insurance industry. [ABSTRACT FROM AUTHOR]

Since the introduction of adaptive steganography, most of the recent research works seek at designing cost functions that are evaluated against steganalysis methods. While those approaches have been successful, they rely on intuitive principles and ad-hoc costs associated with each pixel or Discrete Cosine Transform (DCT) coefficient. Beyond the empirical assessments, the insights one can get from such approaches are very limited. On the opposite, this paper presents an original method for steganography in JPEG images that exploits a statistical model of the DCT coefficients. Within the framework of hypothesis testing theory, we use a statistical model of covers to derive the analytical expression of the most powerful detector. The objective of the steganographer is to minimize the statistical performance of this “omniscient detector” which represents a “worst-case” scenario for security. This paper shows how this method allows designing effective steganography, in terms of both security and computational complexity, in the two main use cases: when having only one single JPEG image and when the uncompressed image is available, case also known as Side-Informed (SI). A wide range of numerical comparisons shows that the proposed method outperforms the current state-of-the-art especially against the latest and most accurate steganalysis approaches based on Deep Learning. [ABSTRACT FROM AUTHOR]

Transportation agencies have an opportunity to leverage increasingly available trajectory datasets to improve their analyses and decision-making processes. However, this data is typically purchased from vendors, which means agencies must understand its potential benefits beforehand in order to properly assess its value relative to the cost of acquisition. While the literature concerned with trajectory data is rich, it is naturally fragmented and focused on technical contributions in niche areas, which makes it difficult for government agencies to assess its value across different transportation domains. To overcome this issue, this paper explores trajectory data from the perspective of a road transportation agency interested in acquiring trajectories to enhance its analysis. This paper provides a literature review illustrating applications of trajectory data in six areas of road transportation systems analysis: demand estimation, modeling human behavior, designing public transit, traffic performance measurement and prediction, environment, and safety. In addition, it visually explores 20 million GPS traces in Maryland, USA, illustrating the existing and suggesting new applications of trajectory data. [ABSTRACT FROM AUTHOR]

This paper presents an Adaboost algorithm based cutting data analysis for chatter detection. This offline chatter analysis uses the vibration data collected by accelerometers attached to the spindle housing. A comparison of the accuracy achieved with support vector machine, Random Forest, 1D Convolutional Neural Networks and Multilayer Perceptron algorithm is also made. In this paper, the accelerometer data are transformed into bandwidth. Time-accelerometer and time-spectral bandwidth learning models are built in order to realize chatter detection and automated machine learning. A comparison of the models is made. The results of cross validation indicate that an accuracy of 98% is achieved, which is made possible by using the bandwidth signals that are transformed from accelerometer data. Experimental results show that applying the Adaboost algorithm to analyze the spectral data transformed from vibration signals and using them to detect chatters has higher reliability and accuracy compared to other algorithms and analyzing other transform signals. [ABSTRACT FROM AUTHOR]

The online retail market shows a sharp increase in traffic during holiday sales. The ability to distinguish customers who will likely purchase is critical for provisioning traffic and for providing cost-effective promotions. This paper uniquely studies the browsing and purchasing behaviors of online shoppers during a yearly sale event in China, the world’s largest online marketplace. Based on 31 million action logs gathered from wide residential areas, we characterize the steps leading to purchases and determine their precursors. We investigate the effect of time (e.g., date, time of date), environment (e.g., platform, viewed category), and action (e.g., session time, clicks, sequence) on purchases. Action cues from shopping behaviors can be used for early detection. While most shoppers start with strong intentions to purchase, yet the moment of ordering comes rather impulsively within 30 seconds to several minutes of browsing. The predictive accuracy reaches as a high AUC of 0.924. The findings in this paper provide an understanding of traffic during mega sale events that can help online shops plan and provide a better user experience for upcoming shopping festivals. [ABSTRACT FROM AUTHOR]

Graph-based clustering plays an important role in the clustering area. Recent studies about graph neural networks (GNN) have achieved impressive success on graph-type data. However, in general clustering tasks, the graph structure of data does not exist such that GNN can not be applied to clustering directly and the strategy to construct a graph is crucial for performance. Therefore, how to extend GNN into general clustering tasks is an attractive problem. In this paper, we propose a graph auto-encoder for general data clustering, AdaGAE, which constructs the graph adaptively according to the generative perspective of graphs. The adaptive process is designed to induce the model to exploit the high-level information behind data and utilize the non-euclidean structure sufficiently. Importantly, we find that the simple update of the graph will result in severe degeneration, which can be concluded as better reconstruction means worse update. We provide rigorous analysis theoretically and empirically. Then we further design a novel mechanism to avoid the collapse. Via extending the generative graph models to general type data, a graph auto-encoder with a novel decoder is devised and the weighted graphs can be also applied to GNN. AdaGAE performs well and stably in different scale and type datasets. Besides, it is insensitive to the initialization of parameters and requires no pretraining. [ABSTRACT FROM AUTHOR]

Deep learning models have been shown to be vulnerable to adversarial attacks. Adversarial attacks are imperceptible perturbations added to an image such that the deep learning model misclassifies the image with a high confidence. Existing adversarial defenses validate their performance using only the classification accuracy. However, classification accuracy by itself is not a reliable metric to determine if the resulting image is “adversarial-free”. This is a foundational problem for online image recognition applications where the ground-truth of the incoming image is not known and hence we cannot compute the accuracy of the classifier or validate if the image is “adversarial-free” or not. This paper proposes a novel privacy preserving framework for defending Black box classifiers from adversarial attacks using an ensemble of iterative adversarial image purifiers whose performance is continuously validated in a loop using Bayesian uncertainties. The proposed approach can convert a single-step black box adversarial defense into an iterative defense and proposes three novel privacy preserving Knowledge Distillation (KD) approaches that use prior meta-information from various datasets to mimic the performance of the Black box classifier. Additionally, this paper proves the existence of an optimal distribution for the purified images that can reach a theoretical lower bound, beyond which the image can no longer be purified. Experimental results on six public benchmark datasets namely: 1) Fashion-MNIST, 2) CIFAR-10, 3) GTSRB, 4) MIO-TCD, 5) Tiny-ImageNet, and 6) MS-Celeb show that the proposed approach can consistently detect adversarial examples and purify or reject them against a variety of adversarial attacks. [ABSTRACT FROM AUTHOR]

Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks. In this paper, we give a survey for MTL from the perspective of algorithmic modeling, applications and theoretical analyses. For algorithmic modeling, we give a definition of MTL and then classify different MTL algorithms into five categories, including feature learning approach, low-rank approach, task clustering approach, task relation learning approach and decomposition approach as well as discussing the characteristics of each approach. In order to improve the performance of learning tasks further, MTL can be combined with other learning paradigms including semi-supervised learning, active learning, unsupervised learning, reinforcement learning, multi-view learning and graphical models. When the number of tasks is large or the data dimensionality is high, we review online, parallel and distributed MTL models as well as dimensionality reduction and feature hashing to reveal their computational and storage advantages. Many real-world applications use MTL to boost their performance and we review representative works in this paper. Finally, we present theoretical analyses and discuss several future directions for MTL. [ABSTRACT FROM AUTHOR]

Network embedding has been widely employed in networked data mining applications as it can learn low-dimensional and dense node representations from the high-dimensional and sparse network structure. While most existing network embedding methods only model the proximity between two nodes regardless of the order of the proximity, this paper proposes to explicitly model multi-node proximities which can be widely observed in practice, e.g., multiple researchers coauthor a paper, and multiple genes co-express a protein. Explicitly modeling multi-node proximities is important because some two-node interactions may not come into existence without a third node. By proving that LINE(1st), a recent network embedding method, is equivalent to kernelized matrix factorization, this paper proposes coupled kernelized multi-dimensional array factorization (Cetera) which jointly factorizes multiple multi-dimensional arrays by enforcing a consensus representation for each node. In this way, node representations can be more comprehensive and effective, which is demonstrated on three real-world networks through link prediction and multi-label classification. [ABSTRACT FROM AUTHOR]

This paper presents an asset health index (HI) prediction methodology for high voltage transmission overhead lines (OHLs) using supervised machine learning and structured, unambiguous visual inspections. We propose a framework for asset HI predictions to determine the technical condition of individual OHL towers to improve grid reliability in a cost-effective manner. The paper focuses on asset HI prediction and the selection of the most parsimonious model. Based on the technical specifications and HI data, our methodology allows for the prediction of a HI for OHLs without HI data, and models asset aging behaviour. Technical specifications and the HI as defined in this paper are taken from the Estonian TSO periodical visual inspections implemented in 2018. The case study successfully demonstrates that the proposed methodology can predict tower HI values for a single OHL with nearly 80 percent accuracy without the need for additional measurements. [ABSTRACT FROM AUTHOR]

The Cox proportional hazards model is a popular semi-parametric model for survival analysis. In this paper, we aim at developing a federated algorithm for the Cox proportional hazards model over vertically partitioned data (i.e., data from the same patient are stored at different institutions). We propose a novel algorithm, namely VERTICOX, to obtain the global model parameters in a distributed fashion based on the Alternating Direction Method of Multipliers (ADMM) framework. The proposed model computes intermediary statistics and exchanges them to calculate the global model without collecting individual patient-level data. We demonstrate that our algorithm achieves equivalent accuracy for the estimation of model parameters and statistics to that of its centralized realization. The proposed algorithm converges linearly under the ADMM framework. Its computational complexity and communication costs are polynomially and linearly associated with the number of subjects, respectively. Experimental results show that VERTICOX can achieve accurate model parameter estimation to support federated survival analysis over vertically distributed data by saving bandwidth and avoiding exchange of information about individual patients. The source code for VERTICOX is available at: https://github.com/daiwenrui/VERTICOX. [ABSTRACT FROM AUTHOR]

Chemical mechanical polishing/planarization (CMP) combines physical grinding and chemical reactions to planarize the wafer surface. The complex mechanism of CMP brings great challenges to the mechanism-based modeling process. The data-driven CMP modeling process is limited by insufficient datasets. At the same time, these two types of models generally have high computational complexity. In this paper, we introduce the group method of data handling (GMDH)-type polynomial network to build the CMP model to address the above challenges. We designed and manufactured the test chip using a 28nm process. The measurement data from the test chip shows that compared with the mechanism-based CMP model, the trained CMP model based on GMDH-type polynomial network has higher accuracy and lower computational complexity, with the average simulation speed being 115x faster. Experiments based on silicon data show that this modeling method has a small demand for data, and 20 randomly selected sets of data can meet the needs for modeling the current CMP process. [ABSTRACT FROM AUTHOR]

Many applications of hyperspectral remote sensing involve automatic detection of solid targets. The design and applicability of such systems depend on their detection performance under various deployment scenarios; thus, it is useful to develop an accurate and realistic performance model. In this paper, we present a hyperspectral target detection performance prediction model for the common matched filter and normalized matched filter detection algorithms. A statistical model for hyperspectral data is discussed, which includes a replacement model for target pixels and a finite mixture of $t$ -elliptically contoured distributions for background materials. For this general input model, analytic forms for detector output distributions are not always available. The main contribution of this paper is to develop an efficient and robust performance simulation technique using Monte Carlo (MC) with importance sampling. Compared to standard MC, our simulation technique requires a substantially smaller sample size to obtain accurate performance estimates at low false alarm rates. The proposed technique is useful for predicting detection performance over a wide range of input models when analytic solutions are unavailable. [ABSTRACT FROM AUTHOR]

This paper presents a joint trajectory smoothing and tracking framework for a specific class of targets with smooth motion. We model the target trajectory by a continuous function of time (FoT), which leads to a curve fitting approach that finds a trajectory FoT fitting the sensor data in a sliding time-window. A simulation study is conducted to demonstrate the effectiveness of our approach in tracking a maneuvering target, in comparison with the conventional filters and smoothers. Note to Practitioners—Estimation, such as automatically tracking and predicting the movement of an aircraft, a train, or a bus, plays a key role in our daily life. In this paper, we provide a new approach for the online estimation of the target trajectory function by means of fitting the time-series observation, which accommodates the lack of quantifiable knowledge about the target motion and of the statistical property of the sensor observation noise. The resulting trajectory function can be used to infer either the past or the present state of the target. Engineering-friendly strategies are provided for computationally efficient implementation. The proposed approach is particularly appealing to a broad range of real-world targets that move in smooth courses, such as passenger aircraft and ships. [ABSTRACT FROM AUTHOR]

This paper proposes a novel hybrid model for learning discrete and continuous dynamics of car-following behaviors. Multiple modes representing driving patterns are identified by partitioning the model into groups of states. The model is visualizable and interpretable for car-following behavior recognition, traffic simulation, and human-like cruise control. The experimental results using the next generation simulation datasets demonstrate its superior fitting accuracy over conventional models. [ABSTRACT FROM AUTHOR]

Accurate estimation of short-term traffic flow, which can help to assist travelers make better route choices, is a significant research field of intelligent transportation system. In order to extract complex spatiotemporal features from a small amount of available traffic data, in this paper we propose a novel Deep Graph Gaussian Processes (DGGPs) for short-term traffic flow prediction. First, in order to accurately describe the relationship between vertices in time series, this paper proposes an attention kernel. Based on this, the Aggregation Gaussian Process uses attention kernel as the covariance function, which overcomes the problem that the existing Gaussian processes and the deep Gaussian processes cannot effectively obtain dynamic spatial features. Second, DGGPs are constructed by the Aggregation Gaussian Process (AGP), the Temporal Convolutional Gaussian Process (TCGP) and the Gaussian process with linear kernel, to solve the existing short-term traffic flow forecasting models cannot obtain complex spatiotemporal features from a small amount of available data. We verify that the attention kernel helps to the proposed model convergence on the three data sets. At the same time, the proposed DGGP can obtain spatiotemporal features from the situation with less available spatial information or temporal information, accurately predict short-term traffic flow, and quantify temporal uncertainty. [ABSTRACT FROM AUTHOR]

Modern complexities associated with an arterial traffic makes existing safety prediction methods insufficient to meet desired standards required by recent developmental needs. This paper proposes an enhanced active safety prediction method based on big-data approach and Stacked AutoEncoder-Gated Recurrent Unit. Firstly, the big-data technology is used to construct a dynamic identification model to recognize real-time operation state and risk state. Secondly, the Stacked AutoEncoder-Gated Recurrent Unit is used to predict a level of safety based on associated recognition results. This paper uses data from working days of Sunset Boulevard, California, from January $1^{\mathrm{st}}$ , 2020, to February $28^{\mathrm{th}}$ , 2020. The results of analysis show that the accuracy of the proposed dynamic recognition model reaches 98.92%, which is better than existing models such as random forest, K-nearest neighbor, and naïve Bayes models. In addition, it is found that the Stacked AutoEncoder-Gated Recurrent Unit can achieve a prediction accuracy of 95.157% and has significant advantages in terms of efficiency. The proposed methods will provide feasible solutions for actively monitoring safety levels. [ABSTRACT FROM AUTHOR]

Bridges play an important role in transportation infrastructure systems. Intelligent and digital management of bridges group is an essential part of the future intelligent transportation infrastructure system. This paper proposes a digital twin system for bridges group in the regional transportation infrastructure network, which is interconnected by measured traffic loads. In physical space, a full-bridge traffic load monitoring system based on information fusion of weigh-in-motion (WIM) and multi-source heterogeneous machine vision is set up on the target bridge to measure traffic loads, also lightweight sensors are employed on the bridges group for structural response information. Furthermore, by establishing mechanical analysis models in the corresponding digital space and using the measured traffic loads as links, the working condition perception and safety warning of all bridges in the regional transportation network is achieved, forming an important support for further intelligent transportation infrastructure system. The proposed digital twin system has been preliminarily implemented in a bridges group around Shanghai, China, demonstrating the feasibility of the technical framework proposed in this paper and the bright prospects. [ABSTRACT FROM AUTHOR]

This paper presents a dynamic event data-based stability risk assessment method for power grids with high penetrations of inverter-based resources (IBRs). This method relies on obtaining the IBRs’ DQ admittance through dynamic event data and computing the system’s eigenvalues based on the admittance models. Two critical technologies are employed in this research, including time-domain and frequency-domain data fitting and $dq$ -frame voltage and current signal derivation. The first technology is key to obtaining the $s$ -domain expressions from the transient response data, and the $s$ -domain DQ admittance model from the frequency-domain measurements. The second technology is key to obtaining the $dq$ -frame voltage and current signals from either the three-phase instantaneous measurements or the phasor measurement unit (PMU) data. The method is illustrated using data generated from a Type-4 wind power plant modeled in PSCAD. This paper demonstrates the technical feasibility of the proposed approach. [ABSTRACT FROM AUTHOR]

Drug-induced liver injury describes the adverse effects of drugs that damage the liver. Life-threatening results were also reported in severe cases. Therefore, liver toxicity is an important assessment for new drug candidates. These reports are documented in research papers that contain preliminary in vitro and in vivo experiments. Conventionally, data extraction from publications relies on resource-demanding manual labeling, which restricts the efficiency of the information extraction. The development of natural language processing techniques enables the automatic processing of biomedical texts. Herein, based on around 28,000 papers (titles and abstracts) provided by the Critical Assessment of Massive Data Analysis challenge, this study benchmarked model performances on filtering liver-damage-related literature. Among five text embedding techniques, the model using term frequency-inverse document frequency (TF-IDF) and logistic regression outperformed others with an accuracy of 0.957 on the validation set. Furthermore, an ensemble model with similar overall performances was developed with a logistic regression model on the predicted probability given by separate models with different vectorization techniques. The ensemble model achieved a high accuracy of 0.954 and an F1 score of 0.955 in the hold-out validation data in the challenge. Moreover, important words in positive/negative predictions were identified via model interpretation. The prediction reliability was quantified with conformal prediction, which provides users with a control over the prediction uncertainty. Overall, the ensemble model and TF-IDF model reached satisfactory classification results, which can be used by researchers to rapidly filter literature that describes events related to liver injury induced by medications. [ABSTRACT FROM AUTHOR]

Landing is generally cited as one of the riskiest phases of a flight, as indicated by the much higher accident rate than other flight phases. In this paper, we focus on the hard landing problem (which is defined as the touchdown vertical speed exceeding a predefined threshold), and build a probabilistic predictive model to forecast the aircraft’s vertical speed at touchdown, using DASHlink data. Previous work has treated hard landing as a classification problem, where the vertical speed is represented as a categorical variable based on a predefined threshold. In this paper, we build a machine learning model to numerically predict the touchdown vertical speed during aircraft landing. Probabilistic forecasting is used to quantify the uncertainty in model prediction, which in turn supports risk-informed decision-making. A Bayesian neural network approach is leveraged to construct the predictive model. The overall methodology consists of five steps. First, a clustering method based on the minimum separation between different airports is developed to identify flights in the dataset that landed at the same airport. Secondly, identifying the touchdown point itself is not straightforward; in this paper, it is determined by comparing the vertical speed distributions derived from different candidate touchdown indicators. Thirdly, a forward and backward filtering (filtfilt) approach is used to smooth the data without introducing phase lag. Next, a minimal-redundancy-maximal-relevance (mRMR) analysis is used to reduce the dimensionality of input variables. Finally, a Bayesian recurrent neural network is trained to predict the touchdown vertical speed and quantify the uncertainty in the prediction. The model is validated using several flights in the test dataset, and computational results demonstrate the satisfactory performance of the proposed approach. [ABSTRACT FROM AUTHOR]

To accurately pour drinks into various containers is an essential skill for service robots. However, drink pouring is a dynamic process and difficult to model. Traditional deep imitation learning techniques for implementing autonomous robotic pouring have an inherent black-box effect and require a large amount of demonstration data for model training. To address these issues, an Explainable Hierarchical Imitation Learning (EHIL) method is proposed in this paper such that a robot can learn high-level general knowledge and execute low-level actions across multiple drink pouring scenarios. Moreover, with the EHIL method, a logical graph can be constructed for task execution, through which the decision-making process for action generation can be made explainable to users and the causes of failure can be traced out. Based on the logical graph, the framework is manipulable to achieve different targets while the adaptability to unseen scenarios can be achieved in an explainable manner. A series of experiments have been conducted to verify the effectiveness of the proposed method. Results indicate that EHIL outperforms the traditional behavior cloning method in terms of success rate, adaptability, manipulability, and explainability. Note to Practitioners—Pouring liquids is a common activity in people’s daily lives and all wet-lab industries. Drink pouring dynamic control is difficult to model, while the accurate perception of flow is challenging. To enable the robot to learn under unknown dynamics via observing the human demonstration, deep imitation learning can be used. To address the limitations of traditional deep neural networks, an Explainable Hierarchical Imitation Learning (EHIL) method is proposed in this paper. The proposed method enables the robot to learn a sequence of reasonable pouring phases for performing the task rather than simply execute the task via traditional behavior cloning. In this way, explainability and safety can be ensured. Manipulability can be achieved by reconstructing the logical graph. The target of this research is to obtain pouring dynamics via the learning method and realize the precise and quick pouring of drink from the source containers to various targeted containers with reliable performance, adaptability, manipulability, and explainability. [ABSTRACT FROM AUTHOR]

Random traffic flow load (TFL) simulation is an important analysis method for bridge design and safety assessment, and accurate TFL modelling is a prerequisite for high-quality simulation. The existing TFL modelling methods almost all rely on the load data monitored by the weigh-in-motion system (WIM system). However, the WIM system has natural defects such as unsatisfactory measurement accuracy at low speed and the inability to measure vehicle lengths and transverse positions in the lane, limiting the improvement of TFL simulation accuracy. Regarding this, a TFL monitoring system that integrates the functions of machine vision and WIM system is developed in this paper. In this system, a deep learning method is applied, for the accurate detection of vehicles and wheels in the video, and the extraction of key parameters for TFL modelling based on detection results. According to the long-term monitoring value, statistical distributions of key parameters are determined, and then an intelligent TFL model is derived from the Intelligent Driver Model (IDM), considering the car-following behavior of vehicles. Correspondingly, this paper further suggests a TFL simulation method and achieves an accurate TFL simulation. A cable-stayed bridge is taken as an example to verify the feasibility of the method. The results show that, compared to the modelling and simulation methods that only rely on the WIM system, the proposed method not only reduces the measurement error of vehicle dimensions by nearly 4 times, but also performs higher resolution in time measurement. The proposed method effectively overcomes the shortcomings of existing schemes and has good application potential in engineering. [ABSTRACT FROM AUTHOR]

This report analyzes the reproducibility of the article “Computing Planetary Interior Normal Modes with A Highly Parallel Polynomial Filtering Eigensolver” by Jia Shi et al. (Shi, 2018). To reproduce the results we perform different weak and strong scaling studies using a series of Mars models. All experimental runs were performed during the SC19 Student Cluster Competition on a four node Intel Skylake cluster. We show that the findings of the original article can be reproduced in a different environment. [ABSTRACT FROM AUTHOR]

The integration of global navigation satellite system (GNSS) and inertial navigation system (INS) has been widely studied in the past decades. The traditional Kalman filtering method, a procedure that leads to historical states and observations loss, can estimate fast by limiting the update to the latest state. Furthermore, the performance of loosely coupled GNSS/INS navigation integration depends largely on environmental conditions and sensor costs. In cities, GNSS signals may be interrupted due to the influence of obstructions and moving objects, which leads to the discontinuity of GNSS/INS navigation. Therefore, in order to overcome these difficulties an auto regressive integrated moving average (ARIMA) auxiliary model based on time sequence is proposed in this paper, which makes use of the data before interruption to predict the GNSS measurements during the interruption period and makes up for the data gap. In addition, the INS and GNSS measurements are loosely coupled using the most advanced factor graph model. Compared to the filtering algorithm, all previous measurements are used for state estimation through the factor graph framework. In this paper, the experiment is based on the dataset of Tokyo which is a typical challenging city canyon. Experiments showed that, compared with the traditional GNSS/INS integration method, the proposed method can provide a higher precision and a series of continuous navigation results even when the GNSS measurement data was interrupted. [ABSTRACT FROM AUTHOR]

With low voltage (LV) distribution networks increasingly being re-purposed beyond their original design specifications to accommodate low carbon technologies, the ability to accurately calculate their actual spare capacity is critical. Traditionally, within the Great Britain (GB) power system, there has been limited monitoring of LV distribution networks, making this difficult. This paper proposes a method for estimating spare capacity of unmonitored LV networks using demand data from customer Smart Meters. In particular, the proposed method infers existing LV network capacity, as well as losses, across scenarios where only a limited number of customers have Smart Meters installed. Typical daily load profiles across customers with Smart Meters are learned using a Dirichlet sampled Gaussian mixture model (GMM). Learned profiles are then applied to all unmetered customers to estimate network parameters. Method accuracy is assessed by comparing estimations with simulated, fully observed, LV network models. The method is also compared to benchmark models for establishing unobserved demand profiles. Overall, results in the paper show that the proposed method outperforms benchmark models in terms of accurately assessing substation headroom, particularly in scenarios where only 10–50% of customers have Smart Meters installed. [ABSTRACT FROM AUTHOR]

The paper presents a theoretical result that clarifies when it is at all possible to determine the nonlinear dynamic equations of a biological system in stable oscillation, from measured data. As it turns out the minimal order needed for this is dependent on the minimal dimension in which the stable orbit of the system does not intersect itself. This is illustrated with a simulated fourth order Hodgkin-Huxley spiking neuron model, which is identified using a non-linear second order differential equation model. The simulated result illustrates that the underlying higher order model of the spiking neuron cannot be uniquely determined given only the periodic measured data. The result of the paper is of general validity when the dynamics of biological systems in stable oscillation is identified, and illustrates the need to carefully address non-linear identifiability aspects when validating models based on periodic data. [ABSTRACT FROM PUBLISHER]

Data quality plays an important role during the training stage of machine/deep learning models. The annotation hinges on the experiences of domain experts. To acquire the expert’s knowledge in the context of machine learning, manual data labeling, a tedious and time-consuming task in supervised learning, should be given a top priority. However, the domain experts in the line of plentiful manual annotation may easily get distracted or fatigued after long-time work, causing judgment errors, mislabeling, etc. The pattern recognition of wafer defect map is investigated in this paper, the primary goal of which is to train the convolutional neural network (CNN) model through a very limited number of manually labeled data so that the trained model is capable of performing pseudo labeling. Subsequently, a self-assured adaptive ensemble learner in terms of a series of shallow neural networks is proposed to filter wafer map samples with untrusted pseudo-labels. In the result, the amount of human annotations is significantly reduced by 61% for training a highly accurate classifier. A minimum number of manually labeled data is suggested while the equally high classification performance of wafer defect pattern is maintained. For the evaluation purpose, the proposed self-assured learning is compared with the confidence learning. [ABSTRACT FROM AUTHOR]

Federated learning (FL) models are vulnerable to membership inference attacks (MIAs), and the requirement of individual privacy motivates the protection of subjects where the individual data is distributed across multiple users in the cross-silo FL setting. In this paper, we propose a subject-level membership inference attack based on data augmentation and model discrepancy. It can effectively infer whether the data distribution of the target subject has been sampled and used for training by specific federated users, even if other users (also) may sample from the same subject and use it as part of their training set. Specifically, the adversary uses a generative adversarial network (GAN) to perform data augmentation on a small amount of priori federation-associated information known in advance. Subsequently, the adversary merges two different outputs from the global and tested user models using an optimal feature construction method. We simulate a controlled federation configuration and conduct extensive experiments on real datasets that include both image and categorical data. Results show that the area under the curve (AUC) is improved by 12.6% to 16.8% compared to the classical membership inference attack. This is at the expense of the test accuracy of the data augmented with GAN, which is at most 3.5% lower than the real test data. We also explore the degree of privacy leakage between overfitted models and well-generalized models in the cross-silo FL setting and conclude experimentally that the former is more likely to leak individual privacy with a subject-level degradation rate of up to 0.43. Finally, we present two possible defense mechanisms to attenuate this newly discovered privacy risk. [ABSTRACT FROM AUTHOR]

The paper is devoted to the problem of erasure coding in distributed storage. We consider a model of storage that assumes that nodes are organized into equally sized groups, called racks, that within each group the nodes can communicate freely without taxing the system bandwidth, and that the only information transmission that counts is the one between the racks. This assumption implies that the nodes within each of the racks can collaborate before providing information to the failed node. The main emphasis of the paper is on code construction for this storage model. We present an explicit family of maximum distance separable (MDS) array codes that support recovery of a single failed node from any number of helper racks using the minimum possible amount of inter-rack communication(such codes are said to provide optimal repair). The codes are constructed over finite fields of size comparable to the code length. We also derive a bound on the number of symbols accessed at helper nodes for the purposes of repair, and construct a code family that approaches this bound, while still maintaining the optimal repair property. Finally, we present a construction of scalar Reed-Solomon codes that support optimal repair for the rack-oriented storage model. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs), including convolutional neural networks (CNNs) and residual networks (ResNets) models, are able to learn abstract representations from the input data by considering a deep hierarchy of layers that perform advanced feature extraction. The combination of these models with visual attention techniques can assist with the identification of the most representative parts of the data from a visual standpoint, obtained through more detailed filtering of the features extracted by the operational layers of the network. This is of significant interest for analyzing remotely sensed hyperspectral images (HSIs), characterized by their very high spectral dimensionality. However, few efforts have been conducted in the literature in order to adapt visual attention methods to remotely sensed HSI data analysis. In this paper, we introduce a new visual attention-driven technique for the HSI classification. Specifically, we incorporate attention mechanisms to a ResNet in order to better characterize the spectral–spatial information contained in the data. Our newly proposed method calculates a mask that is applied to the features obtained by the network in order to identify the most desirable ones for classification purposes. Our experiments, conducted using four widely used HSI data sets, reveal that the proposed deep attention model provides competitive advantages in terms of classification accuracy when compared to other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Lithography simulation is one of the key steps in physical verification, enabled by the substantial optical and resist models. A resist model bridges the aerial image simulation to printed patterns. While the effectiveness of learning-based solutions for resist modeling has been demonstrated, they are considerably data-demanding. Meanwhile, a set of manufactured data for a specific lithography configuration is only valid for the training of one single model, indicating low data efficiency. Due to the complexity of the manufacturing process, obtaining enough data for acceptable accuracy becomes very expensive in terms of both time and cost, especially during the evolution of technology generations when the design space is intensively explored. In this paper, we propose a new resist modeling framework for contact layers, utilizing existing data from old technology nodes and active selection of data in a target technology node, to reduce the amount of data required from the target lithography configuration. Our framework based on transfer learning and active learning techniques is effective within a competitive range of accuracy, i.e., $3 \times -10 \times $ reduction on the amount of training data with comparable accuracy to the state-of-the-art learning approach. [ABSTRACT FROM AUTHOR]

Decision support is a vital function in electronic commerce (e-commerce). The purpose of this paper is to construct a review-based decision support model for items comparison in e-commerce. The proposed model uses probability multivalued neutrosophic linguistic numbers (PMVNLNs) to characterize online reviews. It overcomes the limitation of existing models by considering neutral information and hesitancy in text reviews. The fuzzy characterization of reviews (i.e., PMVNLN) can reflect similarities and differences in positive (negative) information. In addition, the model considers consumers’ bounded rational behaviors by combining the regret theory with an outranking method. We empirically compare the proposed model with models in http://PConline.com and four existing models with data from http://PConline.com. The performance of these models in terms of accuracy is measured by the total relative difference metric. Results indicate the good performance of the proposed model. Our model is a promising option for e-commerce to provide consumers with good decision support service. [ABSTRACT FROM AUTHOR]

A new approach to evaluate personalized energy consumption is presented in this paper. The method consists of identifying driver–vehicle dynamics using the probability weighted autoregressive model, which is one of the multi-mode ARX models, and then of reproducing the driver–vehicle behavior in a vehicle-following task. The energy consumption of the vehicle is estimated from the velocity profile calculated by using the driver–vehicle model. In this paper, driving simulator and real-world driving data were recorded to identify the driver–vehicle model in various situations. As a result, real-world energy consumption could be reproduced in a variety of situations with an average error of 1.9% and a standard deviation within 1.5%. Several promising applications of the energy consumption evaluation are introduced in this paper, such as an online energy consumption prediction, a powertrain choice-assistance system for car buyers, and a solution to estimate the macroscopic energy consumption of aggregated vehicles in a traffic flow. [ABSTRACT FROM PUBLISHER]

This paper considers turbo equalization for 2-D magnetic recording. Magnetic grains are modeled as Voronoi regions of randomly distributed nuclei. Bits read from the magnetic grain model flow into a 2-D intersymbol interference (2D-ISI) model including additive white Gaussian noise. At high bit densities, some bits are not written on any grain, and hence are effectively “overwritten” by surrounding bits. The proposed system iteratively exchanges log-likelihood ratios (LLRs) between a 2D-ISI equalizer based on the forward-backward algorithm and an irregular repeat-accumulate (IRA) decoder. To combat bit overwrites, the system employs a non-linear function to map 2D-ISI extrinsic output LLRs to IRA decoder input LLRs. To pass back LLRs from the IRA decoder to the 2D-ISI equalizer, we design a simple likelihood-ratio-based LLR estimator. Simulations of the proposed system that employ the perturbed-bit-centers grain model proposed in a 2010 IEEE Transactions on Magnetics paper show a 6.5% increase in user bits per grain (U/G) and a 16.4 dB signal-to-noise ratio (SNR) gain compared with the previous paper, without iterative turbo equalization. Utilizing the LLR estimator to do iterative detection results in SNR gains of up to 1.7 dB compared with non-iterative detection. The random Voronoi model employed in this paper appears to be more difficult to equalize than the grain model in the 2010 paper. The proposed system with random Voronoi model achieves 0.4422 U/G at \mathrm SNR=11.6 dB, i.e., about 8.8 Tb/in2 at (typically assumed future grain density) 20 Tgr/in2; this is almost ten times the density of current systems at 10 Tgr/in2. [ABSTRACT FROM PUBLISHER]

In-home health monitoring has attracted great attention for the ageing population worldwide. With the abundant user health data accessed by Internet of Things (IoT) devices and recent development in machine learning, smart healthcare has seen many successful stories. However, existing approaches for in-home health monitoring do not pay sufficient attention to user data privacy and thus are far from being ready for large-scale practical deployment. In this paper, we propose FedHome, a novel cloud-edge based federated learning framework for in-home health monitoring, which learns a shared global model in the cloud from multiple homes at the network edges and achieves data privacy protection by keeping user data locally. To cope with the imbalanced and non-IID distribution inherent in user’s monitoring data, we design a generative convolutional autoencoder (GCAE), which aims to achieve accurate and personalized health monitoring by refining the model with a generated class-balanced dataset from user’s personal data. Besides, GCAE is lightweight to transfer between the cloud and edges, which is useful to reduce the communication cost of federated learning in FedHome. Extensive experiments based on realistic human activity recognition data traces corroborate that FedHome significantly outperforms existing widely-adopted methods. [ABSTRACT FROM AUTHOR]

This paper studies instance-dependent Positive and Unlabeled (PU) classification, where whether a positive example will be labeled (indicated by $s$ s ) is not only related to the class label $y$ y , but also depends on the observation $\mathbf {x}$ x . Therefore, the labeling probability on positive examples is not uniform as previous works assumed, but is biased to some simple or critical data points. To depict the above dependency relationship, a graphical model is built in this paper which further leads to a maximization problem on the induced likelihood function regarding $P(s,y|\mathbf {x})$ P (s , y | x) . By utilizing the well-known EM and Adam optimization techniques, the labeling probability of any positive example $P(s=1|y=1,\mathbf {x})$ P (s = 1 | y = 1 , x) as well as the classifier induced by $P(y|\mathbf {x})$ P (y | x) can be acquired. Theoretically, we prove that the critical solution always exists, and is locally unique for linear model if some sufficient conditions are met. Moreover, we upper bound the generalization error for both linear logistic and non-linear network instantiations of our algorithm, with the convergence rate of expected risk to empirical risk as $\mathcal {O}(1/\sqrt{k}+1/\sqrt{n-k}+1/\sqrt{n})$ O (1 / k + 1 / n - k + 1 / n) ($k$ k and $n$ n are the sizes of positive set and the entire training set, respectively). Empirically, we compare our method with state-of-the-art instance-independent and instance-dependent PU algorithms on a wide range of synthetic, benchmark and real-world datasets, and the experimental results firmly demonstrate the advantage of the proposed method over the existing PU approaches. [ABSTRACT FROM AUTHOR]

This paper presents a command governor (CG) based adaptive cruise controller (ACC) that is applied in simulation to normal driving scenarios and emergency stopping scenarios. The vehicle-following case study used in this paper involves a heavy-duty ego vehicle and a light-duty non-connected lead vehicle (i.e., the ego vehicle does not communicate with the lead vehicle and can only infer the lead vehicles’ position and velocity states through its own sensors). Typically, to ensure constraints in the presence of disturbances, receding horizon based ACCs will assume some known worst-case behavior of the lead vehicle. In the presence of a stochastic, non-connected lead vehicle, however, achieving such a guarantee requires a worst-case assumption on the behavior of the lead vehicle for all future time. In this work, the CG assumes a lead vehicle velocity profile that will be achieved with a prescribed level of certainty, based on a stochastic characterization of lead vehicle behavior that has been informed by actual on-road data. The CG ensures safe following distance under this probabilistic lead vehicle assumption. Here, “safe following distance” is based on the ego vehicle’s ability to come to a stop without collision if the lead vehicle were to suddenly brake at maximum deceleration after proceeding at a velocity profile that is prescribed based on a statistical lower bound on lead vehicle velocity. Ultimately, the CG ensures that the worst-case safe following distance is satisfied with a prescribed probability, thereby paralleling chance-constrained CG formulations. Simulation results for a heavy-duty truck indicate that the CG-based ACC outperforms a PID-ACC in terms of fuel economy and drivability. Additionally, the CG-ACC approach was able to ensure rear-end collision avoidance in emergency stopping simulations. [ABSTRACT FROM AUTHOR]

Traffic state estimation (TSE) bifurcates into two main categories, model-driven and data-driven (e.g., machine learning, ML) approaches, while each suffers from either deficient physics or small data. To mitigate these limitations, recent studies introduced hybrid methods, such as physics-informed deep learning (PIDL), which contains both model-driven and data-driven components. This paper contributes an improved paradigm, called physics-informed deep learning with a fundamental diagram learner (PIDL + FDL), which integrates ML terms into the model-driven component to learn a functional form of a fundamental diagram (FD), i.e., a mapping from traffic density to flow or velocity. The proposed PIDL + FDL has the advantages of performing the TSE learning, model parameter identification, and FD estimation simultaneously. This paper focuses on highway TSE with observed data from loop detectors, using traffic density or velocity as traffic variables. We demonstrate the use of PIDL + FDL to solve popular first-order and second-order traffic flow models and reconstruct the FD relation as well as model parameters that are outside the FD term. We then evaluate the PIDL + FDL-based TSE using the Next Generation SIMulation (NGSIM) dataset. The experimental results show the superiority of the PIDL + FDL in terms of improved estimation accuracy and data efficiency over advanced baseline TSE methods, and additionally, the capacity to properly learn the unknown underlying FD relation. [ABSTRACT FROM AUTHOR]