Edge artificial intelligence (AI) redistributes AI computation from distant cloud to local processors for real-time processing and enhanced privacy. This fundamental shift underscores a critical gap in current university curricula, which predominantly focus on AI fundamentals and algorithms while often neglecting essential AI hardware topics. To address this deficiency, this paper presents Edge AI, a postgraduate curriculum co-designed by two universities in Germany. Guided by the Dagstuhl triangle, the curriculum is designed to comprehensively cover technical, sociocultural, and application perspectives. Courses are developed using the Four-Component Instructional Design model to encourage action-oriented skill development, with a Learning Management System template available to assist in the design of individual courses. Selected practical courses are formulated as self-managed projects and inverted classrooms, enabling students to learn at their own pace with just-in-time guidance. All curriculum materials are accessible online and maintained by the Open Science Framework to enhance collaboration across institutions and promote applicability in diverse domains. Evaluation results from 176 students over two years (2023-2025) demonstrate universal satisfaction across various curriculum components.

Volunteered geographic information (VGI) often contains rich geolocations that are crucial for disaster response and post-disaster assessment. However, existing studies on VGI geolocalization have not fully used the potential of multi-source and multimodal data. In this paper, we constructed a multimodal disaster dataset (MultiIan) and developed two novel methods (i.e. StaGeo and TriGeo) to enhance the cross-view geolocalization accuracy of disaster-related VGI. MultiIan comprised VGI texts and images, street view imagery (SVI) and remote sensing imagery (RSI). Large language models (LLMs) were used to extract the implicit geoinformation from VGI texts for geotagging. StaGeo was developed using staged training with ConvNeXt and vision transformer (ViT), while TriGeo used VGI ↔ SVI ↔ RSI triple-objective joint training of the ViT based on DINOv2. Using SVI to link VGI and RSI, our methods significantly improved the geolocalization accuracy of VGI across various train–test splits in MultiIan. With a typical 8:2 data split, StaGeo achieved Recall@1, Recall@5, Recall@10 and Recall@1% of 54.93%, 71.27%, 77.93% and 80.33%, respectively. TriGeo further improved these metrics, achieving 62.87%, 85.55%, 90.54% and 90.89%, respectively. These findings demonstrate significant advancements in our cross-view geolocalization methods, enabling timely geolocation to support rapid decision-making in emergency response and promoting the broader application of GeoAI in geospatial analysis.

Effective human mobility modeling and prediction constitute the core prerequisites for various location-based applications. To encourage research in this direction, the ACM SIGSPATIAL Cup 2025 posed the challenge of predicting human mobility trajectories from a sparse multi-city dataset. This paper presents our solution, MoBERT, a BERT-like model that adapts and leverages mobility semantics with additional direction and distance prediction, providing supplementary supervision signals for robust feature learning. MoBERT models are trained in stages through curriculum learning, where augmented trajectories are ordered by increasing mobility entropy for training with progressively increasing difficulty. The final score of our method is 0.14609, as measured by average GEO-BLEU distances across four cities. Finally, we analyze the results and discuss insights from our approach.

Two-dimensional (2D) convolutional kernels have dominated convolutional neural networks (CNNs) in image processing. While linearly scaling 1D convolution provides parameter efficiency, its naive integration into CNNs disrupts image locality, thereby degrading performance. This paper presents path convolution (PathConv), a novel CNN design exclusively with 1D operations, achieving ResNet-level accuracy using only 1/3 parameters. To obtain locality-preserving image traversal paths, we analyze Hilbert/Z-order paths and expose a fundamental trade-off: improved proximity for most pixels comes at the cost of excessive distances for other sacrificed ones to their neighbors. We resolve this issue by proposing path shifting, a succinct method to reposition sacrificed pixels. Using the randomized rounding algorithm, we show that three shifted paths are sufficient to offer better locality preservation than trivial raster scanning. To mitigate potential convergence issues caused by multiple paths, we design a lightweight path-aware channel attention mechanism to capture local intra-path and global inter-path dependencies. Experimental results further validate the efficacy of our method, establishing the proposed 1D PathConv as a viable backbone for efficient vision models.

Continuous authentication (CA) based on wrist photoplethysmogram (PPG) has been increasingly studied, but still requires further extensive investigation on PPG reliability over time and heart rates for real-world deployments. In this paper, we first analyze the inadequacy of current research, i.e., limited generalization capability for new users and insufficient experiments due to the absence of across-session data under different heart rates (HR). To address these problems, we then propose a unified and scalable feature extraction framework for wrist PPG-based CA. Given a continuous PPG waveform, our framework first encodes the PPG of each period separately, then extracts variability features contained in consecutive multi-period PPG for user authentication. On two datasets with a total of 155 subjects, we evaluate the performances of our system using different across-session levels and HR intervals, respectively. Despite more stringent experimental settings, we achieve even better performances than in previous studies. Using the subject-exclusive cross-validation protocol, our system reaches an average accuracy of 92.1% under the constraint of equal error rates in across-session evaluation, and average accuracy ranges from 86.4% (high HR) to 91.4% (low HR) for different HR intervals.

Biometrics are widely used for user identification/authentication, but the fact has rarely been noticed that general capacitive touchscreens can reveal user identities by touch signals. This paper proposes a new biometric method with inherent liveness detection for reliable user recognition based on the cardiac signal captured by the capacitive touchscreen, namely Capacitive Plethysmogram (CPG). And a systematic framework is designed for CPG collection, processing, and exploitation to identify users. Specifically, since the finger usually forms capacitors with multiple sensing electrodes during touching, we can extract several CPG signals simultaneously from the screen output. Then we propose a series of preprocessing algorithms to filter CPG for signal quality enhancement. Finally, to further leverage filtered CPG signals and extract efficient features for identifying users, we build an encoder based on 3D attention CNN and metric learning. Experimental results demonstrate that the proposed method can achieve an average accuracy of 96.73%, FAR of 3.03%, and FRR of 7.35% in the laboratory environment, which reveals the potential of CPG for user privacy protection and data security on various devices laced with capacitive touchscreens.

The ACM SIGSPATIAL Cup 2023 proposed the challenge to identify and map supraglacial lakes in Greenland in satellite imagery. The peculiarities of supraglacial lakes pose a hard problem for semantic segmentation and object detection tasks because the definition of a lake is ill-fitted to the inner workings of such approaches. For example, lakes are often covered by ice and snow and narrow streams can connect distinct lakes, which is not directly translatable to the semantic segmentation of water. It is also not well-posed for object detection, especially the identity relation - what is a lake, what is not (yet) a lake, and what are two lakes is challenging. In this context, we worked on adapting semantic segmentation using the Segment Anything Model and instance segmentation using Mask R-CNN to the setting. The latter ended up superior in our own evaluation and even got ranked second among all participants. We are proud that our approach has led to competitive performance. The source code is available from https://github.com/tum-bgd/GISCup23.

Recent advances in (deep) machine learning offer new opportunities to solve indoor fingerprint-based localization problems. However, the majority of localization solutions employing popular machine learning models, such as k-nearest neighbors ($k$-NN), support vector machine (SVM), multi-layer perceptron (MLP), and convolutional neural network (CNN), do not sufficiently realize inability of these models to fully represent the non-Euclidean nature of fingerprint data, which consequently degrades their performance. In this paper, we first explain how these commonly-used models fail to effectively encode the fingerprint data due to their assumption (or lack of it) regarding fingerprints and/or geometric and topology information hidden within the RSSI measurements. Based on this, we provide our motivation to use geometric deep learning for indoor fingerprint-based localization. We then present a systematic approach to transform fingerprints into graphs, accounting for the co-existence of multiple radio frequency signal technologies. Finally, we present our localization approach based on a GraphSAGE estimator. Through extensive performance evaluation, using two different case studies (datasets), we show to what extent our proposed localization approach improves upon the state-of-the-art localization solutions. We also conclude that the best configuration of our approach requires both the edge features in the graphs and the pooling aggregator in the GraphSAGE model.