CBOL-Tuner: Classifier-pruned Bayesian optimization to explore temporally structured latent spaces for particle accelerator tuning

Complex dynamical systems, such as particle accelerators, often require complicated and time-consuming tuning procedures for optimal performance. It may also be required that these procedures estimate the optimal system parameters, which govern the dynamics of a spatiotemporal beam -- this can be a high-dimensional optimization problem. To address this, we propose a Classifier-pruned Bayesian Optimization-based Latent space Tuner (CBOL-Tuner), a framework for efficient exploration within a temporally-structured latent space. The CBOL-Tuner integrates a convolutional variational autoencoder (CVAE) for latent space representation, a long short-term memory (LSTM) network for temporal dynamics, a dense neural network (DNN) for parameter estimation, and a classifier-pruned Bayesian optimizer (C-BO) to adaptively search and filter the latent space for optimal solutions. CBOL-Tuner demonstrates superior performance in identifying multiple optimal settings and outperforms alternative global optimization methods.

Dual-Branch Graph Transformer Network for 3D Human Mesh Reconstruction from Video

Human Mesh Reconstruction (HMR) from monocular video plays an important role in human-robot interaction and collaboration. However, existing video-based human mesh reconstruction methods face a trade-off between accurate reconstruction and smooth motion. These methods design networks based on either RNNs or attention mechanisms to extract local temporal correlations or global temporal dependencies, but the lack of complementary long-term information and local details limits their performance. To address this problem, we propose a \textbf{D}ual-branch \textbf{G}raph \textbf{T}ransformer network for 3D human mesh \textbf{R}econstruction from video, named DGTR. DGTR employs a dual-branch network including a Global Motion Attention (GMA) branch and a Local Details Refine (LDR) branch to parallelly extract long-term dependencies and local crucial information, helping model global human motion and local human details (e.g., local motion, tiny movement). Specifically, GMA utilizes a global transformer to model long-term human motion. LDR combines modulated graph convolutional networks and the transformer framework to aggregate local information in adjacent frames and extract crucial information of human details. Experiments demonstrate that our DGTR outperforms state-of-the-art video-based methods in reconstruction accuracy and maintains competitive motion smoothness. Moreover, DGTR utilizes fewer parameters and FLOPs, which validate the effectiveness and efficiency of the proposed DGTR. Code is publicly available at \href{https://github.com/TangTao-PKU/DGTR}{\textcolor{myBlue}{https://github.com/TangTao-PKU/DGTR}}.

HiMoE: Heterogeneity-Informed Mixture-of-Experts for Fair Spatial-Temporal Forecasting

Spatial-temporal forecasting has various applications in transportation, climate, and human activity domains. Current spatial-temporal forecasting models primarily adopt a macro perspective, focusing on achieving strong overall prediction performance for the entire system. However, most of these models overlook the importance of enhancing the uniformity of prediction performance across different nodes, leading to poor prediction capabilities for certain nodes and rendering some results impractical. This task is particularly challenging due to the inherent heterogeneity of spatial-temporal data. To address this issue, in this paper, we propose a novel Heterogeneity-informed Mixture-of-Experts (HiMoE) for fair spatial-temporal forecasting. Specifically, we design a Heterogeneity-Informed Graph Convolutional Network (HiGCN), integrated into each expert model to enhance the flexibility of the experts. To adapt to the heterogeneity of spatial-temporal data, we design a Node-wise Mixture-of-Experts (NMoE). This model decouples the spatial-temporal prediction task into sub-tasks at the spatial scale, which are then assigned to different experts. To allocate these sub-tasks, we use a mean-based graph decoupling method to distinguish the graph structure for each expert. The results are then aggregated using an output gating mechanism based on a dense Mixture-of-Experts (dMoE). Additionally, fairness-aware loss and evaluation functions are proposed to train the model with uniformity and accuracy as objectives. Experiments conducted on four datasets, encompassing diverse data types and spatial scopes, validate HiMoE's ability to scale across various real-world scenarios. Furthermore, HiMoE consistently outperforms baseline models, achieving superior performance in both accuracy and uniformity.

Signal Processing over Time-Varying Graphs: A Systematic Review

As irregularly structured data representations, graphs have received a large amount of attention in recent years and have been widely applied to various real-world scenarios such as social, traffic, and energy settings. Compared to non-graph algorithms, numerous graph-based methodologies benefited from the strong power of graphs for representing high-dimensional and non-Euclidean data. In the field of Graph Signal Processing (GSP), analogies of classical signal processing concepts, such as shifting, convolution, filtering, and transformations are developed. However, many GSP techniques usually postulate the graph is static in both signal and typology. This assumption hinders the effectiveness of GSP methodologies as the assumption ignores the time-varying properties in numerous real-world systems. For example, in the traffic network, the signal on each node varies over time and contains underlying temporal correlation and patterns worthy of analysis. To tackle this challenge, more and more work are being done recently to investigate the processing of time-varying graph signals. They cope with time-varying challenges from three main directions: 1) graph time-spectral filtering, 2) multi-variate time-series forecasting, and 3) spatiotemporal graph data mining by neural networks, where non-negligible progress has been achieved. Despite the success of signal processing and learning over time-varying graphs, there is no survey to compare and conclude the current methodology for GSP and graph learning. To compensate for this, in this paper, we aim to review the development and recent progress on signal processing and learning over time-varying graphs, and compare their advantages and disadvantages from both the methodological and experimental side, to outline the challenges and potential research directions for future research.

Forecasting Foreign Exchange Market Prices Using Technical Indicators with Deep Learning and Attention Mechanism

Accurate prediction of price behavior in the foreign exchange market is crucial. This paper proposes a novel approach that leverages technical indicators and deep neural networks. The proposed architecture consists of a Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), and attention mechanism. Initially, trend and oscillation technical indicators are employed to extract statistical features from Forex currency pair data, providing insights into price trends, market volatility, relative price strength, and overbought and oversold conditions. Subsequently, the LSTM and CNN networks are utilized in parallel to predict future price movements, leveraging the strengths of both recurrent and convolutional architectures. The LSTM network captures long-term dependencies and temporal patterns in the data, while the CNN network extracts local patterns. The outputs of the parallel LSTM and CNN networks are then fed into an attention mechanism, which learns to weigh the importance of each feature and temporal dependency, generating a context-aware representation of the input data. The attention-weighted output is then used to predict future price movements, enabling the model to focus on the most relevant features and temporal dependencies. Through a comprehensive evaluation of the proposed approach on multiple Forex currency pairs, we demonstrate its effectiveness in predicting price behavior and outperforming benchmark models.

Real-Time Anomaly Detection in Video Streams

This thesis is part of a CIFRE agreement between the company Othello and the LIASD laboratory. The objective is to develop an artificial intelligence system that can detect real-time dangers in a video stream. To achieve this, a novel approach combining temporal and spatial analysis has been proposed. Several avenues have been explored to improve anomaly detection by integrating object detection, human pose detection, and motion analysis. For result interpretability, techniques commonly used for image analysis, such as activation and saliency maps, have been extended to videos, and an original method has been proposed. The proposed architecture performs binary or multiclass classification depending on whether an alert or the cause needs to be identified. Numerous neural networkmodels have been tested, and three of them have been selected. You Only Looks Once (YOLO) has been used for spatial analysis, a Convolutional Recurrent Neuronal Network (CRNN) composed of VGG19 and a Gated Recurrent Unit (GRU) for temporal analysis, and a multi-layer perceptron for classification. These models handle different types of data and can be combined in parallel or in series. Although the parallel mode is faster, the serial mode is generally more reliable. For training these models, supervised learning was chosen, and two proprietary datasets were created. The first dataset focuses on objects that may play a potential role in anomalies, while the second consists of videos containing anomalies or non-anomalies. This approach allows for the processing of both continuous video streams and finite videos, providing greater flexibility in detection.

Predicting Extubation Failure in Intensive Care: The Development of a Novel, End-to-End Actionable and Interpretable Prediction System

Predicting extubation failure in intensive care is challenging due to complex data and the severe consequences of inaccurate predictions. Machine learning shows promise in improving clinical decision-making but often fails to account for temporal patient trajectories and model interpretability, highlighting the need for innovative solutions. This study aimed to develop an actionable, interpretable prediction system for extubation failure using temporal modelling approaches such as Long Short-Term Memory (LSTM) and Temporal Convolutional Networks (TCN). A retrospective cohort study of 4,701 mechanically ventilated patients from the MIMIC-IV database was conducted. Data from the 6 hours before extubation, including static and dynamic features, were processed through novel techniques addressing data inconsistency and synthetic data challenges. Feature selection was guided by clinical relevance and literature benchmarks. Iterative experimentation involved training LSTM, TCN, and LightGBM models. Initial results showed a strong bias toward predicting extubation success, despite advanced hyperparameter tuning and static data inclusion. Data was stratified by sampling frequency to reduce synthetic data impacts, leading to a fused decision system with improved performance. However, all architectures yielded modest predictive power (AUC-ROC ~0.6; F1 <0.5) with no clear advantage in incorporating static data or additional features. Ablation analysis indicated minimal impact of individual features on model performance. This thesis highlights the challenges of synthetic data in extubation failure prediction and introduces strategies to mitigate bias, including clinician-informed preprocessing and novel feature subsetting. While performance was limited, the study provides a foundation for future work, emphasising the need for reliable, interpretable models to optimise ICU outcomes.

Machine learning-based classification for Single Photon Space Debris Light Curves

The growing number of man-made debris in Earth's orbit poses a threat to active satellite missions due to the risk of collision. Characterizing unknown debris is, therefore, of high interest. Light Curves (LCs) are temporal variations of object brightness and have been shown to contain information such as shape, attitude, and rotational state. Since 2015, the Satellite Laser Ranging (SLR) group of Space Research Institute (IWF) Graz has been building a space debris LC catalogue. The LCs are captured on a Single Photon basis, which sets them apart from CCD-based measurements. In recent years, Machine Learning (ML) models have emerged as a viable technique for analyzing LCs. This work aims to classify Single Photon Space Debris using the ML framework. We have explored LC classification using k-Nearest Neighbour (k-NN), Random Forest (RDF), XGBoost (XGB), and Convolutional Neural Network (CNN) classifiers in order to assess the difference in performance between traditional and deep models. Instead of performing classification on the direct LCs data, we extracted features from the data first using an automated pipeline. We apply our models on three tasks, which are classifying individual objects, objects grouped into families according to origin (e.g., GLONASS satellites), and grouping into general types (e.g., rocket bodies). We successfully classified Space Debris LCs captured on Single Photon basis, obtaining accuracies as high as 90.7%. Further, our experiments show that the classifiers provide better classification accuracy with automated extracted features than other methods.

SpikeAtConv: An Integrated Spiking-Convolutional Attention Architecture for Energy-Efficient Neuromorphic Vision Processing

Spiking Neural Networks (SNNs) offer a biologically inspired alternative to conventional artificial neural networks, with potential advantages in power efficiency due to their event-driven computation. Despite their promise, SNNs have yet to achieve competitive performance on complex visual tasks, such as image classification. This study introduces a novel SNN architecture designed to enhance computational efficacy and task accuracy. The architecture features optimized pulse modules that facilitate the processing of spatio-temporal patterns in visual data, aiming to reconcile the computational demands of high-level vision tasks with the energy-efficient processing of SNNs. Our evaluations on standard image classification benchmarks indicate that the proposed architecture narrows the performance gap with traditional neural networks, providing insights into the design of more efficient and capable neuromorphic computing systems.

Multi-Resolution Generative Modeling of Human Motion from Limited Data

We present a generative model that learns to synthesize human motion from limited training sequences. Our framework provides conditional generation and blending across multiple temporal resolutions. The model adeptly captures human motion patterns by integrating skeletal convolution layers and a multi-scale architecture. Our model contains a set of generative and adversarial networks, along with embedding modules, each tailored for generating motions at specific frame rates while exerting control over their content and details. Notably, our approach also extends to the synthesis of co-speech gestures, demonstrating its ability to generate synchronized gestures from speech inputs, even with limited paired data. Through direct synthesis of SMPL pose parameters, our approach avoids test-time adjustments to fit human body meshes. Experimental results showcase our model's ability to achieve extensive coverage of training examples, while generating diverse motions, as indicated by local and global diversity metrics.