A5041841729- Data Visualization and Analytics
- Human-Automation Interaction and Safety
- Anomaly Detection Techniques and Applications
- Maritime Navigation and Safety
- Team Dynamics and Performance
- Network Security and Intrusion Detection
- Neural Networks and Applications
- Time Series Analysis and Forecasting
- Advanced Text Analysis Techniques
- Advanced Clustering Algorithms Research
- Geographic Information Systems Studies
- Bayesian Modeling and Causal Inference
- Traffic and Road Safety
- Safety Warnings and Signage
- Building Energy and Comfort Optimization
- Sports Performance and Training
- Cell Image Analysis Techniques
- Risk and Safety Analysis
- Vehicle License Plate Recognition
- Sports Dynamics and Biomechanics
- Data Management and Algorithms
- Air Traffic Management and Optimization
- Systems Engineering Methodologies and Applications
- Gene expression and cancer classification
- Sports Analytics and Performance
Jönköping University
2020-2024
Infor (United States)
2024
University of Skövde
2011-2020
Hôpital Beaujon
2013
Inserm
2013
Université Paris Cité
2013
Assistance Publique – Hôpitaux de Paris
2013
To investigate the impact of visualizing car uncertainty on drivers' trust during an automated driving scenario, a simulator study was conducted. A between-group design experiment with 59 Swedish drivers carried out where continuous representation car's ability to autonomously drive snow conditions displayed one groups, whereas omitted for control group. The results show that, average, group who were provided took faster when needed, while they were, at same time, ones spent more time...
For many years, uncertainty visualization has been a topic of research in several disparate fields, particularly geographical (geovisualization), information visualization, and scientific visualization. Multiple techniques have proposed implemented to visually depict uncertainty, but their evaluation received less attention by the community. In order understand how influences reasoning decision-making using spatial visual displays, this paper presents comprehensive review assessments from...
The analysis of large amounts multidimensional road traffic data for anomaly detection is a complex task. Visual analytics can bridge the gap between computational and human approaches to detecting anomalous behavior in traffic, making process more transparent. In this paper, we present visual framework that provides support for: 1) exploration data; 2) normal behavioral models built from 3) events; 4) explanation events. We illustrate use with examples database real collected several areas...
Research in the social sciences has shown that expectations are an important factor explanations as used between humans: rather than explaining cause of event per se, explainer will often address another did not occur but explainee might have expected. For AI-powered systems, this finding suggests explanation-generating systems may need to identify such end user expectations. In general, is a challenging task, least because users keep them implicit; there thus investigate importance ability....
Elisidepsin (PM02734, Irvalec®) is a synthetic marine-derived cyclic peptide of the Kahalalide F family currently in phase II clinical development. was shown to induce rapid oncosis ErbB3-expressing cells. Other predictive factors elisidepsin sensitivity remained unknown. A panel 23 cancer cell lines different origin assessed for cytotoxicity and correlated with mutational state, mRNA protein expression selected genes. showed potent broad cytotoxic effects our line panel, being active at...
The increasing use of artificial intelligence (AI) technologies across application domains has prompted our society to pay closer attention AI's trustworthiness, fairness, interpretability, and accountability. In order foster trust in AI, it is important consider the potential interactive visualization, how such visualizations help build AI systems. This manifesto discusses relevance makes following four claims: i) not a technical problem, ii) dynamic, iii) visualization cannot address all...
This paper highlights the importance of uncertainty visualization in information fusion, reviews general methods representing and presents perceptual cognitive principles from Tufte, Chambers Bertin as well users experiments documented literature. Examples representations fusion are analyzed using these theories. These can be used future theoretical evaluations existing or newly developed techniques before usability testing with actual users.
Indoor occupancy prediction is a prerequisite for the management of energy consumption, security, health, and other systems in smart buildings. Previous studies have shown that buildings automatize their heating, lighting, air conditioning, ventilation through considering activity information might reduce consumption by more than 50%. However, it difficult to use high-resolution sensors cameras due privacy concerns. In this paper, we propose novel solution predicting using multiple low-cost...
The surveillance of large sea areas often generates huge amounts multidimensional data. Exploring, analyzing and finding anomalous behavior within this data is a complex task. Confident decisions upon the abnormality particular vessel require certain level situation awareness that may be difficult to achieve when operator overloaded by available information. Based on visual analytics process model, we present novel system supports acquisition involvement user in anomaly detection using two...
Abstract To find correlations and cause effect relationships in multivariate data sets is central many analysis problems. A common way of representing causal relations among variables to use node‐link diagrams, where nodes depict edges show between them. When performing a analysis, analysts may be biased by the position collected evidences, especially when they are at top list. This crucial importance since finding root or derived effect, searching for chains inferences essential analytic...
Solving the challenge of occupancy prediction is crucial in order to design efficient and sustainable office spaces automate lighting, heating, air circulation these facilities. In where large areas need be observed, multiple sensors must used for full coverage. cases, it normally important keep costs low, but also make sure that privacy people who use such environments are preserved. Low-cost low-resolution heat (thermal) can very useful build solutions address concerns. However, they...
This article presents an empirical user study that compares eight multidimensional projection techniques for supporting the estimation of number clusters, [Formula: see text], embedded in six data sets. The selection was based on their intended design, or use, visually encoding structures, is, neighborhood relations between points groups a set. Concretely, we study: difference estimates text] as given by participants when using different projections; accuracy estimations with respect to...
Maritime surveillance systems analyze vast amounts of heterogeneous sensor data from a large number objects. In order to support the operator while monitoring such systems, identification anomalous vessels or situations that might need further investigation may reduce operator's cognitive load. While it is worth acknowledging many existing mining applications behavior, autonomous anomaly detection are rarely used in real world, since behavior normally not well-defined problem and therefore,...
Recently, innovative technology like Trackman has made it possible to generate data describing golf swings. In this application paper, we analyze from 275 golfers using descriptive statistics and machine learning techniques. The overall goal is find non-trivial general patterns in the that can be used identify explain what separates skilled poor. Experimental results show random forest models, generated data, were able predict handicap of a golfer, with performance comparable human experts....
This paper presents an empirical study that evaluates the effects of visualizing missing data on decision-making tasks. A comparison between three visualization techniques: (1) emptiness, (2) fuzziness, and (3) emptiness plus explanation, revealed latter technique induced significantly higher degree decision-confidence than fuzziness. Moreover, explanation yield highest number risky choices three. result suggests uncertainty techniques affect decision-maker decisionconfidence. Additionally,...
The execution of teamwork varies widely depending on the domain and task in question. Despite considerable diversity teams their operation, researchers tend to aim for unified theories models regardless field. However, we argue that there is a need translation adaptation theoretical each specific domain. To this end, case study was carried out fighter pilots it investigated how performed specialised challenging environment, with focus dependence technology these teams. collaboration between...
Explanations in artificial intelligence (AI) ensure that users of complex AI systems understand why the system behaves as it does. Expectations may have about behaviour play a role since they co-determine appropriate content explanations. In this paper, we investigate user-desired explanations when unexpected ways. Specifically, presented participants with various scenarios involving an automated text classifier and then asked them to indicate their preferred explanation each scenario. One...
Monitoring the surveillance of large sea areas normally involves analysis huge quantities heterogeneous data from multiple sources (radars, cameras, automatic identification systems, reports, etc.). The rapid anomalous behavior or any threat activity in is an important objective for enabling homeland security. While it worth acknowledging that many existing mining applications support behavior, autonomous anomaly detection systems are rarely used real world. There two main reasons: (1) not a...