arXiv subjects

Ziwen Zhong

Publications and source records attributed to Ziwen Zhong.

5 recordsLinked to original sources

arXiv2025

A Cloud-Based Cross-Modal Transformer for Emotion Recognition and Adaptive Human-Computer Interaction

Emotion recognition is a fundamental component of next-generation human-computer interaction (HCI), enabling machines to perceive, understand, and respond to users' affective states. However, existing systems often rely on single-modality analysis such as facial expressions, speech tone, or textual sentiment, resulting in limited robustness and poor generalization in real-world environments. To address these challenges, this study proposes a Cloud-Based Cross-Modal Transformer (CMT) framework for multimodal emotion recognition and adaptive human-computer interaction. The proposed model integrates visual, auditory, and textual signals using pretrained encoders (Vision Transformer, Wav2Vec2, and BERT) and employs a cross-modal attention mechanism to capture complex interdependencies among heterogeneous features. By leveraging cloud computing infrastructure with distributed training on Kubernetes and TensorFlow Serving, the system enables scalable, low-latency emotion recognition for large-scale user interactions. Experiments conducted on benchmark datasets including IEMOCAP, MELD, and AffectNet demonstrate that the CMT achieves state-of-the-art performance, improving the F1-score by 3.0 percent and reducing cross-entropy loss by 12.9 percent compared to strong multimodal baselines. Additionally, cloud deployment evaluations show an average response latency of 128 ms, representing a 35 percent reduction compared with conventional transformer-based fusion systems. These results confirm that the proposed framework enables efficient, real-time emotion recognition and adaptive feedback in applications such as intelligent customer service, virtual tutoring systems, and affective computing interfaces, marking an important step toward cloud-native affective computing and emotionally intelligent interactive systems.

cs.CV↗

arXiv2025

Earthquake Forecasting with ETAS.inlabru

The ETAS models are currently the most popular in the field of earthquake forecasting. The MCMC method is time-consuming and limited by parameter correlation while bringing parameter uncertainty. The INLA-based method "inlabru" solves these problems and performs better at Bayesian inference. The report introduces the composition of the ETAS model, then provides the model's log-likelihood and approximates it using Taylor expansion and binning strategies. We also present the general procedure of Bayesian inference in inlabru. The report follows three experiments. The first one explores the effect of fixing one parameter at its actual or wrong values on the posterior distribution of other parameters. We found that $α$ and $K$ have an apparent mutual influence relationship. At the same time, fixing $α$ or $K$ to its actual value can reduce the model fitting time by more than half. The second experiment compares normalised inter-event-time distribution on real data and synthetic catalogues. The distributions of normalised inter-event-time of real data and synthetic catalogues are consistent. Compared with Exp(1), they have more short and long inter-event-time, indicating the existence of clustering. Change on $μ$ and $p$ will influence the inter-event-time distribution. In the last one, we use events before the mainshock to predict events ten weeks after the mainshock. We use the number test and Continuous Ranked Probability Score (CRPS) to measure the accuracy and precision of the predictions. We found that we need at least one mainshock and corresponding offspring to make reliable forecasting. And when we have more mainshocks in our data, our forecasting will be better. Besides, we also figure out what is needed to obtain a good posterior distribution for each parameter.

stat.AP↗

arXiv2025

Estimation of rates in population-age-dependent processes by means of test functions

This paper aims to develop practical applications of the model for the highly technical measure-valued populations developed by the authors in \cite{FanEtal20}. We consider the problem of estimation of parameters in the general age and population-dependent model, in which the individual birth and death rates depend not only on the age of the individual but also on the whole population composition. We derive new estimators of the rates based on the use of test functions in the functional Law of Large Numbers and Central Limit Theorem for populations with a large carrying capacity. We consider the rates to be simple functions, that take finitely many values both in age $x$ and measure $A$, which leads to systems of linear equations. The proposed method of using test functions for estimation is a radically new approach which can be applied to a wide range of models of dynamical systems.

math.ST↗

arXiv2024

Finding pure Nash equilibria in large random games

Best Response Dynamics (BRD) is a class of strategy updating rules to find Pure Nash Equilibria (PNE) in a game. At each step, a player is randomly picked, and the player switches to a "best response" strategy based on the strategies chosen by others, so that the new strategy profile maximises their payoff. If no such strategy exists, a different player will be chosen randomly. When no player wants to change their strategy anymore, the process reaches a PNE and will not deviate from it. On the other hand, either PNE may not exist, or BRD could be "trapped" within a subgame that has no PNE. We consider a random game with $N$ players, each with two actions available, and i.i.d. payoffs, in which the payoff distribution may have an atom, i.e. ties are allowed. We study a class of random walks in a random medium on the $N$-dimensional hypercube induced by the random game. The medium contains two types of obstacles corresponding to PNE and traps. The class of processes we analyze includes BRD, simple random walks on the hypercube, and many other nearest neighbour processes. We prove that, with high probability, these processes reach a PNE before hitting any trap.

math.PR↗

arXiv2020

Pure Nash Equilibria and Best-Response Dynamics in Random Games

In finite games mixed Nash equilibria always exist, but pure equilibria may fail to exist. To assess the relevance of this nonexistence, we consider games where the payoffs are drawn at random. In particular, we focus on games where a large number of players can each choose one of two possible strategies, and the payoffs are i.i.d. with the possibility of ties. We provide asymptotic results about the random number of pure Nash equilibria, such as fast growth and a central limit theorem, with bounds for the approximation error. Moreover, by using a new link between percolation models and game theory, we describe in detail the geometry of Nash equilibria and show that, when the probability of ties is small, a best-response dynamics reaches a Nash equilibrium with a probability that quickly approaches one as the number of players grows. We show that a multitude of phase transitions depend only on a single parameter of the model, that is, the probability of having ties.

cs.GT↗