Search

Fluid dynamical simulations are often performed using cheap macroscopic models like the Euler equations. For rarefied gases under near-equilibrium conditions, however, macroscopic models are not sufficiently accurate and a simulation using more accurate microscopic models is often expensive. In this paper, we introduce a hierarchical micro-macro acceleration based on moment models that combines the speed of macroscopic models and the accuracy of microscopic models. The hierarchical micro-macro acceleration is based on a flexible four step procedure including a micro step, restriction step, macro step, and matching step. We derive several new micro-macro methods from that and compare to existing methods. In 1D and 2D test cases, the new methods achieve high accuracy and a large speedup.

This paper is part of an ongoing endeavor to bring the theory of fair division closer to practice by handling requirements from real-life applications. We focus on two requirements originating from the division of land estates: (1) each agent should receive a plot of a usable geometric shape, and (2) plots of different agents must be physically separated. With these requirements, the classic fairness notion of \emph{proportionality} is impractical, since it may be impossible to attain any multiplicative approximation of it. In contrast, the \emph{ordinal maximin share approximation}, introduced by Budish in 2011, provides meaningful fairness guarantees. We prove upper and lower bounds on achievable maximin share guarantees when the usable shapes are squares, fat rectangles, or arbitrary axis-aligned rectangles, and explore the algorithmic and query complexity of finding fair partitions in this setting. Our work makes use of tools and concepts from computational geometry such as independent sets of rectangles and guillotine partitions., Appears in the 30th International Joint Conference on Artificial Intelligence (IJCAI), 2021

The dynamics of ecosystems is of crucial importance. Various model-based approaches exist to understand and analyze their internal effects. In this paper, we model the space structure dynamics and ecological dynamics of meta-ecosystems using the formal technique of Graph Transformation (short GT). We build GT models to describe how a meta-ecosystem (modeled as a graph) can evolve over time (modeled by GT rules) and to analyze these GT models with respect to qualitative properties such as the existence of structural stabilities. As a case study, we build three GT models describing the space structure dynamics and ecological dynamics of three different savanna meta-ecosystems. The first GT model considers a savanna meta-ecosystem that is limited in space to two ecosystem patches, whereas the other two GT models consider two savanna meta-ecosystems that are unlimited in the number of ecosystem patches and only differ in one GT rule describing how the space structure of the meta-ecosystem grows. In the first two GT models, the space structure dynamics and ecological dynamics of the meta-ecosystem shows two main structural stabilities: the first one based on grassland-savanna-woodland transitions and the second one based on grassland-desert transitions. The transition between these two structural stabilities is driven by high-intensity fires affecting the tree components. In the third GT model, the GT rule for savanna regeneration induces desertification and therefore a collapse of the meta-ecosystem. We believe that GT models provide a complementary avenue to that of existing approaches to rigorously study ecological phenomena.

Real-world multi-objective optimization problems encounter different types of uncertainty that may affect the quality of solutions. One common type is the stochastic noise that contaminates the objective functions. Another type of uncertainty is the different forms of dynamism including changes in the objective functions. Although related work in the literature targets only a single type, in this paper, we study Dynamic Multi-objective Optimization problems (DMOPs) contaminated with stochastic noises by dealing with the two types of uncertainty simultaneously. In such problems, handling uncertainty becomes a critical issue since the evolutionary process should be able to distinguish between changes that come from noise and real environmental changes that resulted from different forms of dynamism. To study both noisy and dynamic environments, we propose a flexible mechanism to incorporate noise into the DMOPs. Two novel techniques called Multi-Sensor Detection Mechanism (MSD) and Welford-Based Detection Mechanism (WBD) are proposed to differentiate between real change points and noise points. The proposed techniques are incorporated into a set of Dynamic Multi-objective Evolutionary Algorithms (DMOEAs) to analyze their impact. Our empirical study reveals the effectiveness of the proposed techniques for isolating noise from real dynamic changes and diminishing the noise effect on performance.

Screw and Lie group theory allows for user-friendly modeling of multibody systems (MBS) while at the same they give rise to computationally efficient recursive algorithms. The inherent frame invariance of such formulations allows for use of arbitrary reference frames within the kinematics modeling (rather than obeying modeling conventions such as the Denavit-Hartenberg convention) and to avoid introduction of joint frames. The computational efficiency is owed to a representation of twists, accelerations, and wrenches that minimizes the computational effort. This can be directly carried over to dynamics formulations. In this paper recursive $O\left( n\right) $ Newton-Euler algorithms are derived for the four most frequently used representations of twists, and their specific features are discussed. These formulations are related to the corresponding algorithms that were presented in the literature. The MBS motion equations are derived in closed form using the Lie group formulation. One are the so-called 'Euler-Jourdain' or 'projection' equations, of which Kane's equations are a special case, and the other are the Lagrange equations. The recursive kinematics formulations are readily extended to higher orders in order to compute derivatives of the motions equations. To this end, recursive formulations for the acceleration and jerk are derived. It is briefly discussed how this can be employed for derivation of the linearized motion equations and their time derivatives. The geometric modeling allows for direct application of Lie group integration methods, which is briefly discussed.

The widespread diffusion of connected smart devices has greatly contributed to the rapid expansion and evolution of the Internet at its edge, where personal mobile devices follow the behavior of their human users and interact with other smart objects located in the surroundings. In such a scenario, the user context is represented by a large variety of information that can rapidly change, and the ability of personal mobile devices to locally process this data is fundamental to make the system able to quickly adapt its behavior to the current situation. This ability, in practice, can be represented by a single elaboration process integrated in the final user application, or by a middleware platform aimed at implementing different context processing and reasoning to support third-party applications. However, the lack of public datasets that take into account the complexity of the user context in the mobile environment strongly limits the advance of the research in this field. In this paper, we present MyDigitalFootprint, a novel large-scale dataset composed of smartphone embedded sensors data, physical proximity information, and Online Social Networks interactions aimed at supporting multimodal context-recognition and social relationships modeling. The dataset includes two months of measurements and information collected from the personal mobile devices of 31 volunteer users, in their natural environment, without limiting their usual behavior. Existing public datasets generally consist of a limited set of context data, aimed at optimizing specific application domains (human activity recognition is the most common example). On the contrary, our dataset contains a comprehensive set of information describing the user context in the mobile environment. In order to demonstrate the efficacy of the proposed dataset, we present three context-aware applications based on different machine learning tasks: (i) a social link prediction algorithm based on physical proximity data, (ii) the recognition of daily-life activities based on smartphone-embedded sensors data, and (iii) a pervasive context-aware recommender system. To the best of our knowledge, this is the first large-scale dataset containing such heterogeneity of information, representing an invaluable source of data to validate new research in mobile and edge computing.

A major drawback of nonlinear dimensionality reduction (DR) techniques is their inability to preserve some authentic information from the source domain, leading to projections that are often hard to interpret when it comes to observing anything other than the topological structure of the data. In this paper, we propose a nonlinear DR approach enforcing projection constraints resulting from an a priori knowledge about the structure of the data in multivariate periodical time series. We then propose several ways of exploiting this constrained projection to extract user-relevant information, such as the nominal behavior of a periodical dynamical system or the deviant behaviors which may occur at different time scales. The techniques are demonstrated on both a synthetic dataset composed of simulated multivariate data exhibiting a periodical behavior, and a real dataset corresponding to six months of sensor data acquisitions and recordings inside experimental buildings. 1 We would like to thank the Institut National de l'Energie Solaire (INES) and the CEA, LITEN, Laboratoire Energetique du Bâtiment for providing the data.

Various studies on latency in remote mixed reality collaborations (remote MR collaboration) have been conducted, but studies related to interaction latency are scarce. Interaction latency in a remote MR collaboration occurs because action detection (such as contact or collision) between a human and a virtual object is required for finding the interaction performed. Therefore, in this paper, we propose a method based on interaction prediction to reduce the time for detecting the action between humans and virtual objects. The proposed method predicts an interaction based on consecutive joint angles. To examine the effectiveness of the proposed method, an experiment was conducted and the results were given. From the experimental results, it was confirmed that the proposed method could reduce the interaction latency compared to the one obtained by conventional methods.

In the recent past, complex deep neural networks have received huge interest in various document understanding tasks such as document image classification and document retrieval. As many document types have a distinct visual style, learning only visual features with deep CNNs to classify document images have encountered the problem of low inter-class discrimination, and high intra-class structural variations between its categories. In parallel, text-level understanding jointly learned with the corresponding visual properties within a given document image has considerably improved the classification performance in terms of accuracy. In this paper, we design a self-attention-based fusion module that serves as a block in our ensemble trainable network. It allows to simultaneously learn the discriminant features of image and text modalities throughout the training stage. Besides, we encourage mutual learning by transferring the positive knowledge between image and text modalities during the training stage. This constraint is realized by adding a truncated-Kullback-Leibler divergence loss Tr-KLD-Reg as a new regularization term, to the conventional supervised setting. To the best of our knowledge, this is the first time to leverage a mutual learning approach along with a self-attention-based fusion module to perform document image classification. The experimental results illustrate the effectiveness of our approach in terms of accuracy for the single-modal and multi-modal modalities. Thus, the proposed ensemble self-attention-based mutual learning model outperforms the state-of-the-art classification results based on the benchmark RVL-CDIP and Tobacco-3482 datasets., Accepted at IJDAR 2021

Finding an appropriate transfer function (TF) for mapping color and opacity values in direct volume rendering (DVR) can be a daunting task. This paper presents a novel approach towards TF generation for DVR, where the traditional low-level color and opacity parameter manipulations are not necessary. The TF generation process is hidden behind a simple and intuitive spherical self-organizing map (SSOM) visualization. The SSOM represents a visual form of the topological relations among the clusters. The user interacts with the SSOM lattice to find interesting regions in the volume. The color and opacity values are generated automatically from the voxel features based on the user's perception. We also use harmonic colors to present a visually pleasing result. Due to the independence of SSOM from feature type, our proposed method is flexible in nature and can be integrated with any set of features. The GPU implementation provides real-time volume rendering and fast interaction. Experimental results on several benchmark volume datasets show the effectiveness of our proposed method.

Predictability is a prerequisite for effective human control of artificial intelligence (AI). For example, the inability to predict the malfunctioning of AI impedes timely human intervention. In this paper, we employ a computerized navigation task, a lunar lander game, to investigate empirically how AI's predictability compares to humans' predictability. To this end, we ask participants to guess whether the landings of a spaceship in this game performed by AI and humans will succeed. We show that humans are worse at predicting AI performance than at predicting human performance in this environment. Significantly, participants underestimate the differences in the relative predictability of AI and, at times, overestimate their prediction skills. We link the difference in predictability to differences in the approaches, i.e. different landing patterns, employed by AI and humans to succeed in the task. These results highlight important differences in perception of AI and human with implications for human-computer interaction.

In the face of the global concern about climate change and endangered ecosystems, monitoring individual animals is of paramount importance. Computer vision methods for animal recognition and re-identification from video or image collections are a modern alternative to more traditional but intrusive methods such as tagging or branding. While there are many studies reporting results on various animal re-identification databases, there is a notable lack of comparative studies between different classification methods. In this paper we offer a comparison of 25 classification methods including linear, non-linear and ensemble models, as well as deep learning networks. Since the animal databases are vastly different in characteristics and difficulty, we propose an experimental protocol that can be applied to a chosen data collections. We use a publicly available database of five video clips, each containing multiple identities (9 to 27), where the animals are typically present as a group in each video frame. Our experiment involves five data representations: colour, shape, texture, and two feature spaces extracted by deep learning. In our experiments, simpler models (linear classifiers) and just colour feature space gave the best classification accuracy, demonstrating the importance of running a comparative study before resorting to complex, time-consuming, and potentially less robust methods., This work is supported by the UKRI Centre for Doctoral Training in Artificial Intelligence, Machine Learning and Advanced Computing (AIMLAC), funded by grant EP/S023992/1. This work is also supported by the Junta de Castilla León under project BU055P20 (JCyL/FEDER, UE), and the Ministry of Science and Innovation under project PID2020-119894 GB-I00 co-financed through European Union FEDER funds. J.L. Garrido-Labrador is supported through Consejería de Educación of the Junta de Castilla y León and the European Social Fund through a pre-doctoral grant (EDU/875/2021). I. Ramos-Perez is supported by the predoctoral grant (BDNS 510149) awarded by the Universidad de Burgos, Spain. J.J. Rodríguez was supported by mobility grant PRX21/00638 of the Spanish Ministry of Universities.

Restrictive public health measures such as isolation and quarantine have been used to reduce the pandemic viruss transmission. With no proper treatment, older adults have been specifically advised to stay home, given their vulnerability to COVID-19. This pandemic has created an increasing need for new and innovative assistive technologies capable of easing the lives of people with special needs. Smart home systems have become widely popular in providing such assistive services to isolated older adults. These systems can provide better services to assist older people if it anticipates what activities inhabitants will perform ahead of time. For example, a smart home can prompt inhabitants to initiate essential activities like taking medicine using activity prediction. This paper proposes a multi- task activity prediction system that jointly predicts labels, lo- cations, and starting times of future activities. The observed sequence of previous activities characterizes future activities. We use body activity information from wearable sensors and motion information from passive environmental sensors to sense activities of daily living of older adults. The activity prediction system consists of recurrent neural networks to capture temporal dependencies. This work also carries out several experiments on collected and existing real datasets to evaluate the systems performance.

With the dramatic progress of wearable devices, continuous collection of single lead ECG wave is able to be implemented in a comfortable fashion. Data mining on single lead ECG wave is therefore attracting increasing attention, where atrial fibrillation (AF) detection is a hot topic. In this paper, we propose a dual-channel neural network for AF detection from a single lead ECG wave. Two primary phases are included, the data preprocessing part followed by a dual-channel neural network. A two-stage denoising procedure is developed for data preprocessing, so as to tackle the high noise and disturbance which generally resides in the ECG wave collected by wearable devices. Then the time-frequency spectrum and Poincare plot of the denoised ECG signal are imported into the developed dual-channel neural network for feature extraction and AF detection. On the 2017 PhysioNet/CinC Challenge database, the F1 values were 0.83, 0.90, and 0.75 for AF rhythm and normal rhythm, and other rhythm, respectively. The results well validate the effectiveness of the proposed method for AF detection from a single lead ECG wave, and also indicate its performance advantages over some state-of-the-art counterparts.

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.

An important issue when designing conformal lattice structures is the geometric modeling and prediction of mechanical properties. This paper presents suitable methods for obtaining optimized conformal lattice structures and validating them without the need for high computational power and time, enabling the designer to have quick feedback in the first design phases. A wireframe modeling method based on non-uniform rational basis spline (NURBS) free-form deformation (FFD) that allows conforming a regular lattice structure inside a design space is presented. Next, a previously proposed size optimization method is adopted for optimizing the cross-sections of lattice structures. Finally, two different commercial finite element software are involved for the validation of the results, based on Euler–Bernoulli and Timoshenko beam theories. The findings highlight the adaptability of the NURBS-FFD modeling approach and the reliability of the size optimization method, especially in stretching-dominated cell topologies and load conditions. At the same time, the limitation of the structural beam analysis when dealing with thick beams is noted. Moreover, the behavior of different kinds of lattices was investigated.

International audience; The paper formulates the concept of persistence of excitation for discrete-time linear switched systems, and provides sufficient conditions for an input signal to be persistently exciting. Persistence of excitation is formulated as a property of the input signal, and it is not tied to any specific identification algorithm. The results of the paper rely on realization theory and on the notion of Markov-parameters for linear switched systems.

Cities worldwide are facing the challenge of digital information governance: different and competing service providers operating Internet of Things (IoT) devices often produce and maintain large amounts of data related to the urban environment. As a consequence, the need for interoperability arises between heterogeneous and distributed information, to enable city councils to make data-driven decisions and to provide new and effective added value services to their citizens. In this paper, we present the Urban IoT suite of ontologies, a common conceptual model to harmonise the data exchanges between municipalities and service providers, with specific focus on the sharing mobility and electric mobility domains.

Modality translation grants diagnostic value to wearable devices by translating signals collected from low-power sensors to their highly-interpretable counterparts that are more familiar to healthcare providers. For instance, bio-impedance (Bio-Z) is a conveniently collected modality for measuring physiological parameters but is not highly interpretable. Thus, translating it to a well-known modality such as electrocardiogram (ECG) improves the usability of Bio-Z in wearables. Deep learning solutions are well-suited for this task given complex relationships between modalities generated by distinct processes. However, current algorithms usually train a single model for all users that results in ignoring cross-user variations. Retraining for new users usually requires collecting abundant labeled data, which is challenging in healthcare applications. In this paper, we build a modality translation framework to translate Bio-Z to ECG by learning personalized user information without training several independent architectures. Furthermore, our framework is able to adapt to new users in testing using very few samples. We design a meta-learning framework that contains shared and user-specific parameters to account for user differences while learning from the similarity amongst user signals. In this model, a meta-learner approximated by a neural network learns how to learn user-specific parameters and can efficiently update them in testing. Our experiments show that the proposed model reduces the percentage root mean square difference (PRD) by 41% compared to training a single model for all users and by 36% compared to training independent models for each user. When adapting the model to new users, our model outperforms fine-tuning a pre-trained model through back-propagation by 40% using as few as two new samples in testing.

Two wheeled Self balancing robots have become more popular in recent times and used in many applications, commonly used in transportation as these balancing robots are faster and apparently stable. Balancing is achieved by using controllers tuned for the system. Inverted pendulum principle is used in these robots. This paper proposes the use of two control methods, namely Proportional-Integral-Derivative (PID) and Extended PID (EPID), for maintaining the balance of two-wheeled and self-balancing robots, even when slightly tilted, thus preventing them from falling. PID control theory generally depends up on transfer functions, this paper extends the theory using EPID. EPID provides a new perspective on the working principle of PID control and its relationship with other control theories, such as tracking control and disturbance observer. This approach is illustrated using the fundamental principle of inverted pendulum technology. The key advantage of these robots over other mobile robots is their increased stability due to zero turning radius, which allows for smoother rotations during changes in direction.

© 2023 Elsevier B.V.This paper studies the cluster consensus problem for networks with antagonistic interactions modelled by adjacency matrices with negative weights. By introducing an extended digraph representation consisting of purely cooperative interactions with lifting approach, we relate the trajectories of the system to those of an extended system with a positive digraph. The behaviours of agents in a signed network are extracted from its extended digraph. Consequently, the number of clusters and the cluster members are explicitly determined for any signed digraph by using primary and secondary layer subgraph concepts. The relation between the dynamics of a signed system and its extended representation is investigated for first and higher-order systems. The conditions that make both systems stable are stated. Additionally, the control parameters to achieve cluster consensus are derived explicitly for first, second and third order systems. The obtained results for continuous-time networks are subsequently extended to discrete-time networks. Finally, theoretical results are illustrated via numerical examples.

CTS 2021, 16th IFAC Symposium on Control in Transportation Systems, Lille, FRANCE, 08-/06/2021 - 10/06/2021; This paper tackles the real-time Railway Traffic Management Problem (rtRTMP). It is the problem of finding an optimal choice for the train schedules and routes to reduce the delays of trains due to conflicts. We present a new Constraint Based Scheduling (CBS) formulation of the rtRTMP. This new formulation is based on the concept of conditional time-interval variables provided in the Ilog CP-optimizer library. A time-interval variable is the time interval in which an activity is executed, but it can also be a specific value meaning the activity is non-executed. The new formulation exploits this new kind of variables and specific constraint propagation algorithms which contribute to the efficiency of the solution methods. The formulation has been validated with experiments on a large set of instances. The experimental results demonstrate the effectiveness of this new CBS model and show its good performance compared with the state-of-the art RECIFE-MILP algorithm.

Multi-access edge computing (MEC) has been recently considered in challenging environments lacking available terrestrial infrastructures by extending the computing resources to the air for further enhancing the computation capability of the new aerial user equipment (AUE). Additionally, wireless power transfer (WPT) is a promising solution to prolong the battery lifetime of energy-constrained wireless devices like AUEs. In this paper, we investigate the integration of laser-beamed WPT in the high-altitude platform (HAP) aided MEC systems for the HAP-connected AUEs. By discretizing the three-dimensional coverage space of the HAP, we present a multi-tier tile grid-based spatial structure to provide aerial locations for laser charging. With this setup, we identify a new privacy vulnerability caused by the openness during the air-to-air transmission of WPT signaling messages in the presence of a terrestrial adversary. A privacy-aware laser-powered aerial MEC framework is developed that addresses this vulnerability and enhances the location privacy of AUEs for laser WPT. Specifically, the interaction between the HAP as a defender and the adversary in their tile grid allocation as charging locations to AUEs is formulated as a Colonel Blotto game, which models the competition of the players for limited resources over multiple battlefields for a finite time horizon. Moreover, we derive the mixed-strategy Nash equilibria of the tile grid allocation game for both symmetric and asymmetric tile grids between the defender and the adversary. Simulations results show that the proposed framework significantly outperforms the design baselines with a given privacy protection level in terms of system-wide expected total utilities.

This paper considers identification of sparse Volterra systems. Two identification meth- ods based on the almost orthogonal matching pur- suit (AOMP) and the RIVAL (removing irrele- vant variables amidst Lasso iterations) algorithm are proposed. The AOMP algorithm allows one to estimate one non-zero coefficient at a time until all non-zero coefficients are found without losing the optimality and the sparsity, thus avoiding the curse of dimensionality often encountered in Volterra sys- tem identification. However, the conditions for the AOMP are strong. To this end, the RIVAL is pro- posed that solves the set identification and param- eter estimation problems simultaneously with the convergence results, and outperforms the standard Lasso-type algorithms.

Generative adversarial networks (GANs) are a hot research topic recently. GANs have been widely studied since 2014, and a large number of algorithms have been proposed. However, there is few comprehensive study explaining the connections among different GANs variants, and how they have evolved. In this paper, we attempt to provide a review on various GANs methods from the perspectives of algorithms, theory, and applications. Firstly, the motivations, mathematical representations, and structure of most GANs algorithms are introduced in details. Furthermore, GANs have been combined with other machine learning algorithms for specific applications, such as semi-supervised learning, transfer learning, and reinforcement learning. This paper compares the commonalities and differences of these GANs methods. Secondly, theoretical issues related to GANs are investigated. Thirdly, typical applications of GANs in image processing and computer vision, natural language processing, music, speech and audio, medical field, and data science are illustrated. Finally, the future open research problems for GANs are pointed out.

Deep generative models have gained much attention given their ability to generate data for applications as varied as healthcare to financial technology to surveillance, and many more - the most popular models being generative adversarial networks and variational auto-encoders. Yet, as with all machine learning models, ever is the concern over security breaches and privacy leaks and deep generative models are no exception. These models have advanced so rapidly in recent years that work on their security is still in its infancy. In an attempt to audit the current and future threats against these models, and to provide a roadmap for defense preparations in the short term, we prepared this comprehensive and specialized survey on the security and privacy preservation of GANs and VAEs. Our focus is on the inner connection between attacks and model architectures and, more specifically, on five components of deep generative models: the training data, the latent code, the generators/decoders of GANs/ VAEs, the discriminators/encoders of GANs/ VAEs, and the generated data. For each model, component and attack, we review the current research progress and identify the key challenges. The paper concludes with a discussion of possible future attacks and research directions in the field., Comment: To be published in IEEE Transactions on Knowledge and Data Engineering

The recent work Unsupervised Linear Discriminant Analysis (Un-LDA) completes its clustering process during the alternating optimization by converting equivalently the objective and finally using the K-means algorithm. However, the K-means algorithm has its inherent drawbacks. It is hard for the K-means algorithm to deal well with some complex clustering cases where there are too many real clusters or non-convex clusters. In this paper, a novel clustering optimization method is presented to accomplish the clustering process in Un-LDA and the resulting method can be named Un-LDA(CD). Specifically, instead of the K-means algorithm, an elaborately designed coordinate descent algorithm is adopted to obtain the clusters after the objective function goes through a series of simple but deft equivalent conversions. Extensive experiments have demonstrated that the coordinate descent clustering solution for Un-LDA can outperform the original K-means based solution on the tested data sets especially those complex data sets with a pretty large number of real clusters.

With the powerful learning ability of deep convolutional networks, deep clustering methods can extract the most discriminative information from individual data and produce more satisfactory clustering results. However, existing deep clustering methods usually ignore the relationship between the data. Fortunately, the graph convolutional network can handle such relationship, opening up a new research direction for deep clustering. In this paper, we propose a cross-attention based deep clustering framework, named Cross-Attention Fusion based Enhanced Graph Convolutional Network (CaEGCN), which contains four main modules: the cross-attention fusion module which innovatively concatenates the Content Auto-encoder module (CAE) relating to the individual data and Graph Convolutional Auto-encoder module (GAE) relating to the relationship between the data in a layer-by-layer manner, and the self-supervised model that highlights the discriminative information for clustering tasks. While the cross-attention fusion module fuses two kinds of heterogeneous representation, the CAE module supplements the content information for the GAE module, which avoids the over-smoothing problem of GCN. In the GAE module, two novel loss functions are proposed that reconstruct the content and relationship between the data, respectively. Finally, the self-supervised module constrains the distributions of the middle layer representations of CAE and GAE to be consistent. Experimental results on different types of datasets prove the superiority and robustness of the proposed CaEGCN.

Time series anomaly detection (TSAD) is an essential problem faced in several fields, e.g. fault detection, fraud detection, and intrusion detection, etc. Although TSAD is a crucial problem in anomaly detection, few solutions in anomaly detection are suitable for it at present. Recently, some researchers use GAN-based methods such as TAnoGAN and TadGAN to solve TSAD problem. However, problems such as model collapse, low generalization capability and poor accuracy still exist. In this paper, we proposed a Dilated Convolutional Transformer-based GAN (DCT-GAN) to enhance accuracy and improve generalization capability of the model. Specifically, DCT-GAN utilize several generators and a single discriminator to alleviate the mode collapse problem. Each generator consists of a dilated convolutional neural network and a Transformer block to obtain fine-grained and coarse-grained information of the time series, which is a useful component to improve generalization capability. We also use weight-based mechanism to balance these generators. Experiments verify the effectiveness of our method and each part of DCT-GAN.

Choosing a decomposition method for multi-class classification is an important trade-off between efficiency and predictive accuracy. Trying all the decomposition methods to find the best one is too time-consuming for many applications, while choosing the wrong one may result in large loss on predictive accuracy. In this paper, we propose an automatic decomposition method selection approach called ``D-Chooser", which is lightweight and can choose the best decomposition method accurately. D-Chooser is equipped with our proposed difficulty index which consists of sub-metrics including distribution divergence, overlapping regions, unevenness degree and relative size of the solution space. The difficulty index has two intriguing properties: 1) fast to compute and 2) measuring multi-class problems comprehensively. Extensive experiments on real-world multi-class problems show that D-Chooser achieves an accuracy of 83.3% in choosing the best decomposition method. It can choose the best method in just a few seconds, while existing approaches verify the effectiveness of a decomposition method often takes a few hours. We also provide case studies on Kaggle competitions and the results confirm that D-Chooser is able to choose a better decomposition method than the winning solutions.

Image copy detection is an important technology of copyright protection. This paper proposes an efficient hashing method for image copy detection using 2D-2D (two-directional two-dimensional) PCA (Principal Component Analysis). The key is the discovery of the translation invariance of 2D-2D PCA. With the property of translation invariance, a novel model of extracting rotation-invariant low-dimensional features is designed by combining PCT (Polar Coordinate Transformation) and 2D-2D PCA. The PCT can convert an input rotated image to a translation matrix. Since the 2D-2D PCA is invariant to translation, the low-dimensional features learned from the translation matrix are rotation-invariant. Moreover, vector distances of low-dimensional features are stable to common digital operations and thus hash construction with the vector distances is of robustness and compactness. Three open image datasets are exploited to conduct various experiments for validating efficiencies of the proposed method. The results demonstrate that the proposed method is much better than some representative hashing methods in the performances of classification and copy detection.

Influential community search aims to find cohesive subgraphs (communities) with considerable influence. It is a fundamental graph management operator that can play a crucial role in biological network analysis, activity organization, and other real-life applications. Existing research on influential community search is mainly focused on deterministic graphs with the assumption that influences between entities are certain. This assumption is invalid in many cases because it ignores the uncertainty which is an inherent property of influence. Against this backdrop, in this paper, we introduce an uncertain influential community model, namely (k,)-influential community, based on which the influential community search problem over uncertain graphs is formulated. Furthermore, we propose an online approach by integrating a peeling-pruning strategy that can progressively refine the given uncertain graph to find the (k,)-influential communities. To further improve the search performance, two novel indexes, ICU-Index and FICU-Index, are developed to organize the (k,)-influential communities at different probabilistic intervals. The indexes decompose the probabilistic interval into multiple subintervals and based on this, the (k,)-influential communities are divided into different groups in turn. Compared with ICU-Index, FICU-Index requires considerably less space with the introduction of two optimization strategies.

With the continued proliferation of mobile Internet and geo-locating technologies, carpooling as a green transport mode is widely accepted and becoming tremendously popular worldwide. In this paper, we focus on a popular carpooling service called ride hitching, which is typically implemented using a publish/subscribe approach. In a ride hitching service, drivers subscribe ride orders published by riders and continuously receive matching ride orders until one is picked. The current systems (e.g., Didi Hitch) adopt a threshold-based approach to filter out ride orders. That is, a new ride order will be sent to all subscribing drivers whose planned trips can match the ride order within a pre-defined detour threshold. A limitation of this approach is that it is difficult for drivers to specify a reasonable detour threshold in practice. In addressing this problem, we propose a novel top-k subscription query called Top-k Ride Subscription (TkRS) query, which continuously returns the best k ride orders that match drivers' trip plans to them. We propose two efficient algorithms to enable the top-k results maintenance. We also design a novel hybrid index and a two-level buffer to efficiently track the top- $k$ results. Finally, extensive experiments on real-life datasets suggest that our algorithms can achieve desirable performance in practical settings.

The goal of personalized search is to tailor the document ranking list to meet user's individual needs. Previous studies showed users usually look for the information that has been searched before. This is called re-finding behavior which is widely explored in existing personalized search approaches. However, most existing methods for identifying re-finding behavior focus on simple lexical similarities between queries. In this paper, we propose a personalized framework based on hierarchical memory networks (MN) to enhance the identification of the potential re-finding behavior. Specifically, we explore the potential re-finding behaviors of users from two dimensions. (1) Granularity dimension. The framework carries out re-finding identification with external memories from word, sentence, and session levels. (2) Query intent dimension. Query-based re-finding and document-based re-finding are taken into account to cover user's different query intents. To enhance the interaction between different memory slots, we optimize the $READ$ operation of MN with two strategies that utilize the information in memory in a multi-hop way. Endowed with these memory networks, we can enhance user's potential re-finding behaviors and build a fine-grained user model dynamically. Experimental results on two datasets have a significant improvement over baselines, and the optimized $READ$ operation shows better performance.

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.

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)

Temporal point process is widely used for sequential data modeling. In this paper, we focus on the problem of modeling sequential event propagation in graph, such as retweeting by social network users, news transmitting between websites, etc. Given a collection of event propagation sequences, conventional point process model consider only the event history, i.e. embed event history into a vector, not the latent graph structure. We propose a Graph Biased Temporal Point Process (GBTPP) leveraging the structural information from graph representation learning, where the direct influence between nodes and indirect influence from event history is modeled respectively. Moreover, the learned node embedding vector is also integrated into the embedded event history as side information. Experiments on a synthetic dataset and two real-world datasets show the efficacy of our model compared to conventional methods and state-of-the-art., Comment: 9 pages, 6 figures, 2 tables

Birth asphyxia is a major newborn mortality problem in low-resource countries. International guideline provides treatment recommendations; however, the importance and effect of the different treatments are not fully explored. The available data is collected in Tanzania, during newborn resuscitation, for analysis of the resuscitation activities and the response of the newborn. An important step in the analysis is to create activity timelines of the episodes, where activities include ventilation, suction, stimulation etc. Methods: The available recordings are noisy real-world videos with large variations. We propose a two-step process in order to detect activities possibly overlapping in time. The first step is to detect and track the relevant objects, like bag-mask resuscitator, heart rate sensors etc., and the second step is to use this information to recognize the resuscitation activities. The topic of this paper is the first step, and the object detection and tracking are based on convolutional neural networks followed by post processing. Results: The performance of the object detection during activities were 96.97 % (ventilations), 100 % (attaching/removing heart rate sensor) and 75 % (suction) on a test set of 20 videos. The system also estimate the number of health care providers present with a performance of 71.16 %. Conclusion: The proposed object detection and tracking system provides promising results in noisy newborn resuscitation videos. Significance: This is the first step in a thorough analysis of newborn resuscitation episodes, which could provide important insight about the importance and effect of different newborn resuscitation activities, 8 pages

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.

Missing data widely exist in the raw or processed data, implying information loss. In many cases, missing values have to be accurately imputed for further use. In this paper, an extreme case, consecutively missing data in large-length and mainly remaining data in small-length, is discussed for time series varying with operating conditions, very universal in industrial processes. Firstly, to fully utilize the information of remaining data, a similar conditions screening scheme is provided, efficient to improve imputation accuracy. Then, multiple receding imputation via Gaussian process regression (GPR) and long short term memory (LSTM) neural network are proposed, deducing generic multiple combination imputation and bidirectional imputation structures. At last, applied for data imputation of extremely missing wind power data, condition-dependent on wind speed, imputation effects of the proposed methods are carefully compared. Simulation results reveal effectiveness of these methods to impute missing data under the extreme case, laying very important foundation for data-driven applications.

Unsupervised feature selection can play an important role in addressing the issue of processing massive unlabelled high-dimensional data in the domain of machine learning and data mining. This paper presents a novel unsupervised feature selection method, referred to as Multi-Group Adaptive Graph Representation (MGAGR). Different from existing methods, the relationship between features is explored via the global similarity matrix, which is reconstructed by local similarities of multiple groups. Specifically, the similarity of a feature compared to other features can be represented by the linear combination of all the local similarities. The local similarity of a representative group is given a large weight to reconstruct the global similarity. Besides, an iterative algorithm is given to solve the optimization problem, in which the global similarity matrix, its corresponding reconstruction weights and the self-representation matrix are iteratively improved. Experimental results on 8 benchmark datasets demonstrates that the proposed method outperforms the state-of-the-art unsupervised feature selection methods in terms of clustering performance. The source code is available at: https://github.com/misteru/MGAGR.

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.

Leaf disease recognition using image processing and deep learning techniques is currently a vibrant research area. Most studies have focused on recognizing diseases from images of whole leaves. This approach limits the resulting models’ ability to estimate leaf disease severity or identify multiple anomalies occurring on the same leaf. Recent studies have demonstrated that classifying leaf diseases based on individual lesions greatly enhances disease recognition accuracy. In those studies, however, the lesions were laboriously cropped by hand. This study proposes a semi-automatic algorithm that facilitates the fast and efficient preparation of datasets of individual lesions and leaf image pixel maps to overcome this problem. These datasets were then used to train and test lesion classifier and semantic segmentation Convolutional Neural Network (CNN) models, respectively. We report that GoogLeNet’s disease recognition accuracy improved by more than 15% when diseases were recognized from lesion images compared to when disease recognition was done using images of whole leaves. A CNN model which performs semantic segmentation of both the leaf and lesions in one pass is also proposed in this paper. The proposed KijaniNet model achieved state-of-the-art segmentation performance in terms of mean Intersection over Union (mIoU) score of 0.8448 and 0.6257 for the leaf and lesion pixel classes, respectively. In terms of mean boundary F1 score, the KijaniNet model attained 0.8241 and 0.7855 for the two pixel classes, respectively. Lastly, a fully automatic algorithm for leaf disease recognition from individual lesions is proposed. The algorithm employs the semantic segmentation network cascaded to a GoogLeNet classifier for lesion-wise disease recognition. The proposed fully automatic algorithm outperforms competing methods in terms of its superior segmentation and classification performance despite being trained on a small dataset.

Today there is a rapid development taking place in phenotyping of plants using non-destructive image based machine vision techniques. Machine vision based plant phenotyping ranges from single plant trait estimation to broad assessment of crop canopy for thousands of plants in the field. Plant phenotyping systems either use single imaging method or integrative approach signifying simultaneous use of some of the imaging techniques like visible red, green and blue (RGB) imaging, thermal imaging, chlorophyll fluorescence imaging (CFIM), hyperspectral imaging, 3-dimensional (3-D) imaging or high resolution volumetric imaging. This paper provides an overview of imaging techniques and their applications in the field of plant phenotyping. This paper presents a comprehensive survey on recent machine vision methods for plant trait estimation and classification. In this paper, information about publicly available datasets is provided for uniform comparison among the state-of-the-art phenotyping methods. This paper also presents future research directions related to the use of deep learning based machine vision algorithms for structural (2-D and 3-D), physiological and temporal trait estimation, and classification studies in plants.

Recent neural architectures in sequence labeling have yielded state-of-the-art performance on single domain data such as newswires. However, they still suffer from (i) requiring massive amounts of training data to avoid overfitting; (ii) huge performance degradation when there is a domain shift in the data distribution between training and testing. To make a sequence labeling system more broadly useful, it is crucial to reduce its training data requirements and transfer knowledge to other domains. In this paper, we investigate the problem of domain adaptation for sequence labeling under homogeneous and heterogeneous settings. We propose MetaSeq, a novel meta-learning approach for domain adaptation in sequence labeling. Specifically, MetaSeq incorporates meta-learning and adversarial training strategies to encourage robust, general and transferable representations for sequence labeling. The key advantage of MetaSeq is that it is capable of adapting to new unseen domains with a small amount of annotated data from those domains. We extensively evaluate MetaSeq on named entity recognition, part-of-speech tagging and slot filling under homogeneous and heterogeneous settings. The experimental results show that MetaSeq achieves state-of-the-art performance against eight baselines. Impressively, MetaSeq surpasses the in-domain performance using only 16.17% and 7% of target domain data on average for homogeneous settings, and 34.76%, 24%, 22.5% of target domain data on average for heterogeneous settings.

Engagement and retention are widely acknowledged problems in computer science and more general higher education. The need to develop programming skills is increasingly ubiquitous, but especially so in computer science where it is one of the core competencies. Learning to write code is a particularly challenging skill to master, which can make retention and success even more difficult. We attempt to address student engagement within an introductory programming module by attempting to motivate students using a gamified interactive programming tutor application that provides immediate feedback on the student’s work. In this paper, we describe the design of the gamified programming tutor application, along with a related topology to characterize student engagement. We discuss the design of the software, the gamified elements, and the structured question design. We evaluate the engagement with the gamified programming tutor of two cohorts of students in the first year of a computer science programme, with over two hundred students taking part. We attempt to frame this engagement in terms of frequency, duration, and intensity of interactions, and compare these engagement metrics with module performance. Additionally, we present quantitative and qualitative data from a survey of students about their experience using the programming tutor application to demonstrate the efficacy of this approach.

Internet of Things (IoT) has brought changes in many fields by joining physical space with the cyber space. The IoT devices are becoming increasingly complex. With the rapid deployment of cameras, tasks in IoT like visual information are more important, but IoT devices have limited computing resources, including power, computing ability, storage, etc. Some tasks that might be perfectly normal to perform on a computer would be rather challenging on an IoT device. Therefore, how to maintain acceptable performance while minimizing resources is becoming a more consequential part in IoT. In the paper, we aim to solve the problem of object detection and tracking in IoT while minimizing resources. The traditional algorithms need to use convolutional neural network (CNN) to identify different objects in each frame, and then determine the tracking target from identified objects, which typically requires a lot of computing resources. By incorporating spatial attention, and multi-domain network, we proposed a novel algorithm named as Spatial Attention Powered Multi-Domain Network (SA-MDNet). By adding spatial attention mechanism to the original MDNet model, and using multi class cross entropy loss, we are able to distinguish the background and the target in different video sequences effectively and efficiently. This novel algorithm achieves similar performance on the OTB 50/100/2013 datasets compared to several state-of-art models, while uses only a fraction of the memory compared to MDNet.

Machine Learning (ML) algorithms can effectively perform analytics and inferences for building smart applications, such as early detection of diseases in the Industrial Internet of Things (IIoT) and smart healthcare systems. The main components of ML, including training and testing phases, can be decomposed into microservices to improve service quality, along with fast implementation and integration with the edge and cloud services. However, the execution of ML in an edge-cloud environment introduces privacy risks to data owners (e.g., patients). In this paper, we present a privacy-preserving machine learning (ML) framework by leveraging microservice technology for safeguarding healthcare IIoT systems. More specifically, we develop a microservice-based distributed privacy-preserving technique using Differential Privacy (DP) and Radial Basis Function Network (RBFN) to balance between privacy protection and model performance in edge networks. We conduct extensive experiments to evaluate the performance of the proposed technique. The results revealed that DP has a significant influence on the model’s performance and achieves more than 90% accuracy with an epsilon value over 0.4, enhancing data protection and analytics through the implementation of microservices.

Agriculture is an important sector that plays an essential role in the economic development of a country. Each year farmers face numerous challenges in producing good quality crops. One of the major reasons behind the failure of the harvest is the use of unscientific agricultural practices. Moreover, every year enormous crop loss is encountered either by pests, specific diseases, or natural disasters. It raises a strong concern to employ sustainable advanced technologies to address agriculture-related issues. In this paper, a sustainable real-time crop disease detection and prevention system, called CROPCARE is proposed. The system integrates mobile vision, Internet of Things (IoT), and Google Cloud services for sustainable growth of crops. The primary function of the proposed intelligent system is to detect crop diseases through the CROPCARE -mobile application. It uses Super-Resolution Convolution Network (SRCNN) and the pretrained model MobileNet-V2 to generate a decision model trained over various diseases. To maintain sustainability, the mobile app is integrated with IoT sensors and Google Cloud services. The proposed system also provides recommendations that help farmers know about current soil conditions, weather conditions, disease prevention methods, etc. It supports both Hindi and English dictionaries for the convenience of the farmers. The proposed approach is validated by using the PlantVillage dataset. The obtained results confirm the performance strength of the proposed system.

Fault diagnostics involving the Internet of Things (IoT) sensors and edge devices is a challenging task due to their limited energy and computational capabilities. Another challenge concerning IoT sensors or devices is the incursion of noise when used in an industrial environment. The noisy samples affect the decision support system that could lead to financial and operational losses. This paper proposes a Noisy Encoder using Artificial Intelligence of Things (NEAT) architecture for fault diagnosis in IoT edge devices. NEAT combines autoencoders and Inception module to co-train the clean and noisy samples for solving the said problem. Experimental results on benchmark datasets reveal that the NEAT architecture is noise resilient in comparison to the existing works. Furthermore, we also show that the NEAT architecture has lightweight characteristics as it yields a lower number of parameters, weight storage, training, and testing times that support its real-life applicability in an Industrial IoT environment.