Abstract We introduce GraphHeatY, a Visual Analytics approach for exploring and comparing heat transfer behavior in buildings. A building can be conceptualized as a connected graph, where nodes represent rooms or external areas, and edges represent the building elements that connect them. Heat flows along these connections. We employ node‐link diagrams and glyph overlays to emphasize the connectivity within buildings. Donut glyphs and bar charts support analysis at both global (i.e., building) and local (i.e., room) levels. GraphHeatY integrates spatial and non‐spatial visualizations to support detailed inspection of heat flows while preserving an overview. Further, GraphHeatY allows users to interactively explore differences in insulation, material composition, and system settings, and assess their impact on the building's thermal state. User evaluations confirmed that GraphHeatY enhances comparative reasoning in early‐stage building design.

Building Information Modeling (BIM) describes a central data pool covering the entire life cycle of a construction project. Similarly, Building Energy Modeling (BEM) describes the process of using a 3D representation of a building as a basis for thermal simulations to assess the building's energy performance. This paper explores the intersection of BIM and BEM, focusing on the challenges and methodologies in converting BIM data into BEM representations for energy performance analysis. BEMTrace integrates 3D data wrangling techniques with visualization methodologies to enhance the accuracy and traceability of the BIM-to-BEM conversion process. Through parsing, error detection, and algorithmic correction of BIM data, our methods generate valid BEM models suitable for energy simulation. Visualization techniques provide transparent insights into the conversion process, aiding error identification, validation, and user comprehension. We introduce context-adaptive selections to facilitate user interaction and to show that the BEMTrace workflow helps users understand complex 3D data wrangling processes.

Abstract [Context] The continuous inflow of bug reports is a considerable challenge in large development projects. Inspired by contemporary work on mining software repositories, we designed a prototype bug assignment solution based on machine learning in 2011-2016. The prototype evolved into an internal Ericsson product, TRR, in 2017-2018. TRR’s first bug assignment without human intervention happened in April 2019. [Objective] Our study evaluates the adoption of TRR within its industrial context at Ericsson, i.e., we provide lessons learned related to the productization of a research prototype within a company. Moreover, we investigate 1) how TRR performs in the field, 2) what value TRR provides to Ericsson, and 3) how TRR has influenced the ways of working. [Method] We conduct a preregistered industrial case study combining interviews with TRR stakeholders, minutes from sprint planning meetings, and bug-tracking data. The data analysis includes thematic analysis, descriptive statistics, and Bayesian causal analysis. [Results] TRR is now an incorporated part of the bug assignment process. Considering the abstraction levels of the telecommunications stack, high-level modules are more positive while low-level modules experienced some drawbacks. Most importantly, some bug reports directly reach low-level modules without first having passed through fundamental root-cause analysis steps at higher levels. On average, TRR automatically assigns 30% of the incoming bug reports with an accuracy of 75%. Auto-routed TRs are resolved around 21% faster within Ericsson, and TRR has saved highly seasoned engineers many hours of work. Indirect effects of adopting TRR include process improvements, process awareness, increased communication, and higher job satisfaction. [Conclusions] TRR has saved time at Ericsson, but the adoption of automated bug assignment was more intricate compared to similar endeavors reported from other companies. We primarily attribute the difference to the very large size of the organization and the complex products. Key facilitators in the successful adoption include a gradual introduction, product champions, and careful stakeholder analysis.

Semantic segmentation is one of the most fundamental problems in computer vision with significant impact on a wide variety of applications. Adversarial learning is shown to be an effective approach for improving semantic segmentation quality by enforcing higher-level pixel correlations and structural information. However, state-of-the-art semantic segmentation models cannot be easily plugged into an adversarial setting because they are not designed to accommodate convergence and stability issues in adversarial networks. We bridge this gap by building a conditional adversarial network with a state-of-the-art segmentation model (DeepLabv3+) at its core. To battle the stability issues, we introduce a novel lookahead adversarial learning (LoAd) approach with an embedded label map aggregation module. We focus on semantic segmentation models that run fast at inference for near real-time field applications. Through extensive experimentation, we demonstrate that the proposed solution can alleviate divergence issues in an adversarial semantic segmentation setting and results in considerable performance improvements (+5% in some classes) on the baseline for three standard datasets.

Magnetostrictive position sensors (MPS) are used for absolute long-range as well as for high-precision linear position measurement. The working principle of these sensors is based on a time-of-flight (TOF) measurement of a structure-borne sound wave within a magnetostrictive waveguide. State-of-the-art techniques only determine the position based on the measured TOF. Physically related parameters like velocity or acceleration are calculated by derivation of the determined position. In this paper, a novel method for real-time simultaneous estimation of position and velocity of a position marker is presented. Related to the position markers velocity eddy currents are induced within the MPS housing. The influence of the magnetic fields generated by this eddy currents leads to a velocity dependent impact on the structure-borne sound wave that is detected and evaluated by means of an artificial neural network. The training dataset for the velocity estimation is created from recorded datasets itself, without an external velocity reference system (self-training). Therefore, the electrical representation of the detected structure-borne sound wave is digitalized at high speed. Using the presented method, the velocity data could be used either as an additional independent parameter for consistency checking (self-diagnostics), or for the improvement of the position measurement by signal fusion (self-optimization).

In this work, we propose an interaction-driven approach streamlined to support and improve a wide range of real-time 2D interaction metaphors for arbitrarily large pointclouds based on detected primitive shapes. Rather than performing shape detection as a costly pre-processing step on the entire point cloud at once, a user-controlled interaction determines the region that is to be segmented next. By keeping the size of the region and the number of points small, the algorithm produces meaningful results and therefore feedback on the local geometry within a fraction of a second. We can apply these finding for improved picking and selection metaphors in large point clouds, and propose further novel shape-assisted interactions that utilize this local semantic information to improve the user's workflow.

We propose an approach to learn image representations that consist of disentangled factors of variation without exploiting any manual labeling or data domain knowledge. A factor of variation corresponds to an image attribute that can be discerned consistently across a set of images, such as the pose or color of objects. Our disentangled representation consists of a concatenation of feature chunks, each chunk representing a factor of variation. It supports applications such as transferring attributes from one image to another, by simply mixing and unmixing feature chunks, and classification or retrieval based on one or several attributes, by considering a user-specified subset of feature chunks. We learn our representation without any labeling or knowledge of the data domain, using an autoencoder architecture with two novel training objectives: first, we propose an invariance objective to encourage that encoding of each attribute, and decoding of each chunk, are invariant to changes in other attributes and chunks, respectively; second, we include a classification objective, which ensures that each chunk corresponds to a consistently discernible attribute in the represented image, hence avoiding degenerate feature mappings where some chunks are completely ignored. We demonstrate the effectiveness of our approach on the MNIST, Sprites, and CelebA datasets.

We present a novel system for sketch-based face image editing, enabling users to edit images intuitively by sketching a few strokes on a region of interest. Our interface features tools to express a desired image manipulation by providing both geometry and color constraints as user-drawn strokes. As an alternative to the direct user input, our proposed system naturally supports a copy-paste mode, which allows users to edit a given image region by using parts of another exemplar image without the need of hand-drawn sketching at all. The proposed interface runs in real-time and facilitates an interactive and iterative workflow to quickly express the intended edits. Our system is based on a novel sketch domain and a convolutional neural network trained end-to-end to automatically learn to render image regions corresponding to the input strokes. To achieve high quality and semantically consistent results we train our neural network on two simultaneous tasks, namely image completion and image translation. To the best of our knowledge, we are the first to combine these two tasks in a unified framework for interactive image editing. Our results show that the proposed sketch domain, network architecture, and training procedure generalize well to real user input and enable high quality synthesis results without additional post-processing.