Time series data pervades multiple domains, yet in real-world applications, there frequently exists a deficiency of labels to ascertain effective representations and enable efficient classification. In this work, we introduce SMDE, a unique time series contrastive learning framework, diverging from conventional techniques that predominantly concentrate on instance-level contrast. SMDE leverages signal decomposition and ensemble methodologies, enhancing our focus on localized mode alterations, within time series signals. We further introduce the global signal consistency and intrinsic mode consistency mechanisms to promote the robust learning of global and local attributes. To ensure more efficient convergence, we present the DE Circle loss furnished with an adaptive weighting mechanism, founded on global signal consistency and intrinsic mode consistency principles. The SMDE framework is designed to be applicable to both univariate and multivariate time series analysis, indicating its potential for a wide range of temporal data applications. Experiments on 128 univariate UCR datasets reveal that SMDE improves the average accuracy by 4.73% over existing techniques. Additionally, our experiments on 29 multivariate UEA datasets demonstrate an average accuracy improvement of 7.42% compared to current methodologies. Moreover, through extensive semi-supervised experimentation, SMDE demonstrates superior performance in 15 disparate semi-supervised configurations, attaining an equivalent performance level to supervised training with 100% labeled data, even with a minimal portion of the labels. The code is publicly available at https://github.com/haobinlaosi/smde.

Natural gas pipeline leaks pose severe risks, leading to substantial economic losses and potential hazards to human safety. In this study, we develop an accurate model for the early prediction of pipeline leaks. To the best of our knowledge, unlike previous anomaly detection, this is the first application to use internal pipeline data for early prediction of leaks. The modeling process addresses two main challenges: long-term dependencies and sample imbalance. First, we introduce a dilated convolution-based prediction model to capture long-term dependencies, as dilated convolution expands the model's receptive field without added computational cost. Second, to mitigate sample imbalance, we propose the MKTCN model, which incorporates the Kolmogorov-Arnold Network as the fully connected layer in a dilated convolution model, enhancing network generalization. Finally, we validate the MKTCN model through extensive experiments on two real-world datasets. Results demonstrate that MKTCN outperforms in generalization and classification, particularly under severe data imbalance, and effectively predicts leaks up to 5000 seconds in advance. Overall, the MKTCN model represents a significant advancement in early pipeline leak prediction, providing robust generalization and improved modeling of the long-term dependencies inherent in multi-dimensional time-series data.

Learning and development, or L&D, plays an important role in talent management, which aims to improve the knowledge and capabilities of employees through a variety of performance-oriented training activities. Recently, with the rapid development of enterprise management information systems, many research efforts and industrial practices have been devoted to building personalized employee training course recommender systems. Nevertheless, a widespread challenge is how to provide explainable recommendations with the consideration of different learning motivations from talents. To this end, we propose CKGE, a contextualized knowledge graph (KG) embedding approach for developing an explainable training course recommender system. A novel perspective of CKGE is to integrate both the contextualized neighbor semantics and high-order connections as motivation-aware information for learning effective representations of talents and courses. Specifically, in CKGE, for each entity pair (i.e., the talent-course pair), we first construct a meta-graph, including the neighbors of each entity and the meta-paths between entities as motivation-aware information. Then, we develop a novel KG-based Transformer, which can serialize entities and paths in the meta-graph as a sequential input, with the specially designed relational attention and structural encoding mechanisms to better model the global dependence of KG structured data. Meanwhile, the local path mask prediction can effectively reveal the importance of different paths. As a result, CKGE not only can make precise predictions but also can discriminate the saliencies of meta-paths in characterizing corresponding preferences. Extensive experiments on real-world and public datasets clearly validate the effectiveness and interpretability of CKGE compared with state-of-the-art baselines.

Every organization has organizational networks for exchange of ideas and information. It is believed that organizational network analysis (ONA) can help the business be more effective. While considerable research efforts have been made for visualizing and analyzing relationships in organizational networks, it lacks a holistic way to model the complex social structures and rich semantic information of these networks. Indeed, employee behaviors can occur across different communication platforms, such as email and instant messaging systems, which naturally lead to the multiplex structure of organizational social networks. Meanwhile, it is also a challenge to model the impact of semantic information, such as employee attributes and organization charts, and the collaboration relationships of employees. To this end, in this paper, we propose a Multiplex Attentive Network Embedding (MANE) approach for modeling organizational social networks in a holistic way. Specifically, we first develop a multiple attributed random walk approach to jointly model multiple networks, with the integration of external work information. Then, we preserve the network structure by maximizing the probability of predicting the central node based on the surrounding context nodes. In particular, we introduce an attention mechanism to assign a weight to each context node in the training process, according to its attributed relation and structural relation with the central node by utilizing the k-core algorithm and the shortest path algorithm. In this way, the embedding results can be kept consistent with their structural relationships. Furthermore, to solve some department-level tasks, we introduce an attentive relational transition method to learn the representation of departments in the organizational networks. Finally, we evaluate the performance of MANE with extensive experiments on real-world data for three important talent management tasks, namely employee performance prediction, employee turnover prediction and department performance prediction. We also conduct a link prediction task to validate the effectiveness of employee embedding. Experimental results clearly show the effectiveness and interpretability of MANE for organizational network analysis.

As an emerging initiative of proactive human resource management, employee turnover prediction is critically important for employers to retain talents and avoid the loss of intellectual capital. While considerable research efforts have been made in this direction, most of them only focus on modeling the within-company career trajectories of employees where the influence of external job market has been largely neglected. To this end, in this paper, we propose an enhanced framework of employee turnover prediction by jointly modeling the turnover clues from both internal and external views. Specifically, from the external-market view, we construct a heterogeneous graph which connects the employees with external job markets through shared skills. In this way, we can capture the potential popularity of employees in external markets specific to skills. Meanwhile, from the internal-company view, we design a graph convolutional network with hierarchical attention mechanism to capture the influence of organizational structure (e.g., superiors, subordinates, and peers) and colleagues with similar skills. Furthermore, both modules are modeled with Bidirectional LSTM and survival analysis to learn effective and dynamic representations of employee turnover prediction. Finally, we conduct extensive experiments on a large-scale real-world talent dataset with state-of-the-art methods, which clearly demonstrate the effectiveness of our approach as well as some interesting findings that could help us understand the employee turnover patterns, such as different impacts of external systems and collaborators from different groups.

As an emerging initiative of proactive human resource management, employee turnover prediction is critically important for employers to retain talents and avoid the loss of intellectual capital. While considerable research efforts have been made in this direction, most of them only focus on modeling the within-company career trajectories of employees where the influence of external job market has been largely neglected. To this end, in this paper, we propose an enhanced framework of employee turnover prediction by jointly modeling the turnover clues from both internal and external views. Specifically, from the external-market view, we construct a heterogeneous graph which connects the employees with external job markets through shared skills. In this way, we can capture the potential popularity of employees in external markets specific to skills. Meanwhile, from the internal-company view, we design a graph convolutional network with hierarchical attention mechanism to capture the influence of organizational structure (e.g., superiors, subordinates, and peers) and colleagues with similar skills. Furthermore, both modules are modeled with Bidirectional LSTM and survival analysis to learn effective and dynamic representations of employee turnover prediction. Finally, we conduct extensive experiments on a large-scale real-world talent dataset with state-of-the-art methods, which clearly demonstrate the effectiveness of our approach as well as some interesting findings that could help us understand the employee turnover patterns, such as different impacts of external systems and collaborators from different groups.

Most topic modeling approaches are based on the bag-of-words assumption, where each word is required to be conditionally independent in the same document. As a result, both of the generative story and the topic formulation have totally ignored the semantic dependency among words, which is important for improving the semantic comprehension and model interpretability. To this end, in this paper, we revisit the task of topic modeling by transforming each document into a directed graph with word dependency as edges between word nodes, and develop a novel approach, namely Graph Neural Topic Model (GNTM). Specifically, in GNTM, a well-defined probabilistic generative story is designed to model both the graph structure and word sets with multinomial distributions on the vocabulary and word dependency edge set as the topics. Meanwhile, a Neural Variational Inference (NVI) approach is proposed to learn our model with graph neural networks to encode the document graphs. Besides, we theoretically demonstrate that Latent Dirichlet Allocation (LDA) can be derived from GNTM as a special case with similar objective functions. Finally, extensive experiments on four benchmark datasets have clearly demonstrated the effectiveness and interpretability of GNTM compared with state-of-the-art baselines.

Community search aims at finding densely connected subgraphs for query vertices in a graph. While this task has been studied widely in the literature, most of the existing works only focus on finding homogeneous communities rather than heterogeneous communities with different labels. In this paper, we motivate a new problem of cross-group community search, namely Butterfly-Core Community (BCC), over a labeled graph, where each vertex has a label indicating its properties and an edge between two vertices indicates their cross relationship. Specifically, for two query vertices with different labels, we aim to find a densely connected cross community that contains two query vertices and consists of butterfly networks, where each wing of the butterflies is induced by a k-core search based on one query vertex and two wings are connected by these butterflies. We first develop a heuristic algorithm achieving 2-approximation to the optimal solution. Furthermore, we design fast techniques of query distance computations, leader pair identifications, and index-based BCC local explorations. Extensive experiments on seven real datasets and four useful case studies validate the effectiveness and efficiency of our BCC and its multi-labeled extension models.

Intelligent path planning is a significant tool for field of industrial robot. This field has attracted the attention of numerous researchers due to the great market demands, broad application prospects, and large potential development. Due to the limitation of neighborhood, the path search by the original A* algorithm is more likely to fail, and the solved path may contain too many local paths. In this study, an improved A* algorithm is proposed to solve the robot path planning problem. The first improvement of the advanced method is the local path between the current node and the goal node, which is planned before the next search in the neighborhood of the current node. And the local path will be adopted directly if it is safe and collisionless. The second advantage of this method is the utilization of post-processing stage to optimize the resulting path, by straightening the local path to reduce the number of local paths as well as the path length. In order to verify the theoretical advantages of the improved A* algorithm, a series of two-dimensional figures of the robot task was presented in this paper. In addition, some comparative experiments in the virtual and real robot manipulator platform are performed to examine the improved A* algorithm. Experimental results show that the search success rate of the improved A* algorithm is higher than the original A* algorithm, along with a shorter and smoother path could be obtained by the improved A* algorithm. Therefore, the success rate of robot path planning and the optimal extent of the robot path are effectively improved by the improved A* algorithm.

Accurate state-of-charge (SoC) estimation is crucial to guarantee the safety and reliability of lithium-ion batteries. This paper aimed to develop an advanced battery estimation method for electric vehicles based on the grey model without the need of a high-fidelity battery model demanding high computation power. The metabolic grey model (MGM) introduced metabolism mechanism to adjust the model parameters according to the evolving operating status and conditions and estimate the state of charge. To further validate the feasibility of the proposed method, the analog acquisition, communication system, and SoC estimation algorithms were programmed to embed within a LabVIEW platform. The performance of the proposed SoC estimation with MGM algorithm was finally investigated with a battery-in-loop platform under different dynamic loading profiles. The experimental results indicated that the MGM can estimate SoC that involved small samples and poor information in real time, with the maximum errors of no over 4% under various loading conditions.

Aiming at the problems of the DASH technology in the initial delay of video playback, the number and duration time which the video is buffered again and the switching frequency between different quality video, an improved QoE-based rate-adaptive switching algorithm is proposed. The algorithm reduces the initial delay of the video by using the lowest bit rate video clip as the initial play file. By designing a fast start algorithm, it can improve the video rate as soon as the current bandwidth environment is satisfied. The algorithm converts the video into multiple rate video, so that the again video buffer phenomenon will not appear when the average bandwidth of the network is greater than the minimum rate video, and the quality of the video playback can be improved in the case of the minimum initial delay, and the average quality of the video can be improved at the lowest initial delay. In order to effectively reduce the average switching times of video rate, the algorithm determines whether to switch the video rate by judging the current buffer state and the average bandwidth over a period of time. Experimental results show that the algorithm can reduce the number of again video buffering and the switching frequency between different quality video, and improved the quality of experience (QoE) of the user to DASH service.

The semantic intimacy of relations in many real-world networks (e.g., social, biological, and communication networks) can be modeled by weighted edges in which the more semantically intimate relations between the nodes translate to smaller edge weights. Recently, the problem of community search that aims to find the cohesive groups containing a given set of query nodes has attracted a great deal of attention. However, the bulk of literature on community search problem assumes a simple unweighted input graph, ignoring how semantically intimate the nodes have in retrieved communities. The discovered communities may have a highly cohesive structure, while they perform poorly in the semantic of intimate connections. In this paper, we investigate a novel problem of Querying Intimate-Core Groups (QICG): given a weighted undirected graph G, a set of query nodes Q and a positive integer k, to find a connected subgraph of G in which each node has at least k neighbors, and the sum of weights on its edges is minimum among all such subgraphs. We show that the QICG problem is NP-hard. We develop efficient algorithms based on several practical heuristic strategies to enhance the retrieval efficiency. Extensive experiments are conducted on real-world datasets to evaluate efficiency and effectiveness of proposed algorithms. The results confirm that our intimate-core group model outperforms state-of-the-art models in weighted graphs.

The wireless networks based on the IEEE 802.15.4a CSS (chirp-spread-spectrum) PHY are expected to provide accurate ranging. However, the problem is that the measured distances are not only noisy but also biased, which becomes more serious in non-line-of-sight situation. To improve the accuracy of ranging, two methods are used to estimate the positive bias, including state augmentation technique and separate-bias estimation. Then the bias estimation can be used to correct the measured distance. Experiments conducted with Nanotron CSS wireless nodes in indoor-environment validate the algorithm actually. The effectiveness and features of the filtering algorithms are analyzed with the support of the experiment results.