Time-series mining in a psychological domain

Kurbalija, Vladimir; Bernstorff, Charlotte von; Burkhard, Hans-Dieter; Nachtwei, Jens; Ivanović, Mirjana; Fodor, Lidija

doi:10.1145/2371316.2371328

Cited by 12 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also recognise the possibilities that could be brought by using mixed groups in experimental research, where some team members may be real users while others may be artificially set up (possible to inform/constitute from trials such as this) [45]. This would further increase the value of the microworld platform outcomes (e.g.…”

Section: Discussionmentioning

confidence: 99%

Teamwork evaluation with a microworld platform

Sapateiro

Antunes

Enwereuzo

et al. 2016

2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design (CSCWD)

View full text Add to dashboard Cite

We developed a platform supporting the evaluation of teamwork. The platform logs oral communications, collaborative tool usage and simulated physical action in the work environment. The paper brings forward observations derived from a comprehensive study of maintenance teams operating simulated network infrastructures. As positive results, we highlight that the platform supports a comprehensive analysis of teamwork at macro and micro levels, including individual and team activities, conducted in quasi naturalistic settings.

show abstract

Section: Discussionmentioning

confidence: 99%

Teamwork evaluation with a microworld platform

Sapateiro

Antunes

Enwereuzo

et al. 2016

2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design (CSCWD)

View full text Add to dashboard Cite

show abstract

“…In contrast to the basic SOM, these methods use a sequence of previous best matching units in deciding what the current best matching unit will be. This makes them suitable for unsupervised clustering of time series data such as speech signals [30], patterns from stock time-series [31], human behavioural patterns [32] and as well as robot's experiences [33] [34]. Even though these temporal self-organising neural networks have proven suitable for time-series and noisy datasets, they suffer some of the limitations of their base algorithms.…”

Section: Review Of Related Workmentioning

confidence: 99%

Unsupervised Temporospatial Neural Architecture for Sensorimotor Map Learning

Ezenkwu

Starkey

2021

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

The ability to learn the sensorimotor maps of unknown environments without supervision is a vital capability of any autonomous agent, be it biological or artificial. An accurate sensorimotor map should be able to encode the agent's world and equip it with the capability to anticipate or predict the results of its actions. However, to design a robust autonomous learning technique for an unknown, dynamic, partially observable or noisy environment remains a daunting task. This paper proposes a Temporospatial Merge Grow When Required (TMGWR) network for continuous self-organisation of an agent's sensorimotor awareness in noisy environments. TMGWR is an adaptive neural algorithm that learns the sensorimotor map of an agent's world using a time series self-organising strategy and the Grow When Required (GWR) algorithm. The algorithm is compared with GNG, GWR and TGNG in terms of their disambiguation performance, sensorial representation accuracy and sensorimotor-link error, a new metric that is developed in this paper to evaluate how well a sensorimotor map represents causality in the agent's world. The outcomes of the experiments show that TMGWR is more efficient and suitable for sensorimotor map learning in noisy environments than the competing algorithms.

show abstract

“…Psychological domain. The last example is devoted to a master's thesis [8], developed intensively using FAP, and it is related to research papers [16] and [18]. The subject of this thesis is analyzing log file data obtained from SAM experiments using the FAP framework in order to find the best distance measure.…”

Section: Figure 11mentioning

confidence: 99%

“…Three types of time series were extracted from the raw data: the first type describes the distance of the object from the starting point, the second type represents information about acceleration, and the third one specifies the deviations from the ideal trajectory (the shortest possible path). In [16], by applying hierarchical clustering on distance matrices (generated for these time series using the DTW, EDR and ERP distance measure) the ERP measure was selected as the most appropriate candidate to distinguish between the two types of navigators (i.e. "fast" and "accurate" navigators).…”

Section: Figure 11mentioning

confidence: 99%

See 1 more Smart Citation

Two Faces of the Framework for Analysis and Prediction, Part 1 - Education

Kurbalija

Ivanović

Geler

et al. 2018

ITC

Self Cite

View full text Add to dashboard Cite

With the ever-increasing amounts of data being generated in all walks of life and work, data analysis tools are gaining in importance and becoming essential in many application scenarios, including commerce, healthcare, research, and education. One important type of data are time series, which can be viewed as chronologically arranged arrays of numerical values that describe sequences of quantitative observations (e.g. in medical examinations, scientific and engineering experiments, etc.). In this article, we survey the successful applications of the Framework for Analysis and Prediction (FAP)-a Java-based tool dedicated to time-series analysis-in the area of education. Its utilization in this domain spans the development of several graphical user interfaces, as well as student projects illustrating and enhancing the capabilities of the system in the domains of time-series reconstruction, medicine (diagnosis), finance (stock value prediction) and psychology.

show abstract

Time-series mining in a psychological domain

Cited by 12 publications

References 8 publications

Teamwork evaluation with a microworld platform

Teamwork evaluation with a microworld platform

Unsupervised Temporospatial Neural Architecture for Sensorimotor Map Learning

Two Faces of the Framework for Analysis and Prediction, Part 1 - Education

Contact Info

Product

Resources

About