Search

Studies have indicated that focusing solely on pairwise interactions between two nodes disregards the associativity among multi-nodes in the network's local structure. This associativity can be seen as dependencies among nodes, where certain edges' presence depends on the path leading to it. Examinations on diverse datasets have approved that the variable order of chained dependencies allows for the preservation of structure information, which enables the reconstruction of the original network into a Higher-Order Network (HON) with improved quality of network representation. This paper proposes a Density-based Higher-Order Network Embedding (DHONE) algorithm, which integrates the concept of higher-order density into the network-embedding process in order to classify the contribution of different orders of dependencies. Through the construction of a novel and effective higher-order adjacency matrix, DHONE steadily improves the accuracy of network representation learning. Experimental results demonstrate DHONEs proficiency in improving embedding accuracy and overall algorithm robustness. Furthermore, grounded in the concept of higher-order density proposed herein, numerous dependencies have been discerned within the network generated from trajectories, potentially indicating the role of multi-node structures in networks. [ABSTRACT FROM AUTHOR]

Abstract This study addresses challenges related to privacy issues in utilizing medical data, particularly the protection of personal information. To overcome this obstacle, the research focuses on data synthesis using real-world time-series generative adversarial networks (RTSGAN). A total of 53,005 data were synthesized using the dataset of 15,799 patients with colorectal cancer. The results of the quantitative evaluation of the synthetic data’s quality are as follows: the Hellinger distance ranged from 0 to 0.25; the train on synthetic, test on real (TSTR) and train on real, test on synthetic (TRTS) results showed an average area under the curve of 0.99 and 0.98; a propensity mean squared error was 0.223. The synthetic and real data were similar in the qualitative methods including t-SNE and histogram analyses. The application of synthetic data in predicting five-year survival in colorectal cancer patients demonstrates comparable performance to models based on real data. This study employs distance to closest records and membership inference test to assess potential privacy exposure, revealing minimal risk. This study demonstrated that it is feasible to synthesize medical data, including time-series data, using the RTSGAN, and the synthetic data can be evaluated to accurately reflect the characteristics of real data through quantitative and qualitative methods as well as by utilizing real-world artificial intelligence models.

This study addresses challenges related to privacy issues in utilizing medical data, particularly the protection of personal information. To overcome this obstacle, the research focuses on data synthesis using real-world time-series generative adversarial networks (RTSGAN). A total of 53,005 data were synthesized using the dataset of 15,799 patients with colorectal cancer. The results of the quantitative evaluation of the synthetic data's quality are as follows: the Hellinger distance ranged from 0 to 0.25; the train on synthetic, test on real (TSTR) and train on real, test on synthetic (TRTS) results showed an average area under the curve of 0.99 and 0.98; a propensity mean squared error was 0.223. The synthetic and real data were similar in the qualitative methods including t-SNE and histogram analyses. The application of synthetic data in predicting five-year survival in colorectal cancer patients demonstrates comparable performance to models based on real data. This study employs distance to closest records and membership inference test to assess potential privacy exposure, revealing minimal risk. This study demonstrated that it is feasible to synthesize medical data, including time-series data, using the RTSGAN, and the synthetic data can be evaluated to accurately reflect the characteristics of real data through quantitative and qualitative methods as well as by utilizing real-world artificial intelligence models. [ABSTRACT FROM AUTHOR]

The discrete element method (DEM) is a vital numerical approach for analyzing the mechanical behavior of elastoplastic wet sand. However, parameter uncertainty persists within the mapping between constitutive relationships and inherent model parameters. We propose a Parameter calibration neural network based on Attention, Retention, and improved Transformer for Sequential data (PartsNet), which effectively captures the nonlinear mechanical behavior of wet sand and obtains the optimal parameter combination for the Edinburgh elasto-plastic adhesion constitutive model. Variational autoencoder-based principal component ordering is employed by PartsNet to reduce the high-dimensional dynamic response and extract critical parameters along with their weights. Gated recurrent units are combined with a novel sparse multi-head attention mechanism to process sequential data. The fusion information is delivered by residual multilayer perceptron, achieving the association between sequential response and model parameters. The errors in response data generated by calibrated parameters are quantified by PartsNet based on adaptive differentiation and Taylor expansion. Remarkable calibration capabilities are exhibited by PartsNet across six evaluation indicators, surpassing seven other deep learning approaches in the ablation test. The calibration accuracy of PartsNet reaches 91.29%, and MSE loss converges to 0.000934. The validation experiments and regression analysis confirmed the generalization capability of PartsNet in the calibration of wet sand. The improved sparse attention mechanism optimizes multi-head attention, resulting in a convergence speed of 21.25%. PartsNet contributes to modeling and simulating the precise mechanical properties of complex elastoplastic systems and offers valuable insights for diverse engineering applications. [ABSTRACT FROM AUTHOR]

Due to the demand for temporary rapid grid connection in renewable energy power plants, the topology structure of T-connected power lines has been widely used in the power grid. In this three-terminal system, fault localization is difficult because of traditional impedance-based or traveling wave-based fault localization methods; the three-terminal data should be synchronized and communicated. Since different terminal assets belong to different enterprises, it is actually difficult to maintain good synchronization between them. Therefore, in practical applications, the fault location of T-connected power lines often fails. This article proposes a single terminal fault location method for a T-connection power line to address this issue. It is based on the fact that the local topology of the T-connected power line in the healthy phase remains unchanged during the fault-clearing process. It utilizes the sequential current and voltage data changes generated by the sequential tripping ping emitted by the circuit breaker from different terminals to describe the constant topology of the healthy phase as an equation and calculates the accurate fault location after solving the equation. The Levenberg–Marquardt algorithm was used to calculate fault distance and transition resistance, and the effectiveness of this method was verified through simulation. [ABSTRACT FROM AUTHOR]

Soil constitutive model parameters can be identified from triaxial test data. The identification is frequently performed by fitting a constitutive model to triaxial test data from a purely statistical or probabilistic perspective based on an assumption that measurements are independent. This ignores the sequential attribute of triaxial test data and is, hence, not realistic. In this paper, a probabilistic state space model (SSM) is proposed for undrained triaxial test data analysis, with which the sequential data attribute is explicitly considered and a constitutive model (physics) is linked to the SSM model (statistics) in a natural way. Then, constitutive model parameters can be rigorously learned under a Bayesian framework based on the SSM without artificially augmenting them into hidden variables of SSM. Without loss of generality, the modified Cam Clay (MCC) model is taken as an example to develop the SSM and to demonstrate the proposed Bayesian framework, which is illustrated using simulated and real-life data. Results from the proposed Bayesian framework based on the SSM include not only the best estimates of MCC model parameters but also their posterior distributions for quantifying the identification uncertainty, based on which the identifiability of MCC model parameters is discussed and highlighted. [ABSTRACT FROM AUTHOR]

This paper presents a study on connection-blocking prediction in Elastic Optical Networks (EONs) using Convolutional Neural Networks (CNNs). In EONs, connections are established and torn down dynamically to fulfill the instantaneous requirements of the users. The dynamic allocation of the connections may cause spectrum fragmentation and lead to network performance degradation as connection blocking increases. Predicting potential blocking situations can be helpful during EON operations. For example, this prediction could be used in real networks to trigger proper spectrum defragmentation mechanisms at suitable moments, thereby enhancing network performance. Extensive simulations over the well-known NSFNET (National Science Foundation Network) backbone network topology were run by generating realistic traffic patterns. The obtained results are later used to train the developed machine learning models, which allow the prediction of connection-blocking events. Resource use was continuously monitored and recorded during the process. Two different Convolutional Neural Network models, a 1D CNN (One-Dimensional Convolutional Neural Network) and 2D CNN (Two-Dimensional Convolutional Neural Network), are proposed as the predicting methods, and their behavior is compared to other conventional models based on an SVM (Support Vector Machine) and KNN (K Nearest Neighbors). The results obtained show that the proposed 2D CNN predicts blocking with the best accuracy (92.17%), followed by the SVM, the proposed 1D CNN, and KNN. Results suggest that 2D CNN can be helpful in blocking prediction and might contribute to increasing the efficiency of future EON networks. [ABSTRACT FROM AUTHOR]

Continuous-time state-space models (SSMs) are flexible tools for analysing irregularly sampled sequential observations that are driven by an underlying state process. Corresponding applications typically involve restrictive assumptions concerning linearity and Gaussianity to facilitate inference on the model parameters via the Kalman filter. In this contribution, we provide a general continuous-time SSM framework, allowing both the observation and the state process to be non-linear and non-Gaussian. Statistical inference is carried out by maximum approximate likelihood estimation, where multiple numerical integration within the likelihood evaluation is performed via a fine discretization of the state process. The corresponding reframing of the SSM as a continuous-time hidden Markov model, with structured state transitions, enables us to apply the associated efficient algorithms for parameter estimation and state decoding. We illustrate the modelling approach in a case study using data from a longitudinal study on delinquent behaviour of adolescents in Germany, revealing temporal persistence in the deviation of an individual's delinquency level from the population mean. [ABSTRACT FROM AUTHOR]

Various areas of educational research are interested in the transitions between different states--or events--in sequential data, with the goal of understanding the significance of these transitions; one notable example is affect dynamics, which aims to identify important transitions between affective states. Unfortunately, several works have uncovered issues with the metrics and procedures commonly used to analyze these transitions. As such, our goal in this work is to address these issues by outlining an alternative procedure that is based on the use of marginal models. We begin by looking at the specific mechanisms responsible for a recently discovered statistical bias with several metrics used in sequential data analysis. After giving a theoretical explanation for the issue, we show that the marginal model procedure appears to adjust for this bias. Next, a related problem is that the common practice of removing transitions to repeated states has been shown to have unintended side-effects--to account for this issue, we develop a method for extending the marginal model procedure to this specific type of analysis. Finally, in a recent study evaluating the problem of multiple comparisons and sequential data analysis, the Benjamini-Hochberg (BH) procedure, a commonly used approach to control for false discoveries, did not perform as expected. By applying a technique from the biostatistics and epidemiology literature, we show that the performance of the BH procedure, when used with the marginal model method, can be brought back to its expected level. In all of our analyses, we evaluate the proposed method by both running simulations and using actual student data. The results indicate that the marginal model procedure seemingly compensates for the problems observed with other transition metrics, thus resulting in more accurate estimates of the importance of transitions between states. [ABSTRACT FROM AUTHOR]

Deep Learning (DL) for monitoring slowly evolving degradation processes typically involves overcoming data drift, complexity, and unavailability issues resulting from dynamic and harsh conditions and the rarity of labeled failure patterns, respectively. While degradation patterns are mostly hidden in such complex data, observation-based DL is prone to producing uncertain predictions and/or overfit models during the training process. This problem is usually caused by the insignificance of certain data representations. Therefore, and particularly due to the sequential nature of data in such a degradation process, it is necessary to consider neighboring observations to judge the accuracy of a representation or improve it. In this context, instead of providing traditional observation-based learning philosophy, this paper presents data-driven sequential mapping while additionally showing that health indices can also be represented as a vector of sequential data and not as a single regressor output changing a model's architecture. Using a dataset generated from a mathematical model mimicking bearing degradation life cycles and responding to the aforementioned three main challenges, a comparative study built on investigating observation-based and sequence-based learning paths was conducted. According to a well-defined visual and numerical evaluation criterion, a sequence-based methodology reflects a better understanding of data representations through parameter tuning, achieving better approximation and generalization. Such results support the necessity of such a learning mechanism, especially for sequential data, dealing with some sort of correlation and degrading controversy. The files required to reproduce the findings of this work have been made publicly available. [ABSTRACT FROM AUTHOR]

The discrete element method (DEM) is a vital numerical approach for analyzing the mechanical behavior of elastoplastic wet sand. However, parameter uncertainty persists within the mapping between constitutive relationships and inherent model parameters. We propose a Parameter calibration neural network based on Attention, Retention, and improved Transformer for Sequential data (PartsNet), which effectively captures the nonlinear mechanical behavior of wet sand and obtains the optimal parameter combination for the Edinburgh elasto-plastic adhesion constitutive model. Variational autoencoder-based principal component ordering is employed by PartsNet to reduce the high-dimensional dynamic response and extract critical parameters along with their weights. Gated recurrent units are combined with a novel sparse multi-head attention mechanism to process sequential data. The fusion information is delivered by residual multilayer perceptron, achieving the association between sequential response and model parameters. The errors in response data generated by calibrated parameters are quantified by PartsNet based on adaptive differentiation and Taylor expansion. Remarkable calibration capabilities are exhibited by PartsNet across six evaluation indicators, surpassing seven other deep learning approaches in the ablation test. The calibration accuracy of PartsNet reaches 91.29%, and MSE loss converges to 0.000934. The validation experiments and regression analysis confirmed the generalization capability of PartsNet in the calibration of wet sand. The improved sparse attention mechanism optimizes multi-head attention, resulting in a convergence speed of 21.25%. PartsNet contributes to modeling and simulating the precise mechanical properties of complex elastoplastic systems and offers valuable insights for diverse engineering applications.

Due to the demand for temporary rapid grid connection in renewable energy power plants, the topology structure of T-connected power lines has been widely used in the power grid. In this three-terminal system, fault localization is difficult because of traditional impedance-based or traveling wave-based fault localization methods; the three-terminal data should be synchronized and communicated. Since different terminal assets belong to different enterprises, it is actually difficult to maintain good synchronization between them. Therefore, in practical applications, the fault location of T-connected power lines often fails. This article proposes a single terminal fault location method for a T-connection power line to address this issue. It is based on the fact that the local topology of the T-connected power line in the healthy phase remains unchanged during the fault-clearing process. It utilizes the sequential current and voltage data changes generated by the sequential tripping ping emitted by the circuit breaker from different terminals to describe the constant topology of the healthy phase as an equation and calculates the accurate fault location after solving the equation. The Levenberg–Marquardt algorithm was used to calculate fault distance and transition resistance, and the effectiveness of this method was verified through simulation.

We identify the free half shuffle algebra of Schützenberger [31] with an algebra of real-valued functionals on paths, where the half shuffle emulates the integration of a functional against another. We then provide two, to our knowledge, new identities in arity 3 involving its commutator (area), and show that these are sufficient to recover the Zinbiel and Tortkara identities introduced by Dzhumadil'daev [11]. We then use these identities to provide a simple proof of the main result of Diehl et al. [8] , namely that any element of the free half shuffle algebra can be expressed as a polynomial over iterated areas. Moreover, we consider minimal sets of Hall iterated integrals defined through the recursive application of the half shuffle product to Hall trees. Leveraging the duality between this set of Hall integrals and classical Hall bases of the free Lie algebra, we prove using combinatorial arguments that any element of the free half shuffle algebra can be written uniquely as a polynomial over Hall integrals. We interpret this result as a structure theorem for streamed information, loosely analogous to the unique prime factorisation of integers, allowing to split any real valued function on streamed data into two parts: a first that extracts and packages the streamed information into recursively defined atomic objects (Hall integrals), and a second that evaluates a polynomial function in these objects without further reference to the original stream. The question of whether a similar result holds if Hall integrals are replaced by Hall areas is left as an open conjecture. Finally, we construct a canonical, but to our knowledge, new decomposition of the free half shuffle algebra as shuffle power series in the greatest letter of the original alphabet with coefficients in a sub-algebra freely generated by a new alphabet with an infinite number of letters. We use this construction to provide a second proof of our structure theorem. [ABSTRACT FROM AUTHOR]

As one of the most popular machine learning methods, random forests have been successfully applied to different data analysis tasks such as classification, regression and cluster analysis. Recently, the random forest clustering method has received much attention due to its simplicity, accuracy and robustness. However, we cannot directly employ the random forest clustering algorithm to solve the discrete sequence clustering problem because of the lack of explicit features and "negative" sequences. In this paper, we propose a new random forest clustering algorithm for discrete sequences. The proposed method firstly injects a set of decoy sequences and then constructs the random forest in a supervised and adaptive manner by generating features on the fly. Experimental results on real data sets show that the proposed method can achieve better performance than those state-of-the-art discrete sequence clustering algorithms. • A discrete sequence clustering method based on random forest is proposed. • We solve the unsupervised sequence clustering problem in a "supervised" manner. • Experimental results demonstrate the feasibility and effectiveness of our method. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) has recently emerged as a powerful tool with versatile applications spanning various domains. AI replicates human intelligence processes through machinery and computer systems, finding utility in expert systems, image and speech recognition, machine vision, and natural language processing (NLP). One notable area with limited exploration pertains to using deep learning models, specifically Recurrent Neural Networks (RNNs), for predicting water quality in wastewater treatment plants (WWTPs). RNNs are purpose-built for handling sequential data, featuring a feedback mechanism. However, standard RNNs may exhibit limitations in accommodating both short-term and long-term dependencies when addressing intricate time series problems. The solution to this challenge lies in adopting Long Short-Term Memory (LSTM) cells, known for their inherent memory management through a 'forget gate' mechanism. In general, LSTM architecture demonstrates superior performance. WWTP data represent a historical series influenced by fluctuating environmental conditions. This study employs simple RNNs and LSTM architecture to construct prediction models for effluent parameters, systematically assessing their performance through various training data scenarios and model architectures. The primary objective was to determine the most suitable WWTP dataset model. The study revealed that an epoch setting of 50 and a batch size of 100 yielded the lowest training time and root mean square error (RMSE) values for both RNN and LSTM models. Furthermore, when these models are applied to predict effluent parameters, they exhibit precise RMSE values for all parameters. The study results can be applied to detect potential upsets in WWTP operations. [ABSTRACT FROM AUTHOR]

With the advancement of sensing technologies, sensor data collected over time have become more useful for detecting anomalies in underlying processes and systems. Sensor data are often affected by contextual variables, such as equipment settings, and can have different patterns, even in normal states depending on the contextual variables. Motivated by this problem, we propose a contextual anomaly detection method for multivariate time series data. We first build a prediction model using training data consisting of only normal observations, and then perform anomaly detection based on the prediction errors for future observations. The prediction model is based on a long short-term memory (LSTM) network that can flexibly model complex relationships between variables as well as temporal correlations between successive time points using the high expressive power of deep recurrent neural networks. In particular, to incorporate the contextual information while ensuring that it does not propagate over time but affects the response data only at specific target time points, we extend the standard LSTM by adding a layer for the contextual variables separately for each time step. The performance of the proposed method was verified with several open-source datasets and a real dataset from a global tire company. [ABSTRACT FROM AUTHOR]

Due to the success and growing job market of deep learning (DL), students and researchers from many areas are interested in learning about DL technologies. Visualization has been used as a modern medium during this learning process. However, despite the fact that sequential data tasks, such as text and function analysis, are at the forefront of DL research, there does not yet exist an educational visualization that covers recurrent neural networks (RNNs). Additionally, the benefits and trade-offs between using visualization environments and conventional learning material for DL have not yet been evaluated. To address these gaps, we propose exploRNN, the first interactively explorable educational visualization for RNNs. exploRNNis accessible online and provides an overview of the training process of RNNs at a coarse level, as well as detailed tools for the inspection of data flow within LSTM cells. In an empirical between-subjects study with 37 participants, we investigate the learning outcomes and cognitive load of exploRNN compared to a classic text-based learning environment. While learners in the text group are ahead in superficial knowledge acquisition, exploRNN is particularly helpful for deeper understanding. Additionally, learning with exploRNN is perceived as significantly easier and causes less extraneous load. In conclusion, for difficult learning material, such as neural networks that require deep understanding, interactive visualizations such as exploRNN can be helpful. [ABSTRACT FROM AUTHOR]

Copyright of Fire Ecology is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the progress of human daily interaction activities and the development of industrial society, a large amount of media data and sensor data become accessible. Humans collect these multi-source data in chronological order, called multi-view sequential data (MvSD). MvSD has numerous potential application domains, including intelligent transportation, climate science, health care, public safety and multimedia, etc. However, as the volume and scale of MvSD increases, the traditional machine learning methods become difficult to withstand such large-scale data, and it is no longer appropriate to use hand-craft features to represent these complex data. In addition, there is no general framework in the process of mining multi-view relationships and integrating multi-view information. In this paper, We first introduce four common data types that constitute MvSD, including point data, sequence data, graph data, and raster data. Then, we summarize the technical challenges of MvSD. Subsequently, we review the recent progress in deep learning technology applied to MvSD. Meanwhile, we discuss how the network represents and learns features of MvSD. Finally, we summarize the applications of MvSD in different domains and give potential research directions. [ABSTRACT FROM AUTHOR]

This paper presents a study on connection-blocking prediction in Elastic Optical Networks (EONs) using Convolutional Neural Networks (CNNs). In EONs, connections are established and torn down dynamically to fulfill the instantaneous requirements of the users. The dynamic allocation of the connections may cause spectrum fragmentation and lead to network performance degradation as connection blocking increases. Predicting potential blocking situations can be helpful during EON operations. For example, this prediction could be used in real networks to trigger proper spectrum defragmentation mechanisms at suitable moments, thereby enhancing network performance. Extensive simulations over the well-known NSFNET (National Science Foundation Network) backbone network topology were run by generating realistic traffic patterns. The obtained results are later used to train the developed machine learning models, which allow the prediction of connection-blocking events. Resource use was continuously monitored and recorded during the process. Two different Convolutional Neural Network models, a 1D CNN (One-Dimensional Convolutional Neural Network) and 2D CNN (Two-Dimensional Convolutional Neural Network), are proposed as the predicting methods, and their behavior is compared to other conventional models based on an SVM (Support Vector Machine) and KNN (K Nearest Neighbors). The results obtained show that the proposed 2D CNN predicts blocking with the best accuracy (92.17%), followed by the SVM, the proposed 1D CNN, and KNN. Results suggest that 2D CNN can be helpful in blocking prediction and might contribute to increasing the efficiency of future EON networks.

Classification of long sequential data is an important Machine Learning task and appears in many application scenarios. Recurrent Neural Networks, Transformers, and Convolutional Neural Networks are three major techniques for learning from sequential data. Among these methods, Temporal Convolutional Networks (TCNs) which are scalable to very long sequences have achieved remarkable progress in time series regression. However, the performance of TCNs for sequence classification is not satisfactory because they use a skewed connection protocol and output classes at the last position. Such asymmetry restricts their performance for classification which depends on the whole sequence. In this work, we propose a symmetric multi-scale architecture called Circular Dilated Convolutional Neural Network (CDIL-CNN), where every position has an equal chance to receive information from other positions at the previous layers. Our model gives classification logits in all positions, and we can apply a simple ensemble learning to achieve a better decision. We have tested CDIL-CNN on various long sequential datasets. The experimental results show that our method has superior performance over many state-of-the-art approaches. The model and experiments are available at (https://github.com/LeiCheng-no/CDIL-CNN). [ABSTRACT FROM AUTHOR]

A recurrent neural network (RNN) is a widely used deep-learning network for dealing with sequential data. Imitating a dynamical system, an infinite-width RNN can approximate any open dynamical system in a compact domain. In general, deep narrow networks with bounded width and arbitrary depth are more effective than wide shallow networks with arbitrary width and bounded depth in practice; however, the universal approximation theorem for deep narrow structures has yet to be extensively studied. In this study, we prove the universality of deep narrow RNNs and show that the upper bound of the minimum width for universality can be independent of the length of the data. Specifically, we show a deep RNN with ReLU activation can approximate any continuous function or Lp function with the widths dx + dy + 3 and max{dx + 1; dy}, respectively, where the target function maps a finite sequence of vectors in ℝdx to a finite sequence of vectors in ℝdy. We also compute the additional width required if the activation function is sigmoid or more. In addition, we prove the universality of other recurrent networks, such as bidirectional RNNs. Bridging a multi-layer perceptron and an RNN, our theory and technique can shed light on further research on deep RNNs. [ABSTRACT FROM AUTHOR]

This article explains the factors that led to the use of a hybrid data collection tool—i.e., a single questionnaire designed to collect both quantitative and qualitative data—in two different research projects that focused on the relation between the labour market trajectories of young people and the use and accumulation of network social capital in these trajectories. The article describes the characteristics of this tool and the methodological challenges posed by its use. The advantages and disadvantages of this specific type of data collection are also addressed. Among the main advantages, the improvement of data quality and the overarching picture obtained of the career path and use of personal networks are highlighted. The most important downside found is the amount of time needed in the interview, which shows the need to pay attention to the balance between quantitative and qualitative elements in the structure of the questionnaire. [ABSTRACT FROM AUTHOR]

Higher-order networks aim at improving the classical network representation of trajectories data as memory-less order 1 Markov models. To do so, locations are associated with different representations or "memory nodes" representing indirect dependencies between visited places as direct relations. One promising area of investigation in this context is variable-order network models as it was suggested by Xu et al. that random walk-based mining tools can be directly applied on such networks. In this paper, we focus on clustering algorithms and show that doing so leads to biases due to the number of nodes representing each location. To address them, we introduce a representation aggregation algorithm that produces smaller yet still accurate network models of the input sequences. We empirically compare the clustering found with multiple network representations of real-world mobility datasets. As our model is limited to a maximum order of 2, we discuss further generalizations of our method to higher orders. [ABSTRACT FROM AUTHOR]

Deep Learning (DL) for monitoring slowly evolving degradation processes typically involves overcoming data drift, complexity, and unavailability issues resulting from dynamic and harsh conditions and the rarity of labeled failure patterns, respectively. While degradation patterns are mostly hidden in such complex data, observation-based DL is prone to producing uncertain predictions and/or overfit models during the training process. This problem is usually caused by the insignificance of certain data representations. Therefore, and particularly due to the sequential nature of data in such a degradation process, it is necessary to consider neighboring observations to judge the accuracy of a representation or improve it. In this context, instead of providing traditional observation-based learning philosophy, this paper presents data-driven sequential mapping while additionally showing that health indices can also be represented as a vector of sequential data and not as a single regressor output changing a model’s architecture. Using a dataset generated from a mathematical model mimicking bearing degradation life cycles and responding to the aforementioned three main challenges, a comparative study built on investigating observation-based and sequence-based learning paths was conducted. According to a well-defined visual and numerical evaluation criterion, a sequence-based methodology reflects a better understanding of data representations through parameter tuning, achieving better approximation and generalization. Such results support the necessity of such a learning mechanism, especially for sequential data, dealing with some sort of correlation and degrading controversy. The files required to reproduce the findings of this work have been made publicly available.

Artificial Intelligence (AI) has recently emerged as a powerful tool with versatile applications spanning various domains. AI replicates human intelligence processes through machinery and computer systems, finding utility in expert systems, image and speech recognition, machine vision, and natural language processing (NLP). One notable area with limited exploration pertains to using deep learning models, specifically Recurrent Neural Networks (RNNs), for predicting water quality in wastewater treatment plants (WWTPs). RNNs are purpose-built for handling sequential data, featuring a feedback mechanism. However, standard RNNs may exhibit limitations in accommodating both short-term and long-term dependencies when addressing intricate time series problems. The solution to this challenge lies in adopting Long Short-Term Memory (LSTM) cells, known for their inherent memory management through a ‘forget gate’ mechanism. In general, LSTM architecture demonstrates superior performance. WWTP data represent a historical series influenced by fluctuating environmental conditions. This study employs simple RNNs and LSTM architecture to construct prediction models for effluent parameters, systematically assessing their performance through various training data scenarios and model architectures. The primary objective was to determine the most suitable WWTP dataset model. The study revealed that an epoch setting of 50 and a batch size of 100 yielded the lowest training time and root mean square error (RMSE) values for both RNN and LSTM models. Furthermore, when these models are applied to predict effluent parameters, they exhibit precise RMSE values for all parameters. The study results can be applied to detect potential upsets in WWTP operations.

The segmentation of sequential data can be formulated as a clustering problem, where the data samples are grouped into non-overlapping clusters with the constraint that all members of each cluster are in a successive order. A popular algorithm for optimally solving this problem is dynamic programming (DP), which has quadratic computation and memory requirements. Given that sequences in practice are too long, this algorithm is not a practical approach. Although many heuristic algorithms have been proposed to approximate the optimal segmentation, they have no guarantee on the quality of their solutions. In this paper, we take a differentiable approach to alleviate the aforementioned issues. First, we introduce a novel sigmoid-based regularization to smoothly approximate the constraints. Combining it with objective of the balanced kernel clustering, we formulate a differentiable model termed Kernel clustering with sigmoid-based regularization (KCSR), where the gradient-based algorithm can be exploited to obtain the optimal segmentation. Second, we develop a stochastic variant of the proposed model. By using the stochastic gradient descent algorithm, which has much lower time and space complexities, for optimization, the second model can perform segmentation on overlong data sequences. Finally, for simultaneously segmenting multiple data sequences, we slightly modify the sigmoid-based regularization to further introduce an extended variant of the proposed model. Through extensive experiments on various types of data sequences performances of our models are evaluated and compared with those of the existing methods. The experimental results validate advantages of the proposed models. Our Matlab source code is available on github.

Many data analytics applications rely on temporal data, generated (and possibly acquired) sequentially for online analysis. How to release this type of data in a privacy-preserving manner is of great interest and more challenging than releasing one-time, static data. Because of the (potentially strong) temporal correlation within the data sequence, the overall privacy loss can accumulate significantly over time; an attacker with statistical knowledge of the correlation can be particularly hard to defend against. An idea that has been explored in the literature to mitigate this problem is to factor this correlation into the perturbation/noise mechanism. Existing work, however, either focuses on the offline setting (where perturbation is designed and introduced after the entire sequence has become available), or requires a priori information on the correlation in generating perturbation. In this study we propose an approach where the correlation is learned as the sequence is generated, and is used for estimating future data in the sequence. This estimate then drives the generation of the noisy released data. This method allows us to design better perturbation and is suitable for real-time operations. Using the notion of differential privacy, we show this approach achieves high accuracy with lower privacy loss compared to existing methods. [ABSTRACT FROM AUTHOR]

Copyright of Papers: Revista de Sociologia is the property of Universitat Autonoma de Barcelona and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Agent-based microsimulation has become the standard to analyze intelligent transportation systems, using disaggregate travel demand data for entire populations, data that are not typically readily available. Population synthesis approaches are thus needed. We present Composite Travel Generative Adversarial Network (CTGAN), a novel deep generative model to estimate the underlying joint distribution of a population, that is capable of reconstructing composite synthetic agents having tabular (e.g. age and sex) as well as sequential mobility data (e.g. trip trajectory and sequence). The CTGAN model is compared with other recently proposed methods such as the Variational Autoencoders (VAE) method, which has shown success in high dimensional tabular population synthesis. We evaluate the performance of the synthesized outputs based on distribution similarity, multi-variate correlations and spatio-temporal metrics. The results show the consistent and accurate generation of synthetic populations and their tabular and spatially sequential attributes, generated over varying spatial scales and dimensions. [ABSTRACT FROM AUTHOR]

RBC (Red Blood Cell) membrane is a highly elastic structure, and proper modelling of this elasticity is essential for biomedical applications that involve computational experiments with blood flow. In this work, we present a new method for estimating one of the key parameters of red blood cell elasticity, which uses a neural network trained on the simulation outputs. We test classic LSTM (Long-Short Term Memory) architecture for the time series regression task, and we also experiment with novel CNN-LSTM (Convolutional Neural Network) architecture. We paid special attention to investigating the impact of the way the three-dimensional training data are reduced to their two-dimensional projections. Such a comparison is possible thanks to working with simulation outputs that are equivalently defined for all dimensions and their combinations. The obtained results can be used as recommendations for an appropriate way to record real experiments for which the reduced dimension of the acquired data is essential. [ABSTRACT FROM AUTHOR]

Along with the rapid expansion of information technology and digitalization of health data, there is an increasing concern on maintaining data privacy while garnering the benefits in the medical field. Two critical challenges are identified: First, medical data is naturally distributed across multiple local sites, making it difficult to collectively train machine learning models without data leakage. Second, in medical applications, data are often collected from different sources and views, resulting in heterogeneity and complexity that requires reconciliation. In this article, we present a generic Federated Multi-view Learning (FedMV) framework for multi-view data leakage prevention. Specifically, we apply this framework to two types of problems based on local data availability: Vertical Federated Multi-view Learning (V-FedMV) and Horizontal Federated Multi-view Learning (H-FedMV). We experimented with real-world keyboard data collected from BiAffect study. Our results demonstrated that the proposed approach can make full use of multi-view data in a privacy-preserving way, and both V-FedMV and H-FedMV perform better than their single-view and pairwise counterparts. Besides, the framework can be easily adapted to deal with multi-view sequential data. We have developed a sequential model (S-FedMV) that takes sequence of multi-view data as input and demonstrated it experimentally. To the best of our knowledge, this framework is the first to consider both vertical and horizontal diversification in the multi-view setting, as well as their sequential federated learning. [ABSTRACT FROM AUTHOR]