The rapid expansion of gaming industry requires advanced recommender systems tailored to its dynamic landscape. Existing Graph Neural Network (GNN)-based methods primarily prioritize accuracy over diversity, overlooking their inherent tradeoff. To address this, we previously proposed CPGRec, a balance-oriented gaming recommender system. However, CPGRec fails to account for critical disparities in player–game interactions, which carry varying significance in reflecting players’ personal preferences and may exacerbate over-smoothness issues inherent in GNN-based models. Moreover, existing approaches underutilize the reasoning capabilities and extensive knowledge of large language models (LLMs) in addressing these limitations. To bridge this gap, we propose two new modules. First, Preference-informed Edge Reweighting (PER) module assigns signed edge weights to qualitatively distinguish significant player interests and disinterests while then quantitatively measuring preference strength to mitigate over-smoothing in graph convolutions. Second, Preference-informed Representation Generation (PRG) module leverages LLMs to generate contextualized descriptions of games and players by reasoning personal preferences from comparing global and personal interests, thereby refining representations of players and games. Experiments on two Steam datasets demonstrate CPGRec+’s superior accuracy and diversity over state-of-the-art models. The code is accessible at https://github.com/HsipingLi/CPGRec-Plus .

Low-cost accelerometers play a crucial role in modern society due to their advantages of small size, ease of integration, wearability, and mass production, making them widely applicable in automotive systems, aerospace, and wearable technology. However, this widely used sensor suffers from severe accuracy and range limitations. To this end, we propose a honed-energy regularized and optimal supervised GAN (HEROS-GAN), which transforms low-cost sensor signals into high-cost equivalents, thereby overcoming the precision and range limitations of low-cost accelerometers. Due to the lack of frame-level paired low-cost and high-cost signals for training, we propose an Optimal Transport Supervision (OTS), which leverages optimal transport theory to explore potential consistency between unpaired data, thereby maximizing supervisory information. Moreover, we propose a Modulated Laplace Energy (MLE), which injects appropriate energy into the generator to encourage it to break range limitations, enhance local changes, and enrich signal details. Given the absence of a dedicated dataset, we specifically establish a Low-cost Accelerometer Signal Enhancement Dataset (LASED) containing tens of thousands of samples, which is the first dataset serving to improve the accuracy and range of accelerometers and is released in Github. Experimental results demonstrate that a GAN combined with either OTS or MLE alone can surpass the previous signal enhancement SOTA methods by an order of magnitude. Integrating both OTS and MLE, the HEROS-GAN achieves remarkable results, which doubles the accelerometer range while reducing signal noise by two orders of magnitude, establishing a benchmark in the accelerometer signal processing.

This article innovatively combines the empirical distribution characteristics of random fuzzy variables to propose a new Wasserstein distributionally robust equilibrium optimization method and effectively applies to an electric vehicle routing problem with contactless delivery (EVRPCD). The proposed method characterizes customer demand and travel time in EVRPCD as random fuzzy variables with ambiguous probability distributions. Moreover, this studied EVRPCD integrates the location decision of the contactless delivery station and the routing decision of the electric vehicle, thus forming a bi-level optimization. Meanwhile, a tolerant load coefficient and an idle loss cost are introduced into the established bi-level optimization model to describe the safety and economic effects of vehicle overloading and underloading, respectively. Importantly, the proposed method generates Wasserstein ambiguity sets to effectively achieve the theoretical characterization of the ambiguous probability distribution of random fuzzy variables in EVRPCD. As the proposed method faces significant computational challenges, this article theoretically deduces its computable reformulation via utilizing the dual theory and the credibility measure method. The computable reformulation realizes the solvability of the model via transforming it into a mixed integer programming with a piecewise penalty function and multiple conditional constraints. An interactive iteration-based algorithm is then given to solve the reconstructed model numerically. The sensitivity analysis and comparative experimental results reveal the effectiveness of the proposed method. Experimental results show that the proportion of vehicle overweight may be reduced by appropriately increasing the penalty and the proposed method pays a small price of distributional robustness to resist the ambiguous probability distributions of random fuzzy variables.

In an increasingly digital world, there is an unprecedented demand in intelligent society for biometric recognition systems that balance security with convenience. Traditional methods, such as passwords and PINs, are vulnerable to breaches and impose the burden of remembering multiple credentials. To this end, we propose a handwriting verification technology leveraging inertial sensors embedded in wearable devices (e.g., smartphones). Handwriting biometrics offer enhanced security as unique writing patterns are inherently resistant to replication and forgery. However, this approach faces two critical challenges: Identity verification independent of written content, and generalizability to unseen writers during deployment. We therefore devise a feature-guided zero-shot learning (FGZSL) framework, which constructs a unique feature vector for each sample and then performs identity verification by comparing these feature vectors. For the first challenge, we design an aim focuser, a module that filters out irrelevant content from the data features, allowing the FGZSL to focus on identity-specific information rather than writing content. For the second challenge, we design a plug-and-play Rényi-entropy-based representation regularization, which constructs informative and discriminative features for seen categories during training. These features serve as bases for representing unseen categories during testing. We contribute the first inertial identity detection dataset, publicly available on GitHub, containing 39 800 training samples and 10 000 test samples. Extensive experiments demonstrate that the FGZSL framework outperforms existing methods in both seen and unseen categories, but also sets a new standard for secure and reliable identity authentication using inertial sensors.

As motion-sensing components, multimodal inertial sensors composed of accelerometers and gyroscopes are recognized for their compact size, low cost, and broad applications in wearable and smart devices, but they are affected by severe noise. Wavelet transform is renowned for its flexibility in analyzing signals due to its diverse wavelet bases, allowing it to adapt to different signal characteristics. However, the diverse signal noises challenge wavelet allocation. Moreover, the modal differences between acceleration and gyroscope signals make it difficult to share the same wavelet, adding complexity to the wavelet allocation for multimodal signals. To this end, we propose an OT-Mamba framework, which leverages Mamba to extract signal features. Mamba is specifically designed to handle ultra-long sequences, allowing it to capture long-range temporal dependencies for better wavelet selection. Considering the heterogeneity and potential synergy between the accelerometer and gyroscope signals, an optimal transport interaction is proposed to mine their relationship for collaborative wavelet selection. The proposed OT-Mamba combines the reliability of wavelet-based methods and the flexibility of deep learning approaches. As a weakly supervised method, OT-Mamba achieves superior performance compared to existing methods (including fully supervised ones) and outperforms the current state-of-the-art method by an order of magnitude across all quantitative metrics and downstream tasks.

As attitude and motion sensing components, inertial sensors are widely used in various portable devices, covering consumer electronics, sports health, aerospace, etc. But the severe intrinsic errors of inertial sensors heavily restrain their function implementation, especially the advanced functionality, including motion trajectory recovery and motion semantic recognition, which attracts considerable attention. As a mainstream signal processing method, wavelet is hailed as the mathematical microscope of signal due to the plentiful and diverse wavelet basis functions. However, complicated noise types and application scenarios of inertial sensors make selecting wavelet basis perplexing. To this end, we propose a wavelet dynamic selection network (WDSNet), which intelligently selects the appropriate wavelet basis for variable inertial signals. In addition, existing deep learning architectures excel at extracting features from input data but neglect to learn the characteristics of target categories, which is essential to enhance the category awareness capability, thereby improving the selection of wavelet basis. Therefore, we propose a category representation mechanism (CRM), which enables the network to extract and represent category features without increasing trainable parameters. Furthermore, CRM transforms the common fully connected network into category representations, which provide closer supervision to the feature extractor than the far and trivial one-hot classification labels. We call this process of imposing interpretability on a network and using it to supervise the feature extractor the feature supervision mechanism, and its effectiveness is demonstrated experimentally and theoretically in this paper. The enhanced inertial signal can perform impracticable tasks with regard to the original signal, such as trajectory reconstruction. Both quantitative and visual results show that WDSNet outperforms the existing methods. Remarkably, WDSNet, as a weakly-supervised method, achieves the state-of-the-art performance of all the compared fully-supervised methods.

Emotion-cause pair extraction (ECPE) aims to extract emotions and their corresponding cause from a document. The previous works have made great progress. However, there exist two major issues in existing works. First, most existing works mainly focus on the semantic relation between the emotion clause and cause clause, ignoring their inner statistical relation in representation space. Second, the existing works are sensitive to the relative position between the emotion clause and cause clause, which damages the model's robustness. To address the two issues, we propose a hierarchical contrastive learning framework (HCL-ECPE), which hierarchically performs contrastive learning on representation from two levels. The first level is inter-clause contrastive learning (ICCL), which performs between emotion clause and cause clause through mutual information maximization. The second level is intra-pair contrastive learning (IPCL), which performs between clause representation and pair representation through contrastive predictive coding (CPC). HCL-ECPE integrates ICCL and IPCL modules to explore the statistical relations between the emotion clause, cause clause, and their constructed emotion-cause pair from the perspective of mutual information, thereby improving the model performance and robustness. Experimental results on two public datasets, ECPED and RECCON, demonstrate that HCL-ECPE outperforms the most competitive baselines. Furthermore, ICCL and IPCL are orthogonal to the existing model, and introducing them into the current models updates state-of-the-art performance.

Inertial sensors, as motion-sensing components, are widely used in inertial navigation, aerospace, and consumer electronics. Their wide applications and severe errors form a sharp contradiction, which attracts considerable attention. Wavelet is hailed as the mathematical signal microscope due to the diverse wavelet basis functions. However, complicated noise types and application scenarios of inertial sensors make selecting wavelet basis perplexing. To this end, we propose a wavelet encoding network (WENet), which intelligently selects the appropriate wavelet for variable inertial signals by representing wavelet characteristics through the devised category representation mechanism (CRM). Furthermore, CRM introduces a feature supervision effect, which imposes interpretability on a black-box network and forces it to provide direct supervision for other network structures. This supervision strategy is closer and more effective than the supervision provided by the output end, which is far and needs to go through backpropagation. The proposed WENet has the reliability of the model-driven method and the flexibility of the data-driven method. As a weakly supervised method, the WENet achieves the best performance among all signal improvement methods, including fully supervised ones. After being enhanced by WENet, the low-cost sensor signal can perform accurate spatial trajectory reconstruction, which was once considered an impossible task.

Graph reservoir computing (GraphRC) gains increasing attention by virtue of its high training efficiency. However, since GraphRC is developed without knowledge of its internal mechanism, it cannot be fully trusted to deploy in practice. Although there are some existing approaches that can be extended to interpret GraphRC, the specific role played by each neuron (i.e., reservoir node) of GraphRC is far less explored. To address this issue, the latent short-term memory property of each reservoir node of GraphRC is qualitatively characterized to unravel its role in predicting the graph signal, thereby enabling an interpretable GraphRC. Specifically, we first deduce the equivalence between the GraphRC and conventional reservoir computing (RC). Then, the underlying memory properties of the GraphRC and its reservoir nodes can be characterized in theory by the multisource reachability among the reservoir nodes in the transformed RC. Moreover, the distinct temporal patterns hidden in reservoir nodes are identified, and then, an attention mechanism based on the identified temporal patterns is deployed in the GraphRC to improve its performance. In addition, the effectiveness of the interpretability for GraphRC and improved GraphRC is verified on the Lorenz-96 spatiotemporal dynamical system. The experimental results of the Lorenz-96 spatiotemporal chaotic system and three real-world traffic datasets demonstrate that the improved GraphRC is superior to original GraphRC and can achieve prediction performance comparable to the state-of-the-art baseline models, but with much less training cost.

Emotion-cause pair extraction (ECPE) task aims to extract all the pairs of emotions and their causes from an unannotated emotion text. The previous works usually extract the emotion-cause pairs from two perspectives of emotion and cause. However, emotion extraction is more crucial to the ECPE task than cause extraction. Motivated by this analysis, we propose an end-to-end emotion-cause extraction approach oriented toward emotion prediction (EPO-ECPE), aiming to fully exploit the potential of emotion prediction to enhance emotion-cause pair extraction. Considering the strong dependence between emotion prediction and emotion-cause pair extraction, we propose a synchronization mechanism to share their improvement in the training process. That is, the improvement of emotion prediction can facilitate the emotion-cause pair extraction, and then the results of emotion-cause pair extraction can also be used to improve the accuracy of emotion prediction simultaneously. For the emotion-cause pair extraction, we divide it into genuine pair supervision and fake pair supervision, where the genuine pair supervision learns from the pairs with more possibility to be emotion-cause pairs. In contrast, fake pair supervision learns from other pairs. In this way, the emotion-cause pairs can be extracted directly from the genuine pair, thereby reducing the difficulty of extraction. Experimental results show that our approach outperforms the 13 compared systems and achieves new state-of-the-art performance.

Multimodal sentiment analysis (MSA) and emotion recognition in conversation (ERC) are key research topics for computers to understand human behaviors.From a psychological perspective, emotions are the expression of affect or feelings during a short period, while sentiments are formed and held for a longer period.However, most existing works study sentiment and emotion separately and do not fully exploit the complementary knowledge behind the two.In this paper, we propose a multimodal sentiment knowledge-sharing framework (UniMSE) that unifies MSA and ERC tasks from features, labels, and models.We perform modality fusion at the syntactic and semantic levels and introduce contrastive learning between modalities and samples to better capture the difference and consistency between sentiments and emotions.Experiments on four public benchmark datasets, MOSI, MOSEI, MELD, and IEMO-CAP, demonstrate the effectiveness of the proposed method and achieve consistent improvements compared with state-of-the-art methods.

This paper is devoted to make a framework for studying a class of uncertain differential equations called Z-differential equations. In order to achieve the purpose, we first introduce four basic operations on Z+-numbers based on semigranular function. Then, the limit and continuity concepts of a Z-number-valued function are given, under a definition of a metric on the space of Z+-numbers. Moreover, the concepts of Z-differentiability, Z-integral, and Z-Laplace transform of a Z-number-valued function are introduced. In addition, by giving some theories proved in this paper, a basis for calculus-Z-calculus-is established. We further give theories based on which existence and uniqueness of Zdifferential equations are investigated. A conceptual unity between Z-differential equations and Z+-numbers is also shown. The conceptual unity demonstrates that a Z-differential equation may be expressed as a bimodal differential equation combining a fuzzy differential equation (FDE) and a random differential equation. Moreover, the concept of a bimodal cut called (s, μ)-cut is introduced and its relation to other new concepts such as acceptable time and acceptable information area is explained. Using an example, the application of Z-differential equations in medicine is clarified. It is demonstrated that Z-differential equations outperform FDEs in making a decision under uncertainty.

In this paper, a class of uncertain linear dynamical systems called fuzzy fractional linear dynamical systems is investigated. The aim is to find control inputs to keep the states of the fuzzy fractional dynamical systems near the zero in an optimal manner. The optimality criterion is in a form of a granular fuzzy integral whose integrand is a quadratic function of the state variables and control inputs. The fuzzy fractional dynamical system is described using fuzzy fractional differential equations (FFDEs). In order to achieve the aim, an effective approach for solving FFDEs should be at disposal. Due to some restrictions imposed by the previous approaches dealing with FFDEs, a new approach is proposed. The proposed approach is based on the granular derivative and the so-called relative-distance-measure fuzzy interval arithmetic. New definitions of fuzzy fractional derivatives and integral called left and right granular Riemann-Liouville fuzzy fractional derivatives, left and right granular Caputo fuzzy fractional derivatives, and the left and right granular fuzzy fractional integral are also presented. In addition, the concepts of granular fuzzy partial derivative and granular fuzzy chain rule are introduced. By the approximations of the granular fuzzy fractional integral and the granular Caputo fuzzy fractional derivative, the approximation solution to the FFDEs is obtained. Consequently, based on the new concepts and theorems, the solution to the fuzzy fractional quadratic regulator problem is given by a theorem. This paper closes with an example of regulating the motion of Boeing 747 in longitudinal direction with the presence of uncertainty in the initial conditions and the coefficients.

Feeling the pulse on the wrist is the regular diagnostic method in traditional Chinese medicine. However it is natural to ask whether there is any difference between feeling the pulse on the wrist or at any other part of the body: such as the fingertips at which it is easily measured by electronic devices. We employ a series of neural networks to model blood pressure propagation from the wrist to the fingertip. In order to avoid the problem of over-fitting we apply information theoretic criterion to determine the optimal model in these networks and then apply surrogate data method to the residuals in this model. We demonstrate the application of this method to recordings of human pulse in six subjects. Our result indicates that there is no significant difference between pulse waveform measure on the lateral arterial artery (wrist) and at the fingertip.