Observation-based trajectory prediction for systems with unknown dynamics is essential in fields such as physics and biology. Most existing approaches are limited to learning within a single system with fixed dynamics patterns. However, many real-world applications require learning across systems with evolving dynamics patterns, a challenge that has been largely overlooked. To address this, we systematically investigate the problem of Continual Dynamics Learning (CDL), examining task configurations and evaluating the applicability of existing techniques, while identifying key challenges. In response, we propose the Mode-switching Graph ODE (MS-GODE) model, which integrates the strengths LG-ODE and sub-network learning with a mode-switching module, enabling efficient learning over varying dynamics. Moreover, we construct a novel benchmark of biological dynamic systems for CDL, Bio-CDL, featuring diverse systems with disparate dynamics and significantly enriching the research field of machine learning for dynamic systems. Our code available at \url{https://github.com/QueuQ/MS-GODE}.

Multi-modal time series analysis has recently emerged as a prominent research area, driven by the increasing availability of diverse data modalities, such as text, images, and structured tabular data from real-world sources. However, effective analysis of multi-modal time series is hindered by data heterogeneity, modality gap, misalignment, and inherent noise. Recent advancements in multi-modal time series methods have exploited the multi-modal context via cross-modal interactions based on deep learning methods, significantly enhancing various downstream tasks. In this tutorial and survey, we present a systematic and up-to-date overview of multi-modal time series datasets and methods. We first state the existing challenges of multi-modal time series analysis and our motivations, with a brief introduction of preliminaries. Then, we summarize the general pipeline and categorize existing methods through a unified cross-modal interaction framework encompassing fusion, alignment, and transference at different levels (i.e., input, intermediate, output), where key concepts and ideas are highlighted. We also discuss the real-world applications of multi-modal analysis for both standard and spatial time series, tailored to general and specific domains. Finally, we discuss future research directions to help practitioners explore and exploit multi-modal time series. The up-to-date resources are provided in the GitHub repository. https://github.com/UConn-DSIS/Multi-modal-Time-Series-Analysis.

Time series analysis provides essential insights for real-world system dynamics and informs downstream decision-making, yet most existing methods often overlook the rich contextual signals present in auxiliary modalities. To bridge this gap, we introduce TimeXL, a multi-modal prediction framework that integrates a prototype-based time series encoder with three collaborating Large Language Models (LLMs) to deliver more accurate predictions and interpretable explanations. First, a multi-modal prototype-based encoder processes both time series and textual inputs to generate preliminary forecasts alongside case-based rationales. These outputs then feed into a prediction LLM, which refines the forecasts by reasoning over the encoder's predictions and explanations. Next, a reflection LLM compares the predicted values against the ground truth, identifying textual inconsistencies or noise. Guided by this feedback, a refinement LLM iteratively enhances text quality and triggers encoder retraining. This closed-loop workflow---prediction, critique (reflect), and refinement---continuously boosts the framework's performance and interpretability. Empirical evaluations on four real-world datasets demonstrate that TimeXL achieves up to 8.9\% improvement in AUC and produces human-centric, multi-modal explanations, highlighting the power of LLM-driven reasoning for time series prediction.

Large Language Models (LLMs) and Foundation Models (FMs) have recently become prevalent for time series forecasting tasks. While fine-tuning LLMs enables domain adaptation, they often struggle to generalize across diverse and unseen datasets. Moreover, existing Time Series Foundation Models (TSFMs) still face challenges in handling non-stationary dynamics and distribution shifts, largely due to the lack of effective mechanisms for adaptation. To this end, we present TS-RAG, a retrieval-augmented generation framework for time series forecasting that enhances the generalization and interpretability of TSFMs. Specifically, TS-RAG leverages pre-trained time series encoders to retrieve semantically relevant segments from a dedicated knowledge base, enriching the contextual representation of the input query. Furthermore, we propose an Adaptive Retrieval Mixer (ARM) module that dynamically fuses the retrieved patterns with the TSFM's internal representation, improving forecasting accuracy without requiring task-specific fine-tuning. Thorough empirical studies on seven public benchmark datasets demonstrate that TS-RAG achieves state-of-the-art zero-shot forecasting performance, outperforming the existing TSFMs by up to 6.84\% across diverse domains while also providing desirable interpretability. Our code and data are available at: https://github.com/UConn-DSIS/TS-RAG.

Recently, there has been a growing interest in leveraging pre-trained large language models (LLMs) for various time series applications. However, the semantic space of LLMs, established through the pre-training, is still underexplored and may help yield more distinctive and informative representations to facilitate time series forecasting. To this end, we propose Semantic Space Informed Prompt learning with LLM ($S^2$IP-LLM) to align the pre-trained semantic space with time series embedding space and perform time series forecasting based on learned prompts from the joint space. We first design a tokenization module tailored for cross-modality alignment, which explicitly concatenates patches of decomposed time series components to create embeddings that effectively encode the temporal dynamics. Next, we leverage the pre-trained word token embeddings to derive semantic anchors and align selected anchors with time series embeddings by maximizing the cosine similarity in the joint space. This way, $S^2$IP-LLM can retrieve relevant semantic anchors as prompts to provide strong indicators (context) for time series that exhibit different temporal dynamics. With thorough empirical studies on multiple benchmark datasets, we demonstrate that the proposed $S^2$IP-LLM can achieve superior forecasting performance over state-of-the-art baselines. Furthermore, our ablation studies and visualizations verify the necessity of prompt learning informed by semantic space.

Time series analysis stands as a focal point within the data mining community, serving as a cornerstone for extracting valuable insights crucial to a myriad of real-world applications. Recent advances in Foundation Models (FMs) have fundamentally reshaped the paradigm of model design for time series analysis, boosting various downstream tasks in practice. These innovative approaches often leverage pre-trained or fine-tuned FMs to harness generalized knowledge tailored for time series analysis. This survey aims to furnish a comprehensive and up-to-date overview of FMs for time series analysis. While prior surveys have predominantly focused on either application or pipeline aspects of FMs in time series analysis, they have often lacked an in-depth understanding of the underlying mechanisms that elucidate why and how FMs benefit time series analysis. To address this gap, our survey adopts a methodology-centric classification, delineating various pivotal elements of time-series FMs, including model architectures, pre-training techniques, adaptation methods, and data modalities. Overall, this survey serves to consolidate the latest advancements in FMs pertinent to time series analysis, accentuating their theoretical underpinnings, recent strides in development, and avenues for future exploration.

Beibei Gao, Yangsen Zhang, Ga Xiang, Yushan Jiang. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Imitation learning that replicates experts' skills via their demonstrations has shown significant success in various decision-making tasks. However, two critical challenges still hinder the deployment of imitation learning techniques in real-world application scenarios. First, existing methods lack the intrinsic interpretability to explicitly explain the underlying rationale of the learned skill and thus making learned policy untrustworthy. Second, due to the scarcity of expert demonstrations from each end user (client), learning a policy based on different data silos is necessary but challenging in privacy-sensitive applications such as finance and healthcare. To this end, we present a privacy-preserved interpretable skill learning framework (FedSkill) that enables global policy learning to incorporate data from different sources and provides explainable interpretations to each local user without violating privacy and data sovereignty. Specifically, our proposed interpretable skill learning model can capture the varying patterns in the trajectories of expert demonstrations, and extract prototypical information as skills that provide implicit guidance for policy learning and explicit explanations in the reasoning process. Moreover, we design a novel aggregation mechanism coupled with the based skill learning model to preserve global information utilization and maintain local interpretability under the federated framework. Thoroughly experiments on three datasets and empirical studies demonstrate that our proposed FedSkill framework not only outperforms state-of-the-art imitation learning methods but also exhibits good interpretability under a federated setting. Our proposed FedSkill framework is the first attempt to bridge the gaps among federated learning, interpretable machine learning, and imitation learning.

Hate speech detection is hampered by the scarcity and topical and lexical biases of annotated data, leading to poor generalization. It is imperative to devise a cross-domain approach to solve this problem. The ability to learn transferable knowledge is critical for cross-domain hate speech detection. In this work, We propose a domain-adaptive dependency graph method based on post-hoc explanation (DPDG). We extract post-hoc explanations from fine-tuned BERT classifiers as the importance score for hate representation. Based on these, we construct in-domain graph and cross-domain graph to better learn in-domain hate representation and adapt to the target domain respectively. Finally, we use interactive GCN blocks to interactively and adaptively learn and adjust the domain adaptive graph representation. The results of cross-domain experiments on multiple domains show that our proposed model outperforms competitive baselines in cross-domain hate speech detection.

Big data analytics and mining have the potential to enable real-time decision making and control in a range of Internet of Things (IoT) application domains, such as the Internet of Vehicles, the Internet of Wings, and the Airport of Things. The prediction toward air mobility, which is essential to the studies of air traffic management, has been a challenging task due to the complex spatial and temporal dependencies in air traffic data with highly nonlinear and variational patterns. Existing works for air traffic prediction only focus on either modeling static traffic patterns of individual flight or temporal correlation, with no or limited addressing of the spatial impact, namely, the propagation of traffic perturbation among airports. In this article, we propose to leverage the concept of graph and model the airports as nodes with time-series features and conduct data mining on graph-structured data. To be specific, first, airline on-time performance (AOTP) data is preprocessed to generate a temporal graph data set, which includes three features: 1) the number; 2) average delay; and 3) average taxiing time of departure and arrival flights. Then, a spatial–temporal graph neural networks model is implemented to forecast the mobility level at each airport over time, where a combination of graph convolution and time-dimensional convolution is used to capture the spatial and temporal correlation simultaneously. Experiments on the data set demonstrate the advantage of the model on spatial–temporal air mobility prediction, together with the impact of different priors on adjacency matrices and the effectiveness of the temporal attention mechanism. Finally, we analyze the prediction performance and discuss the capability of our model. The prediction framework proposed in this work has the potential to be generalized to other spatial–temporal tasks in IoT.

Radio frequency (RF) signal classification has significantly been used for detecting and identifying the features of unknown unmanned aerial vehicles (UAVs). This paper proposes a method using empirical mode decomposition (EMD) and ensemble empirical mode decomposition (EEMD) on extracting the communication channel characteristics of intruding UAVs. The decomposed intrinsic mode functions (IMFs) except noise components are selected for RF signal pattern recognition based on machine learning (ML). The classification results show that the denoising effects introduced by EMD and EEMD could both fit in improving the detection accuracy with different features of RF communication channel, especially on identifying time-varying RF signal sources.

With the development of unmanned aerial systems (UAS), the ubiquitous deployment of UAS is becoming a trend. With the digital transceiver, the remote pilot can control the UAS remotely and effectively. With the deployment of 5G technology on a large scale, the convenience of remote control is becoming obvious and stable. However, the convenience of remote control technologies also brings more vulnerabilities to UAS. Software defined radio (SDR) has been explored to play system exploitation and penetration test for the radio system widely. With block programming, an SDR can become a hands-on system exploitation tool for research. With the adjustment of antennas and programmings, we can exploit the vulnerabilities of the UAS system and fixed the problem in advance. In this paper, we introduce an approach to leverage SDR to realize signal spoofing for GPS location and injection for digital communication. Based on SDR, we analyze the security of UAS on the GPS and digital connections. With the adjustment of antennas, we can define the SDR into a GPS spoofing tool and inject the packets in the communication of the digital transceiver. The evaluation shows the approach can delay the GPS searching for tens of minutes and disorder the connections between ground control station to UAS.

With massive data being generated daily and the ever-increasing interconnectivity of the world’s Internet infrastructures, a machine learning based intrusion detection system (IDS) has become a vital component to protect our economic and national security. In this paper, we perform a comprehensive study on NSL-KDD, a network traffic dataset, by visualizing patterns and employing different learning-based models to detect cyber attacks. Unlike previous shallow learning and deep learning models that use the single learning model approach for intrusion detection, we adopt a hierarchy strategy, in which the intrusion and normal behavior are classified firstly, and then the specific types of attacks are classified. We demonstrate the advantage of the unsupervised representation learning model in binary intrusion detection tasks. Besides, we alleviate the data imbalance problem with SVM-SMOTE oversampling technique in 4-class classification and further demonstrate the effectiveness and the drawback of the oversampling mechanism with a deep neural network as a base model.

Anomaly detection has been a challenging task given high-dimensional multivariate time series data generated by networked sensors and actuators in Cyber-Physical Systems (CPS). Besides the highly nonlinear, complex, and dynamic nature of such time series, the lack of labeled data impedes data exploitation in a supervised manner and thus prevents an accurate detection of abnormal phenomenons. On the other hand, the collected data at the edge of the network is often privacy sensitive and large in quantity, which may hinder the centralized training at the main server. To tackle these issues, we propose an unsupervised time series anomaly detection framework in a federated fashion to continuously monitor the behaviors of interconnected devices within a network and alert for abnormal incidents so that countermeasures can be taken before undesired consequences occur. To be specific, we leave the training data distributed at the edge to learn a shared Variational Autoencoder (VAE) based on Convolutional Gated Recurrent Unit (ConvGRU) model, which jointly captures feature and temporal dependencies in the multivariate time series data for representation learning and downstream anomaly detection tasks. Experiments on three real-world networked sensor datasets illustrate the advantage of our approach over other state-of-the-art models. We also conduct extensive experiments to demonstrate the effectiveness of our detection framework under non-federated and federated settings in terms of overall performance and detection latency.

To accommodate the unprecedented increase of commercial airlines over the next ten years, the Next Generation Air Transportation System (NextGen) has been implemented in the USA that records large-scale Air Traffic Management (ATM) data to make air travel safer, more efficient, and more economical. A key role of collaborative decision making for air traffic scheduling and airspace resource management is the accurate prediction of flight delay. There has been a lot of attempts to apply data-driven methods such as machine learning to forecast flight delay situation using air traffic data of departures and arrivals. However, most of them omit en-route spatial information of airlines and temporal correlation between serial flights which results in inaccuracy prediction. In this paper, we present a novel aviation delay prediction system based on stacked Long Short-Term Memory (LSTM) networks for commercial flights. The system learns from historical trajectories from automatic dependent surveillance-broadcast (ADS-B) messages and uses the correlative geolocations to collect indispensable features such as climatic elements, air traffic, airspace, and human factors data along posterior routes. These features are integrated and then are fed into our proposed regression model. The latent spatio-temporal patterns of data are abstracted and learned in the LSTM architecture. Compared with previous schemes, our approach is demonstrated to be more robust and accurate for large hub airports.

An ultralow quiescent current output-capacitorless low-dropout (LDO) regulator dedicated to Internet-of-Things applications is presented. This is based on an improved adaptive-stage adaptively biased architecture together with the novel frequency compensation to achieve the good stability and fast transient response under ultralow bias current. Validated by the CMOS 0.18-μm technology, the chip area is 0.055 mm2. The proposed LDO regulator consumes only 407-nA quiescent current at no-load current while providing a 1-V output with a maximum load current of 100 mA from a 1.2-V power supply. The adaptive frequency compensation is presented, including a new transistor degeneration frequency compensation (TDFC) to sustain the stability at ultralow quiescent bias. Besides, it also includes Q-reduction and Miller-RC compensation schemes to ensure the stability for full load current range. In addition, a substantial improved transient response is obtained by the proposed distributed overshoot reduction circuit together with the TDFC scheme and the adaptively feed-forward biasing topology. The measured results have shown that the undershoot/overshoot voltage is 117 mV/35.33 mV and the output can settle in 1.56 μs with 1% accuracy. Compared to fixed-biased and adaptively biased architectures, it shows the lowest value in figure of merit (FOM) at the quiescent state. Compared to adaptively biased architectures, it shows the improved FOM at the maximum quiescent state.