Search

Diagnostic theories are fundamental to information system (IS) practice and are represented as trees. While there are approaches for validating diagnostic trees, these validate the overall performance of the tree rather than identifying ways incorrect diagnoses can occur. It is important to fully validate diagnostic trees because even if the tree gives the correct decision “most of the time,” it is possible for incorrect decisions traveling down little-used branches of the tree to result in catastrophic decisions. In this article, we describe the process of using a variant of q-sorting to validate diagnostic trees. In this methodology, diagnostic trees that independent experts develop are transformed into a quantitative form, and that quantitative form is tested to determine the inter-rater reliability of the individual branches in the tree. The trees are then successively transformed to incrementally test if they branch in the same way. The results help researchers not only identify quality items for use in a diagnostic tree but also facilitate diagnoses of problems with those items and facilitate the reconciliation of discrepant trees by experts. The methodology validates not only the whole tree but also its subparts.

Providing a structured approach for complex product development (PD) is a challenging issue that necessitates utilizing sophisticated modeling tools and analysis techniques. One effective approach for optimizing the complex engineering system development is the cross application of modularization and sequencing analyses on the design structure matrix (DSM), which leads to a cost-effective and time-efficient PD process. In this regard, the current study presents an application-specific method for the simultaneous implementation of modularization and sequencing analyses on DSMs to find the most independent and excluded modules with the minimum feedback loops among them. To this end, we first formulate the total feedback length among the modules by introducing two new modules’ feedback criteria. Second, we propose a novel objective function combining these feedback criteria with the modularity index metric to simultaneously fulfill the sequencing and modularization goals. This objective function makes the proposed method application specific in the sense that the expert is able to adjust the importance weight of each criterion based on the project's characteristics. Third, an efficient metaheuristic algorithm named discrete particle swarm optimization simulated annealing (DPSOSA) is developed to find the optimal solution by minimizing the introduced objective function. Eventually, to evaluate the DPSOSA performance in different applications, we conduct comprehensive experiments on a total of 21 well-known real-world DSMs. The obtained results demonstrate the superiority of the proposed method over previous approaches proving its effectiveness in each of modularization, sequencing, and modularization-sequencing experiments.

Various strategies, including controls of morphology, oxidation state, defect, and doping, have been developed to improve the performance of Cu-based catalysts for CO2 reduction reaction (CO2RR), generating a large amount of data. However, a unified understanding of underlying mechanism for further optimization is still lacking. In this work, combining first-principles calculations and machine learning (ML) techniques, we elucidate critical factors influencing the catalytic properties, taking Cu-based single atom alloys (SAAs) as examples. Our method relies on high-throughput calculations of 2669 CO adsorption configurations on 43 types of Cu-based SAAs with various surfaces. Extensive ML analyses reveal that low generalized coordination numbers and valence electron number are key features to determine catalytic performance. Applying our ML model with cross-group learning scheme, we demonstrate the model generalizes well between Cu-based SAAs with different alloying elements. Further, electronic structure calculations suggest surface - negative center could enhance CO adsorption by back donating electrons to antibonding orbitals of CO. Finally, several SAAs, including PCu, AgCu, GaCu, ZnCu, SnCu, GeCu, InCu, and SiCu, are identified as promising CO2RR catalysts. Our work provides a paradigm for the rational design and fast screening of SAAs for various electrocatalytic reactions.

In this work, we consider transferring the structure information from large networks to compact ones for dense prediction tasks in computer vision. Previous knowledge distillation strategies used for dense prediction tasks often directly borrow the distillation scheme for image classification and perform knowledge distillation for each pixel separately, leading to sub-optimal performance. Here we propose to distill structured knowledge from large networks to compact networks, taking into account the fact that dense prediction is a structured prediction problem. Specifically, we study two structured distillation schemes: i) pair-wise distillation that distills the pair-wise similarities by building a static graph; and ii) holistic distillation that uses adversarial training to distill holistic knowledge. The effectiveness of our knowledge distillation approaches is demonstrated by experiments on three dense prediction tasks: semantic segmentation, depth estimation and object detection. Code is available at: https://git.io/StructKD, Comment: v1:10 pages cvpr2019 accepted; v2:15 pages for a journal version; Code is available at: https://github.com/irfanICMLL/structure_knowledge_distillation; fix typos

Roughly four decades ago, Taher ElGamal put forward what is today one of the most widely known and best understood public key encryption schemes. ElGamal encryption has been used in many different contexts, chiefly among them by the OpenPGP email encryption standard. Despite its simplicity, or perhaps because of it, in reality there is a large degree of ambiguity on several key aspects of the cipher. Each library in the OpenPGP ecosystem seems to have implemented a slightly different "flavor" of ElGamal encryption. While-taken in isolation-each implementation may be secure, we reveal that in the interoperable world of OpenPGP, unforeseen cross-configuration attacks become possible. Concretely, we propose different such attacks and show their practical efficacy by recovering plaintexts and even secret keys.

The performance of a convolutional neural network (CNN) heavily depends on its hyperparameters. However, finding a suitable hyperparameters configuration is difficult, challenging, and computationally expensive due to three issues, which are 1) the mixed-variable problem of different types of hyperparameters; 2) the large-scale search space of finding optimal hyperparameters; and 3) the expensive computational cost for evaluating candidate hyperparameters configuration. Therefore, this article focuses on these three issues and proposes a novel estimation of distribution algorithm (EDA) for efficient hyperparameters optimization, with three major contributions in the algorithm design. First, a hybrid-model EDA is proposed to efficiently deal with the mixed-variable difficulty. The proposed algorithm uses a mixed-variable encoding scheme to encode the mixed-variable hyperparameters and adopts an adaptive hybrid-model learning (AHL) strategy to efficiently optimize the mixed-variables. Second, an orthogonal initialization (OI) strategy is proposed to efficiently deal with the challenge of large-scale search space. Third, a surrogate-assisted multi-level evaluation (SME) method is proposed to reduce the expensive computational cost. Based on the above, the proposed algorithm is named surrogate-assisted hybrid-model EDA (SHEDA). For experimental studies, the proposed SHEDA is verified on widely used classification benchmark problems, and is compared with various state-of-the-art methods. Moreover, a case study on aortic dissection (AD) diagnosis is carried out to evaluate its performance. Experimental results show that the proposed SHEDA is very effective and efficient for hyperparameters optimization, which can find a satisfactory hyperparameters configuration for the CIFAR10, CIFAR100, and AD diagnosis with only 0.58, 0.97, and 1.18 GPU days, respectively.

Modern consumer electronics included consumer robots, which are made by heterogeneous Internet of Things, and Internet of robotics things are integral members of the Internet of Everything (IoE . IoE plays an incumbent role in smart cities and generates big data. Moreover, smart city IoE maintains various levels of security provisions. However, those are still vulnerable to security and privacy breaches. Nonetheless, mobility increases the risk of security and privacy breaches. As a result, in the internet era, providing seamless security and privacy for inter and intra communication of heterogeneous things is a significant challenge. Furthermore, blockchain is one of the established communication techniques that ensure both security and privacy. On the other hand, blockchain inherits trivial constraints with respect to scalability, latency, and interoperability. Cross-chain is a blockchain concept that aims to alleviate the aforementioned concerns. Therefore, we proposed a multifactor aware (privacy, security, interoperability, and scalability model-driven reference architecture for the Internet of cross-chains, also known as cross-chain as a service platform.

Numerical weather prediction (NWP) data possess internal inaccuracies, such as low NWP wind speed corresponding to high actual wind power generation. This study is intended to reduce the negative effects of such inaccuracies by proposing a pure data-selection framework (PDF) to choose useful data prior to modeling, thus improving the accuracy of day-ahead wind power forecasting. Briefly, we convert an entire NWP training dataset into many small subsets and then select the best subset combination via a validation set to build a forecasting model. Although a small subset can increase selection flexibility, it can also produce billions of subset combinations, resulting in computational issues. To address this problem, we incorporated metamodeling and optimization steps into PDF. We then proposed a design and analysis of the computer experiments-based metamodeling algorithm and heuristic-exhaustive search optimization algorithm, respectively.Experimental results demonstrate that (1) it is necessary to select data before constructing a forecasting model; (2) using a smaller subset will likely increase selection flexibility, leading to a more accurate forecasting model; (3) PDF can generate a better training dataset than similarity-based data selection methods (e.g., K-means and support vector classification); and (4) choosing data before building a forecasting model produces a more accurate forecasting model compared with using a machine learning method to construct a model directly.

With the application of wireless sensor network (WSN) in healthcare field, online sharing of medical data has attracted more and more attention. However, wearable sensor nodes in WSN are limited in energy, storage space and data processing capacity, which largely restricts their deployment in resource demand application scenarios. Fortunately, cloud storage services can enrich the capabilities of wearable sensors and provide an effective method for people to share data within a group. However, as medical data directly relates to patients' health and privacy information, ensuring the integrity and privacy of medical records stored in cloud servers becomes a key issue to be urgently solved. Many public data auditing schemes have been put forward to address the above issues. Unfortunately, most of them have security vulnerabilities or poor functionality and performance. In this paper, we come up with a secure and efficient certificateless public auditing scheme for cloud-assisted medical WSNs, which not only supports dynamic data sharing and privacy protection, but also achieves efficient group user revocation. Security analysis and performance evaluation demonstrate that our scheme significantly reduce the total computation cost while achieving a higher security level. Compared with other related schemes, our new proposal is more suitable for group user data sharing in cloud-assisted medical WSNs.

The imbalanced issue among data is common in many machine-learning applications, where samples from one or more classes are rare. To address this issue, many imbalanced machine-learning methods have been proposed. Most of these methods rely on cost-sensitive learning. However, we note that it is infeasible to determine the precise cost values even with great domain knowledge for those cost-sensitive machine-learning methods. So in this method, due to the superiority of F-measure on evaluating the performance of imbalanced data classification, we employ F-measure to calculate the cost information and propose a cost-sensitive hypergraph learning method with F-measure optimization to solve the imbalanced issue. In this method, we employ the hypergraph structure to explore the high-order relationships among the imbalanced data. Based on the constructed hypergraph structure, we optimize the cost value with F-measure and further conduct cost-sensitive hypergraph learning with the optimized cost information. The comprehensive experiments validate the effectiveness of the proposed method.

Mid-term load forecasting (MTLF) is of great significance for power system planning, operation, and power trading. However, the mid-term electrical load is affected by the coupling of multiple factors and demonstrates complex characteristics, which leads to low prediction accuracy in MTLF. Furthermore, MTLF is faced with the ``curse of dimensionality'' problem due to a large number of variables. This article proposes an MTLF method based on manifold learning, which can extract the underlying factors of load variations to help improve the accuracy of MTLF and significantly reduce the calculation. Unlike linear dimensionality reduction methods, manifold learning has better nonlinear feature extraction ability and is more suitable for load data with nonlinear characteristics. Furthermore, long short-term memory (LSTM) neural networks are used to establish forecasting models in the low-dimensional space obtained by manifold learning. The proposed MTLF method is tested on independent system operator (ISO) New England datasets, and load forecasting in 24, 168, and 720 h ahead is carried out. The numerical results validate that the proposed method has higher prediction accuracy than many mature methods in the mid-term time scale.

Scene parsing, or semantic segmentation, aims at labeling all pixels in an image with the predefined categories of things and stuff. Learning a robust representation for each pixel is crucial for this task. Existing state-of-the-art (SOTA) algorithms employ deep neural networks to learn (discover) the representations needed for parsing from raw data. Nevertheless, these networks discover desired features or representations only from the given image (content), ignoring more generic knowledge contained in the dataset. To overcome this deficiency, we make the first attempt to explore the meaningful supportive knowledge, including general visual concepts (i.e., the generic representations for objects and stuff) and their relations from the whole dataset to enhance the underlying representations of a specific scene for better scene parsing. Specifically, we propose a novel supportive knowledge mining module (SKMM) and a knowledge augmentation operator (KAO), which can be easily plugged into modern scene parsing networks. By taking image-specific content and dataset-level supportive knowledge into full consideration, the resulting model, called knowledge augmented neural network (KANN), can better understand the given scene and provide greater representational power. Experiments are conducted on three challenging scene parsing and semantic segmentation datasets: Cityscapes, Pascal-Context, and ADE20K. The results show that our KANN is effective and achieves better results than all existing SOTA methods.

In the present work a systemat¬ic study give an overview of new findings in the field of biocidal activities for copper (II) sesame soap complex with urea ligand. The aim of this research work is to present fundamental chemical properties and new investigations of coordination compounds of some transition metal ions with an overview of medicinal applications. Transition metals appear in almost every facet of our day-to-day life, from industrial uses such as the manufacture of construction and building materials, tools, vehicles, up to cosmetics, paints and fertilizers. Their reactions are in general important in many technical processes such as catalysis, material synthesis, photochemistry, as well as, in biology and medicine. The present work deals with the study of synthesis and characterization of biological properties of novel copper (II) soap urea complex.

El objetivo de este trabajo consistió en el estudio de la QoS (por sus siglas en inglés) y la QoE (por sus siglas en inglés) de API (por sus siglas en inglés) de servicios web consumidos por aplicaciones mash-up móvil. El estudio se enfoca en recolectar y analizar indicadores de QoS y de QoE. La metodología usada para el desarrollo de este trabajo es experimental, puesto que se ha realizado una experiencia que permitió recolectar los datos del estudio. Para tal fin, se desarrolló un mash-up móvil que consume tres API REST (por sus siglas en inglés) y una librería que permite recolectar indicadores de QoS y de QoE. El estudio se realizó durante 60 días y se recolectaron 1.012 valores de indicadores. Los resultados obtenidos prueban que realizar un análisis parcial de QoS y de QoE que consideren indicadores de manera aislada puede llevar a conclusiones inexactas, por lo que se debe realizar un análisis y evaluación más integral, en atención a la mayor cantidad de factores que afectan la QoS y la QoE.

The proliferation of location-aware social networks (LSNs) has facilitated the research of user mobility modeling and check-in prediction, thereby benefiting various downstream applications such as precision marketing and urban management. Most of the existing studies only focus on predicting the spatial aspect of check-ins, whereas the joint inference of the spatial and temporal aspects more fits the real application scenarios. Moreover, although social relations have been extensively studied in a recommender system, only a few efforts have been observed in the next check-in location prediction, leaving room for further improvement. In this article, we study the next check-in inference problem, which demands the joint inference of the next check-in location (Where) and time (When) for a target user (Who). We devise a model named ARNPP-GAT, which combines an attention-based recurrent neural point process with a graph attention networks. The core technical insight of ARNPP-GAT is to integrate user long-term representation learning, short-term behavior modeling, and temporal point process into a unified architecture. Specifically, ARNPP-GAT first leverages graph attention networks to learn the long-term representation of users by encoding their social relations. More importantly, the ARNPP endows the model with the capability of characterizing the effects of past check-in events and performing multitask learning to yield the next check-in time and location prediction. Empirical results on two real-world data sets demonstrate that ARNPP-GAT is superior compared with several competitors, validating the contributions of multitask learning and social relation modeling.

This article conducts a comparative analysis to investigate the effects of different classification algorithms and structural proximity indexes on the performance of the supervised link prediction approach to anticipating technology convergence at different forecast horizons. For this, we identify relationships between technologies of interest for different time periods and compute 10 structural proximity indexes among unconnected technologies at each period. We develop a set of classification models that identify potential convergence among unconnected technologies where each model is configured differently by a classification algorithm and a combination of the proximity indexes. We compare the performance of the classification models to investigate effective combinations of classification algorithms and proximity indexes at different forecast horizons. The empirical analysis on Wikipedia articles about artificial intelligence technology indicates that random forest outperforms others in short-term forecasting while support vector machine outperforms others in mid-term forecasting. We also identify structural proximity indexes that produce higher performance when combined with the most effective algorithm at each forecast horizon. The results of this article are expected to offer guidelines for choosing classification algorithms and indexes when applying the supervised link prediction approach in anticipating technology convergence.

Spectral clustering is a well-known clustering algorithm for unsupervised learning, and its improved algorithms have been successfully adapted for many real-world applications. However, traditional spectral clustering algorithms are still facing many challenges to the task of unsupervised learning for large-scale datasets because of the complexity and cost of affinity matrix construction and the eigen-decomposition of the Laplacian matrix. From this perspective, we are looking forward to finding a more efficient and effective way by adaptive neighbor assignments for affinity matrix construction to address the above limitation of spectral clustering. It tries to learn an affinity matrix from the view of global data distribution. Meanwhile, we propose a deep learning framework with fully connected layers to learn a mapping function for the purpose of replacing the traditional eigen-decomposition of the Laplacian matrix. Extensive experimental results have illustrated the competitiveness of the proposed algorithm. It is significantly superior to the existing clustering algorithms in the experiments of both toy datasets and real-world datasets.

Heterogeneous domain adaptation (HDA) tackles the learning of cross-domain samples with both different probability distributions and feature representations. Most of the existing HDA studies focus on the single-source scenario. In reality, however, it is not uncommon to obtain samples from multiple heterogeneous domains. In this article, we study the multisource HDA problem and propose a conditional weighting adversarial network (CWAN) to address it. The proposed CWAN adversarially learns a feature transformer, a label classifier, and a domain discriminator. To quantify the importance of different source domains, CWAN introduces a sophisticated conditional weighting scheme to calculate the weights of the source domains according to the conditional distribution divergence between the source and target domains. Different from existing weighting schemes, the proposed conditional weighting scheme not only weights the source domains but also implicitly aligns the conditional distributions during the optimization process. Experimental results clearly demonstrate that the proposed CWAN performs much better than several state-of-the-art methods on four real-world datasets.

With the dawn of 5G network, a new set of requirements for site spectrum monitoring, cellular planning are emerging, all of which are relying on fine-grained signal map. Although with significant importance, the traditional signal map construction could be time-consuming and labor-intensive. The state-of-the arts usually employ crowdsourcing scheme and matrix completion algorithm to solve the dilemma. However, the crowdsourcing scheme usually suffers from uneven distributed and inadequate participants. To this end, in this paper, we study how to effectively reconstruct and update the signal map in the case of partially measured signal maps with smaller cost and propose a GAN-based active signal map reconstruction method (GSMAC). Our method is mainly innovative in two parts: GSMC, GAN-based signal map construction, and ACS, an active crowdsourcing scheme. Specifically, GSMC can effectively update the signal map with only a small number of observations while updating the signal map online. ACS consists of a reinforce learning-based active query mechanism which quantitatively evaluates the most valuable measurement site for reconstruction. The simulation results and real implemented data-driven experiments demonstrate the advantages and effectiveness of our approach in both accuracy and cost.

Daily schedule recommendation is an intelligent approach to recommend multiple suitable activity locations and activity sequences for users based on their needs in a day. In such a scenario, training the model using traditional methods requires centralized data collection from individual users, which may be prohibited by data protection acts, such as GDPR and CCPA. In this paper, we address the problem of daily schedule recommendation utilizing the deep reinforcement learning model in a federated learning framework (FedDSR). And curriculum learning is applied to guide the training process towards better local optimization and better generalization. For the uploaded local parameters, a similarity aggregation algorithm is proposed to improve the quality of the model. The experimental results show that the proposed FedDSR model is superior and effective to multiple baselines on two real datasets Geolife and Chengdu. Comparing with baselines, our method not only ensures that the parties do not need to share data and thus achieve joint modeling, but also can exceed ~18% under evaluation metric perimeter and improve ~0.72% under evaluation metric ADTS.

In this article, we investigate the problem of social link inference in a target location-aware social network (LSN), which aims at predicting the unobserved links between users within the network. This problem is critical for downstream applications, including network completion and friend recommendation. In addition to the network structures commonly used in general link prediction, the studies tailored for social link inference in an LSN leverage user trajectories from the spatial aspect. However, the temporal factor lying in user trajectories is largely overlooked by most of the prior studies, limiting the capabilities of capturing the temporal relevance between users. Moreover, effective user matching by fusing different views, i.e., social, spatial, and temporal factors, remains unresolved, which hinders the potential improvement of link inference. To this end, this article devises a novel multiview matching network (MVMN) by regarding each of the three factors as one view of any target user pair. MVMN enjoys the flexibility and completeness of modeling each factor by developing its suitable matching module: 1) location matching module; 2) time-series matching module; and 3) relation matching module. Each module learns a view-specific representation for matching, and MVMN fuses them for final link inference. Extensive experiments on two real-world data sets demonstrate the superiority of our approach against several competitive baselines for link prediction and sequence matching, validating the contribution of its key components.

Compressed sensing has been identified as a good candidate for user detection in grant-free non-orthogonal multiple access (NOMA) by exploiting the inherent sparsity of user activity. However, most of the existing works do not fully utilize the temporal correlation in NOMA and rely heavily on the unrealistic assumption that the number of active users is known in advance. To address these issues, we propose a temporal correlation enhanced multiuser detection scheme to achieve efficient and practical multiuser detection. Firstly, using 1 bit memory to piggyback the information whether the active users still have data to transmit, the base station can realize whether the active users in current time slot will turn to be silent or remain active. Then, to make explicit use of the temporal correlation of active user sets, a cross validation based adaptive subspace pursuit (CVASP) algorithm, is developed by utilizing the reported information on prior active users. The proposed CVASP is a highly practical algorithm that does not require any prior knowledge of the user sparsity level, as the cross validation technique could properly determine the stopping condition. Extensive simulation results demonstrate that the proposed mechanism could achieve a superier performance without requiring any prior knowledge.

The adaptive neurofuzzy inference system (ANFIS) is a structured multioutput learning machine that has been successfully adopted in learning problems without noise or outliers. However, it does not work well for learning problems with noise or outliers. High-accuracy real-time forecasting of traffic flow is extremely difficult due to the effect of noise or outliers from complex traffic conditions. In this study, a novel probabilistic learning system, probabilistic regularized extreme learning machine combined with ANFIS (probabilistic R-ELANFIS), is proposed to capture the correlations among traffic flow data and, thereby, improve the accuracy of traffic flow forecasting. The new learning system adopts a fantastic objective function that minimizes both the mean and the variance of the model bias. The results from an experiment based on real-world traffic flow data showed that, compared with some kernel-based approaches, neural network approaches, and conventional ANFIS learning systems, the proposed probabilistic R-ELANFIS achieves competitive performance in terms of forecasting ability and generalizability.

Achieving robust cross contexts speech emotion recognition (SER) has become a critical next direction of research for wide adoption of SER technology. The core challenge is in the large variability of affective speech that is highly contextualized. Prior works have worked on this as a transfer learning problem that mostly focuses on developing domain adaptation strategy. However, many of the existing speech emotion corpora, even those considered as large scale, are still limited in size resulting in an unsatisfactory transfer result. On the other hand, directly collecting context-specific corpus often results in an even smaller data size leading to an inevitably non-robust accuracy. In order to mitigate this issue, we propose the concept of enhancing the affect-related variability when learning the in-context acoustic latent representation by integrating out-of-context emotion data. Specifically, we utilize adversarial autoencoder network as our backbone with multiple out-of-context emotion labels derived for each in-context samples that serve as an auxiliary constraint in learning the latent representation. We extensively evaluate our framework using three in-context databases with three out-of-context databases. In this work, we demonstrate not only an improved recognition accuracy but also a comprehensive analysis on the effectiveness of this representation learning strategy.

The security of our data stores is underestimated in current practice, which resulted in many large-scale data breaches. To change the status quo, this paper presents the design of ShieldDB, an encrypted document database. ShieldDB adapts the searchable encryption technique to preserve the search functionality over encrypted documents without having much impact on its scalability. However, merely realising such a theoretical primitive suffers from real-world threats, where a knowledgeable adversary can exploit the leakage (aka access pattern to the database) to break the claimed protection on data confidentiality. To address this challenge in practical deployment, ShieldDB is designed with tailored padding countermeasures. Unlike prior works, we target a more realistic adversarial model, where the database gets updated continuously, and the adversary can monitor it at an (or multiple) arbitrary time interval(s). ShieldDB's padding strategies ensure that the access pattern to the database is obfuscated all the time. Additionally, ShieldDB provides other advanced features, including forward privacy, re-encryption, and flushing, to further improve its security and efficiency. We present a full-fledged implementation of ShieldDB and conduct intensive evaluations on Azure Cloud., Comment: Accepted version of our work published in IEEE Transactions on Knowledge and Data Engineering (TKDE, 2021)

Remaining useful life (RUL) prediction of aircraft engine (AE) is of great importance to improve its reliability and availability, and reduce its maintenance costs. This article proposes a novel deep bidirectional recurrent neural networks (DBRNNs) ensemble method for the RUL prediction of the AEs. In this method, several kinds of DBRNNs with different neuron structures are built to extract hidden features from sensory data. A new customized loss function is designed to evaluate the performance of the DBRNNs, and a series of the RUL values is obtained. Then, these RUL values are reencapsulated into a predicted RUL domain. By updating the weights of elements in the domain, multiple regression decision tree (RDT) models are trained iteratively. These models integrate the predicted results of different DBRNNs to realize the final RUL prognostics with high accuracy. The proposed method is validated by using C-MAPSS datasets from NASA. The experimental results show that the proposed method has achieved more superior performance compared with other existing methods.

In many domains of empirical sciences, discovering the causal structure within variables remains an indispensable task. Recently, to tackle unoriented edges or latent assumptions violation suffered by conventional methods, researchers formulated a reinforcement learning (RL) procedure for causal discovery and equipped a REINFORCE algorithm to search for the best rewarded directed acyclic graph. The two keys to the overall performance of the procedure are the robustness of RL methods and the efficient encoding of variables. However, on the one hand, REINFORCE is prone to local convergence and unstable performance during training. Neither trust region policy optimization, being computationally expensive, nor proximal policy optimization (PPO), suffering from aggregate constraint deviation, is a decent alternative for combinatory optimization problems with considerable individual subactions. We propose a trust region-navigated clipping policy optimization method for causal discovery that guarantees both better search efficiency and steadiness in policy optimization, in comparison with REINFORCE, PPO, and our prioritized sampling-guided REINFORCE implementation. On the other hand, to boost the efficient encoding of variables, we propose a refined graph attention encoder called SDGAT that can grasp more feature information without priori neighborhood information. With these improvements, the proposed method outperforms the former RL method in both synthetic and benchmark datasets in terms of output results and optimization robustness.

With the rapid development of the Internet, readers tend to share their views and emotions about news events. Predicting these emotions provides a vital role in social media applications (e.g., sentiment retrieval, opinion summary, and election prediction). However, news articles usually consist of objective texts that lack emotion words, making emotion prediction challenging. From prior studies, we know that comments that come directly from readers are full of emotions. Therefore, in this article, we propose a deep learning framework that first merges article and comment information to predict readers' emotions. At the same time, in the prediction process, we design a pseudo comment representation for unpublished news articles by the comments of published news. In addition, a better model is required to encode articles that contain implicit emotions. To solve this problem, we propose a block emotion attention network (BEAN) to encode news articles better. It includes an emotion attention mechanism and a hierarchical structure to capture emotion words and generate structural information during encoding. Experiments performed on three public datasets show that BEAN achieves the state-of-the-art average Pearson (AP) and accuracy (Acc@1). Moreover, results on four self-collected datasets show that both the introduction of emotional comments and BEAN in our framework improve the ability to predict readers' emotions.

Understanding in-network information diffusion is a fundamental problem in many applications and one of the primary challenges is to predict the information cascade size. Most of the existing models rely either on hypothesized point process (e.g., Poisson and Hawkes processes), or simply predict the information propagation via deep neural networks. However, they fail to simultaneously capture the underlying global and local structures of a cascade and the propagation uncertainty in the diffusion, which may result in unsatisfactory prediction performance. To address these, in this work we propose a novel probabilistic cascade prediction framework: Hierarchical Cascade Normalizing Flows (CasFlow). CasFlow allows a non-linear information diffusion inference and models the information diffusion process by learning the latent representation of both the structural and temporal information. It is a pattern-agnostic model leveraging normalizing flows to learn the node-level and cascade-level latent factors in an unsupervised manner. In addition, CasFlow is capable of capturing both the cascade representation uncertainty and node infection uncertainty, while enabling hierarchical pattern learning of information diffusion. Extensive experiments conducted on real-world datasets demonstrate that CasFlow reduces the prediction error to 21.0% by only observing half an hour of cascades, compared to state-of-the-art approaches, while also enabling model interpretability.

The objective of the current study is to present a comparison of techniques for the forecasting of low frequency climate oscillation indices with a focus on the Great Lakes system. A number of time series models have been tested including the traditional Autoregressive Moving Average (ARMA) model, Dynamic Linear model (DLM), Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model, as well as the nonstationary oscillation resampling (NSOR) technique. These models were used to forecast the monthly El Niño-Southern Oscillation (ENSO) and Pacific Decadal Oscillation (PDO) indices which show the most significant teleconnection with the net basin supply (NBS) of the Great Lakes system from a preliminary study. The overall objective is to predict future water levels, ice extent, and temperature, for planning and decision making purposes. The results showed that the DLM and GARCH models are superior for forecasting the monthly ENSO index, while the forecasted values from the traditional ARMA model presented a good agreement with the observed values within a short lead time ahead for the monthly PDO index.

Exciting recent advances in genome sequencing, coupled with greatly reduced storage and computation costs, make genomic testing increasingly accessible to individuals. Already today, one’s digitized DNA can be easily obtained from a sequencing lab and later used to conduct numerous tests by engaging with a testing facility. Due to the inherent sensitivity of genetic material and the often-proprietary nature of genomic tests, privacy is a natural and crucial issue. While genomic privacy received a great deal of attention within and outside the research community, genomic security has not been sufficiently studied. This is surprising since the usage of fake or altered genomes can have grave consequences, such as erroneous drug prescriptions and genetic test outcomes. Unfortunately, in the genomic domain, privacy and security (as often happens) are at odds with each other. In this article, we attempt to reconcile security with privacy in genomic testing by designing a novel technique for a secure and private genomic range query protocol between a genomic testing facility and an individual user. The proposed technique ensures authenticity and completeness of user-supplied genomic material while maintaining its privacy by releasing only the minimum thereof. To confirm its broad usability, we show how to apply the proposed technique to a previously proposed genomic private substring matching protocol. Experiments show that the proposed technique offers good performance and is quite practical. Furthermore, we generalize the genomic range query problem to sparse integer sets and discuss potential use cases.

A temporal analysis of landscape change patterns and consequent evaluation of urban expansion has been studied for the Dera Ghazi Khan city which is developing fast since 2000 as an emerging metropolis of South Punjab. The geospatial techniques particularly remote sensing augmented with GIS are vital tools and are mostly used in studying landscape changes and decision making for sustainable urban development. Four Landsat images (1991, 2001, 2011 and 2021) obtained from the free web of GLFC have been analysed. A supervised classification algorithm was applied to all images and results have been presented in both tabular and graphic forms. Present study, focuses upon two land-use classes i.e. built up and open areas, which will be monitored by land-use patterns of Dera Ghazi Khan city during 1991 to 2021 using satellite images. The graphical depiction of all the landscape changes, which have taken place in D. G. Khan city in the form of tables and maps provides detailed information about the degree and ratio of urban expansion and the changes in land use that occurred during the stipulated period.The classification was based on four categories i.e., urban land, bare soil, vegetation, and water; while maps were prepared to present the temporal changes in D. G. Khan city. A total of 52 sq./kms areas was selected for this study designated as the Dera Ghazi Khan city. According to the results, 33% of the urban area has been expanded in Dera Ghazi Khan from 1991 to 2021 and 19% vegetation cover has been reduced. It is a very alarming situation that agricultural land is decreasing because of urban expansion. The results revealed the significance of remote sensing and GIS in evaluating landscape changes.

Rumors can cause devastating consequences to individuals and our society. Analysis shows that the widespread of rumors typically results from deliberate promotion of information aiming to shape the collective public opinions on the concerned event. In this paper, we combat such chaotic phenomenon with a countermeasure by mirroring against how such chaos is created to make rumor detection more robust and effective. Our idea is inspired by adversarial learning method originated from Generative Adversarial Networks (GAN). We propose a GAN-style approach, where a generator is designed to produce uncertain or conflicting voices, further polarizing the original conversational threads to boost the discriminator. We reveal that feature learning effectiveness is highly relevant to the quality of generated parody. Given the strong natural language generation performance of transformer, we propose a transformer-based method to improve the generated posts, which appear to be closely responsive to the source post and retain the authentic propagation structure. Different from traditional data-driven rumor detection approaches, our method can capture low-frequency but more salient non-trivial discriminant patterns. Extensive experiments on THREE benchmarks demonstrate that our rumor detection method achieves much better results than state-of-the-art methods, and the transformer-based model further improve the performance of our GAN-style approach.

We present RCMVis, a visual analytics system to support interactive Route Choice Modeling analysis. It aims to model which characteristics of routes, such as distance and the number of traffic lights, affect travelers' route choice behaviors and how much they affect the choice during their trips. Through close collaboration with domain experts, we designed a visual analytics framework for Route Choice Modeling. The framework supports three interactive analysis stages: exploration, modeling, and reasoning. In the exploration stage, we help analysts interactively explore trip data from multiple origin-destination (OD) pairs and choose a subset of data they want to focus on. To this end, we provide coordinated multiple OD views with different foci that allow analysts to inspect, rank, and compare OD pairs in terms of their multidimensional attributes. In the modeling stage, we integrate a k-medoids clustering method and a path-size logit model into our system to enable analysts to model route choice behaviors from trips with support for feature selection, hyperparameter tuning, and model comparison. Finally, in the reasoning stage, we help analysts rationalize and refine the model by selectively inspecting the trips that strongly support the modeling result. For evaluation, we conducted a case study and interviews with domain experts. The domain experts discovered unexpected insights from numerous modeling results, allowing them to explore the hyperparameter space more effectively to gain better results. In addition, they gained OD- and road-level insights into which data mainly supported the modeling result, enabling further discussion of the model.

Problem definition: We present a data-driven study of the secondary ticket market. In particular, we are primarily concerned with accurately estimating price sensitivity for listed tickets. In this setting, there are many issues including endogeneity, heterogeneity in price sensitivity for different tickets, binary outcomes, and nonlinear interactions between ticket features. Our secondary goal is to highlight how this estimation can be integrated into a prescriptive trading strategy for buying and selling tickets in an active marketplace. Academic/practical relevance: We present a novel method for demand estimation with heterogeneous treatment effect in the presence of confounding. In practice, we embed this method within an optimization framework for ticket reselling, providing the ticket reselling platform with a new framework for pricing tickets on its platform. Methodology: We introduce a general double/orthogonalized machine learning method for classification problems. This method allows us to isolate the causal effects of price on the outcome by removing the conditional effects of the ticket and market features. Furthermore, we introduce a novel loss function that can be easily incorporated into powerful, off-the-shelf machine learning algorithms, including gradient boosted trees. We show how, in the presence of hidden confounding variables, instrumental variables can be incorporated. Results: Using a wide range of synthetic data sets, we show this approach beats state-of-the-art machine learning and causal inference approaches for estimating treatment effects in the classification setting. Furthermore, using National Basketball Association ticket listings from the 2014–2015 season, we show that probit models with instrumental variables, previously used for price estimation of tickets in the resale market, are significantly less accurate and potentially misspecified relative to our proposed approach. Through pricing simulations, we show our proposed method can achieve an 11% return on investment by buying and selling tickets, whereas existing techniques are not profitable. Managerial implications: The knowledge of how to price tickets on its platform offers a range of potential opportunities for our collaborator, both in terms of understanding sellers on their platform and in developing new products to offer them. History: This paper has been accepted as part of the 2019 Manufacturing & Service Operations Management Practice-Based Research Competition. Funding: This work was supported by the National Science Foundation [Grant CMMI-1563343]. Supplemental Material: The online appendices are available at https://doi.org/10.1287/msom.2021.1065 .

Relation classification (RC) task is one of fundamental tasks of information extraction, aiming to detect the relation information between entity pairs in unstructured natural language text and generate structured data in the form of entity-relation triple. Although distant supervision methods can effectively alleviate the problem of lack of training data in supervised learning, they also introduce noise into the data, and still cannot fundamentally solve the long-tail distribution problem of the training instances. In order to enable the neural network to learn new knowledge through few instances like humans, this work focuses on few-shot relation classification (FSRC), where a classifier should generalize to new classes that have not been seen in the training set, given only a number of samples for each class. To make full use of the existing information and get a better feature representation for each instance, we propose to encode each class prototype in an adaptive way from two aspects. First, based on the prototypical networks, we propose an adaptive mixture mechanism to add label words to the representation of the class prototype, which, to the best of our knowledge, is the first attempt to integrate the label information into features of the support samples of each class so as to get more interactive class prototypes. Second, to more reasonably measure the distances between samples of each category, we introduce a loss function for joint representation learning to encode each support instance in an adaptive manner. Extensive experiments have been conducted on FewRel under different few-shot (FS) settings, and the results show that the proposed adaptive prototypical networks with label words and joint representation learning has not only achieved significant improvements in accuracy, but also increased the generalization ability of few-shot RC models.

Face parsing aims to assign pixel-wise semantic labels to different facial components (e.g., hair, brows, and lips) in given face images. However, directly predicting pixel-level labels for each facial component over the whole face image would obtain limited accuracy, especially for tiny facial components. To address this problem, some recent works propose to first crop tiny patches from the whole face image and then predict masks for each facial component. However, such cropping-and-segmenting strategy consists of two independent stages, which cannot be jointly optimized. Besides, as one valuable piece of information for parsing the highly structured facial components, context cues are not elaborately explored by the existing works. To address these issues, we propose a component-level refinement network (CLRNet) for precisely segmenting out each facial component. Specifically, we introduce an attention mechanism to bridge the two independent stages together and form an end-to-end trainable pipeline for face parsing. Furthermore, we incorporate the global context information into the refining process for each cropped facial component patch, providing informative cues for accurate parsing. Extensive experiments are carried out on two benchmark datasets, LFW-PL and HELEN. The results demonstrate the superiority of the proposed CLRNet over other state-of-the-art methods, especially for tiny facial components.

With the prevalence of voice devices in our daily life, speech data is accumulated at an unprecedented speed. The vast amount of speech data form an invaluable database for security surveillance and financial risk management. However, the speeches collected from different sources are not necessarily annotated with regard to the speaker identity, making the task of retrieving all the speech records for a given identity extremely challenging. In this paper, we propose a scalable system for Identity-Oriented Speech Retrieval (IO-SR), which seamlessly integrates speaker modeling and deep indexing techniques. Given a speech snippet and a speech database, IO-SR efficiently retrieves all speech snippets that are uttered by the same speaker as the given one. Evaluations on an industrial dataset containing millions of speech snippets show that our system achieves superior performance compared with the state-of-the-arts.

Human parsing is a fine-grained semantic segmentation task, which needs to understand human semantic parts. Most existing methods model human parsing as a general semantic segmentation, which ignores the inherent relationship among hierarchical human parts. In this work, we propose a pose-guided hierarchical semantic decomposition and composition framework for human parsing. Specifically, our method includes a semantic maintained decomposition and composition (SMDC) module and a pose distillation (PC) module. SMDC progressively disassembles the human body to focus on the more concise regions of interest in the decomposition stage and then gradually assembles human parts under the guidance of pose information in the composition stage. Notably, SMDC maintains the atomic semantic labels during both stages to avoid the error propagation issue of the hierarchical structure. To further take advantage of the relationship of human parts, we introduce pose information as explicit guidance for the composition. However, the discrete structure prediction in pose estimation is against the requirement of the continuous region in human parsing. To this end, we design a PC module to broadcast the maximum responses of pose estimation to form the continuous structure in the way of knowledge distillation. The experimental results on the look-into-person (LIP) and PASCAL-Person-Part datasets demonstrate the superiority of our method compared with the state-of-the-art methods, that is, 55.21% mean Intersection of Union (mIoU) on LIP and 69.88% mIoU on PASCAL-Person-Part.

Partial multilabel learning (PML) aims to learn from training data, where each instance is associated with a set of candidate labels, among which only a part is correct. The common strategy to deal with such a problem is disambiguation, that is, identifying the ground-truth labels from the given candidate labels. However, the existing PML approaches always focus on leveraging the instance relationship to disambiguate the given noisy label space, while the potentially useful information in label space is not effectively explored. Meanwhile, the existence of noise and outliers in training data also makes the disambiguation operation less reliable, which inevitably decreases the robustness of the learned model. In this article, we propose a prior label knowledge regularized self-representation PML approach, called PAKS, where the self-representation scheme and prior label knowledge are jointly incorporated into a unified framework. Specifically, we introduce a self-representation model with a low-rank constraint, which aims to learn the subspace representations of distinct instances and explore the high-order underlying correlation among different instances. Meanwhile, we incorporate prior label knowledge into the above self-representation model, where the prior label knowledge is regarded as the complement of features to obtain an accurate self-representation matrix. The core of PAKS is to take advantage of the data membership preference, which is derived from the prior label knowledge, to purify the discovered membership of the data and accordingly obtain more representative feature subspace for model induction. Enormous experiments on both synthetic and real-world datasets show that our proposed approach can achieve superior or comparable performance to state-of-the-art approaches.

Long-term visual place recognition (VPR) is challenging as the environment is subject to drastic appearance changes across different temporal resolutions, such as time of the day, month, and season. A wide variety of existing methods address the problem by means of feature disentangling or image style transfer but ignore the structural information that often remains stable even under environmental condition changes. To overcome this limitation, this article presents a novel structure-aware feature disentanglement network (SFDNet) based on knowledge transfer and adversarial learning. Explicitly, probabilistic knowledge transfer (PKT) is employed to transfer knowledge obtained from the Canny edge detector to the structure encoder. An appearance teacher module is then designed to ensure that the learning of appearance encoder does not only rely on metric learning. The generated content features with structural information are used to measure the similarity of images. We finally evaluate the proposed approach and compare it to state-of-the-art place recognition methods using six datasets with extreme environmental changes. Experimental results demonstrate the effectiveness and improvements achieved using the proposed framework. Source code and some trained models will be available at http://www.tianshu.org.cn.

Forest production and growth are obtained from statistical models that allow the generation of information at the tree or forest stand level. Although the use of regression models is common in forest measurement, there is a constant search for estimation procedures that provide greater accuracy. Recently, machine learning techniques have been used with satisfactory performance in measuring forests. However, methods such as Adaptive Neuro-Fuzzy Inference System (ANFIS) and Random Forest are relatively poorly studied for predicting the volume of wood in eucalyptus plantations in Brazil. Therefore, it is essential to check whether these techniques can provide gains in terms of accuracy. Thus, this study aimed to evaluate the use of Random Forest and ANFIS techniques in the prognosis of forest production. The data used come from continuous forest inventories carried out in stands of eucalyptus clones. The data were divided into 70% for training and 30% for validation. The algorithms used to generate rules in ANFIS were Subtractive Clustering and Fuzzy-C-Means. Besides, training was done with the hybrid algorithm (descending gradient and least squares) with the number of seasons ranging from 1 to 20. Several RFs were trained, varying the number of trees from 50 to 850 and the number of observations by five leaves to 35. Artificial neural networks and decision trees were also trained to compare the feasibility of the techniques. The evaluation of the estimates generated by the techniques for training and validation was calculated based on the following statistics: correlation coefficient (r), relative Bias (RB), and the relative root mean square error (RRMSE) in percentage. In general, the techniques studied in this work showed excellent performance for the training and validation data set with RRMSE values 0.98. The RF presented inferior statistics about the ANFIS for the prognosis of forest production. The Subtractive Clustering (SC) and Fuzzy-C-Means (FCM) algorithms provide accurate baseline and volume projection estimates; both techniques are good alternatives for selecting variables used in modeling forest production.

Bayesian optimal inference is often heralded as a principled, general framework for human perception. However, optimal inference requires integration over all possible world states, which quickly becomes intractable in complex real-world settings. Additionally, deviations from optimal inference have been observed in human decisions. A number of approximation methods have previously been suggested, such as sampling methods. In this study, we additionally propose point estimate observers, which evaluate only a single best estimate of the world state per response category. We compare the predicted behavior of these model observers to human decisions in five perceptual categorisation tasks. Compared to the Bayesian observer, the point estimate observer loses decisively in one task, ties in two and wins in two tasks. Two sampling observers also improve upon the Bayesian observer, but in a different set of tasks. Thus, none of the existing general observer models appears to fit human perceptual decisions in all situations, but the point estimate observer is competitive with other observer models and may provide another stepping stone for future model development.

Although quite natural for human beings to communicate based on their own personality in daily life, it is rather challenging for neural dialog systems to do the same. This is because the general dialog systems are difficult to generate diverse responses while at the same time maintaining consistent persona information. Existing methods basically focus on merely one of them, ignoring either of them will reduce the quality of dialog. In this work, we propose a two-stage generation framework to promote the persona-consistency and diversity of responses. In the first stage, we propose a persona-guided conditional variational autoencoder (persona-guided CVAE) to generate diverse responses, and the main difference when compared with general CVAE-based model is that we use additional dialog attribute to assist the latent variables to encode the effective information in the response and further use it as a guiding vector for response generation. In the second stage, we employ persona-consistency checking module and the response rewriting module to mask the inconsistent word in the generated response prototype and rewrite it to more consistent. Automatic evaluation results demonstrate that the proposed model is able to generate diverse and persona-consistent responses.

In the last decade, deep neural networks (DNNs) have become dominant tools for various of supervised learning tasks, especially classification. However, it is demonstrated that they can easily overfit to training set biases, such as label noise and class imbalance. Example reweighting algorithms are simple and effective solutions against this issue, but most of them require manually specifying the weighting functions as well as additional hyperparameters. Recently, a meta-learning-based method Meta-Weight-Net (MW-Net) has been proposed to automatically learn the weighting function parameterized by an MLP via additional unbiased metadata, which significantly improves the robustness of prior arts. The method, however, is proposed in a deterministic manner, and short of intrinsic statistical support. In this work, we propose a probabilistic formulation for MW-Net, probabilistic MW-Net (PMW-Net) in short, which treats the weighting function in a probabilistic way, and can include the original MW-Net as a special case. By this probabilistic formulation, additional randomness is introduced while the flexibility of the weighting function can be further controlled during learning. Our experimental results on both synthetic and real datasets show that the proposed method improves the performance of the original MW-Net. Besides, the proposed PMW-Net can also be further extended to fully Bayesian models, to improve their robustness.