Arrival time prediction (ATP) of public transport vehicles is essential in improving passenger experience and supporting traffic management. Deep learning has demonstrated outstanding performance in ATP due to its ability to model non-linear and temporal dynamics. In the multi-step ATP, non-stationary data will degrade the model performance due to the variation in variables' joint distribution along the temporal direction. Previous studies mainly applied normalization to eliminate the non-stationarity in time series, thereby achieving better predictability. However, the normalization may obscure useful characteristics inherent in non-stationarity, which is known as the over-stationarization. In this work, to trade off predictability and non-stationarity, a new approach for multi-step ATP, named non-stationary ATP ( NSATP), is proposed. The method consists of two stages: series stationarization and non-stationarity effect recovery. The first stage aims at improving the predictability. As for the latter, NSATP extends a state-of-the-art method from one-dimensional to two dimensional based models to capture the hidden periodicity in time series and designs a compensation module of over-stationarization by learning scaling and shifting factors from raw data. 125 days' public transport operational data of Dresden is collected for validation. Experimental results show that compared to baseline methods, the proposed NSATP can reduce RMSE, MAE, and MAPE by 2.37%, 1.22%, and 2.26% for trams and by 1.72%, 0.60%, and 1.17% for buses, respectively.

Classifying 3D MRI images for early detection of Alzheimer's disease is a critical task in medical imaging. Traditional approaches using Convolutional Neural Networks (CNNs) and Transformers face significant challenges in this domain. CNNs, while effective in capturing local spatial features, struggle with long-range dependencies and often require extensive computational resources for high-resolution 3D data. Transformers, on the other hand, excel in capturing global context but suffer from quadratic complexity in inference time and require substantial memory, making them less efficient for large-scale 3D MRI data. To address these limitations, we propose the use of Vision Mamba, an advanced model based on State Space Models (SSMs), for the classification of 3D MRI images to detect Alzheimer's disease. Vision Mamba leverages dynamic state representations and the selective scan algorithm, allowing it to efficiently capture and retain important spatial information across 3D volumes. By dynamically adjusting state transitions based on input features, Vision Mamba can selectively retain relevant information, leading to more accurate and computationally efficient processing of 3D MRI data. Our approach combines the parallelizable nature of convolutional operations during training with the efficient, recurrent processing of states during inference. This architecture not only improves computational efficiency but also enhances the model's ability to handle long-range dependencies within 3D medical images. Experimental results demonstrate that Vision Mamba outperforms traditional CNN and Transformer models accuracy, making it a promising tool for the early detection of Alzheimer's disease using 3D MRI data.

Accurate precipitation nowcasting is essential for various purposes, including flood prediction, disaster management, optimizing agricultural activities, managing transportation routes and renewable energy. While several studies have addressed this challenging task from a sequence-to-sequence perspective, most of them have focused on a single area without considering the existing correlation between multiple disjoint regions. In this paper, we formulate precipitation nowcasting as a spatiotemporal graph sequence nowcasting problem. In particular, we introduce Graph Dual-stream Convolutional Attention Fusion (GD-CAF), a novel approach designed to learn from historical spatiotemporal graph of precipitation maps and nowcast future time step ahead precipitation at different spatial locations. GD-CAF consists of spatio-temporal convolutional attention as well as gated fusion modules which are equipped with depthwise-separable convolutional operations. This enhancement enables the model to directly process the high-dimensional spatiotemporal graph of precipitation maps and exploits higher-order correlations between the data dimensions. We evaluate our model on seven years of precipitation maps across Europe and its neighboring areas collected from the ERA5 dataset, provided by Copernicus. The model receives a fully connected graph in which each node represents historical observations from a specific region on the map. Consequently, each node contains a 3D tensor with time, height, and width dimensions. Experimental results demonstrate that the proposed GD-CAF model outperforms the other examined models. Furthermore, the averaged seasonal spatial and temporal attention scores over the test set are visualized to provide additional insights about the strongest connections between different regions or time steps. These visualizations shed light on the decision-making process of our model.

Sleep Stage Classification (SSC) is a labor-intensive task, requiring experts to examine hours of electrophysiological recordings for manual classification. This is a limiting factor when it comes to leveraging sleep stages for therapeutic purposes. With increasing affordability and expansion of wearable devices, automating SSC may enable deployment of sleep-based therapies at scale. Deep Learning has gained increasing attention as a potential method to automate this process. Previous research has shown accuracy comparable to manual expert scores. However, previous approaches require sizable amount of memory and computational resources. This constrains the ability to classify in real time and deploy models on the edge. To address this gap, we aim to provide a model capable of predicting sleep stages in real-time, without requiring access to external computational sources (e.g., mobile phone, cloud). The algorithm is power efficient to enable use on embedded battery powered systems. Our compact sleep stage classifier can be deployed on most off-the-shelf microcontrollers (MCU) with constrained hardware settings. This is due to the memory footprint of our approach requiring significantly fewer operations. The model was tested on three publicly available data bases and achieved performance comparable to the state of the art, whilst reducing model complexity by orders of magnitude (up to 280 times smaller compared to state of the art). We further optimized the model with quantization of parameters to 8 bits with only an average drop of 0.95% in accuracy. When implemented in firmware, the quantized model achieves a latency of 1.6 seconds on an Arm CortexM4 processor, allowing its use for on-line SSC-based therapies.

Capsule Network is powerful at defining the positional relationship between features in deep neural networks for visual recognition tasks, but it is computationally expensive and not suitable for running on mobile devices. The bottleneck is in the computational complexity of the Dynamic Routing mechanism used between the capsules. On the other hand, XNOR-Net is fast and computationally efficient, though it suffers from low accuracy due to information loss in the binarization process. To address the computational burdens of the Dynamic Routing mechanism, this paper proposes new Fully Connected (FC) layers by xnorizing the linear projection outside or inside the Dynamic Routing within the CapsFC layer. Specifically, our proposed FC layers have two versions, XnODR (Xnorize the Linear Projection Outside Dynamic Routing) and XnIDR (Xnorize the Linear Projection Inside Dynamic Routing). To test the generalization of both XnODR and XnIDR, we insert them into two different networks, MobileNetV2 and ResNet-50. Our experiments on three datasets, MNIST, CIFAR-10, and MultiMNIST validate their effectiveness. The results demonstrate that both XnODR and XnIDR help networks to have high accuracy with lower FLOPs and fewer parameters (e.g., 96.14% correctness with 2.99M parameters and 311.74M FLOPs on CIFAR-10).

Quantum Machine Learning continues to be a highly active area of interest within Quantum Computing. Many of these approaches have adapted classical approaches to the quantum settings, such as QuantumFlow, etc. We push forward this trend and demonstrate an adaption of the Classical Convolutional Neural Networks to quantum systems - namely QuCNN. QuCNN is a parameterised multi-quantum-state based neural network layer computing similarities between each quantum filter state and each quantum data state. With QuCNN, back propagation can be achieved through a single-ancilla qubit quantum routine. QuCNN is validated by applying a convolutional layer with a data state and a filter state over a small subset of MNIST images, comparing the back propagated gradients, and training a filter state against an ideal target state.

Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks. However, modelling global correlations with multi-head self-attention (MSA) layers leads to two widely recognized issues: the massive computational resource consumption and the lack of intrinsic inductive bias for modelling local visual patterns. To solve both issues, we devise a simple yet effective method named Single-Path Vision Transformer pruning (SPViT), to efficiently and automatically compress the pre-trained ViTs into compact models with proper locality added. Specifically, we first propose a novel weight-sharing scheme between MSA and convolutional operations, delivering a single-path space to encode all candidate operations. In this way, we cast the operation search problem as finding which subset of parameters to use in each MSA layer, which significantly reduces the computational cost and optimization difficulty, and the convolution kernels can be well initialized using pre-trained MSA parameters. Relying on the single-path space, we further introduce learnable binary gates to encode the operation choices, which are jointly optimized with network parameters to automatically determine the configuration of each layer. We conduct extensive experiments on two representative ViTs showing that our SPViT achieves a new SOTA for pruning on ImageNet-1k. For example, our SPViT can trim 52.0% FLOPs for DeiT-B and get an impressive 0.6% top-1 accuracy gain simultaneously. The source code is available at https://github.com/ziplab/SPViT.

In recent years we have seen a growing number of edge devices adopted by consumers, in their homes (e.g., smart cameras and doorbells), in their cars (e.g., driver assisted systems), and even on their persons (e.g., smart watches and rings). Similar growth is reported in industries including aerospace, agriculture, healthcare, transport, and manufacturing. At the same time that devices are getting smaller, Deep Neural Networks (DNN) that power most forms of artificial intelligence are getting larger, requiring more compute power, memory, and bandwidth. This creates a growing disconnect between advances in artificial intelligence and the ability to develop smart devices at the edge. In this paper, we present a novel approach to running state-of-the-art AI algorithms at the edge. We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks (BWN) and XNOR-Networks. In BWN, the filters are approximated with binary values resulting in 32x memory saving. In XNOR-Networks, both the filters and the input to convolutional layers are binary. Our binary networks are simple, accurate, efficient, and work on challenging visual tasks. We evaluate our approach on the ImageNet classification task. The classification accuracy with a BWN version of AlexNet is the same as the full-precision AlexNet.