Ecological Interface Design for Computer Network Defense

Application of Big Data Clustering and Visual Communication in Business Website Interface Design

The interface design of commercial websites is used in this paper to demonstrate the application of big data clustering and visual communication technologies. This paper presents the new requirements of user integration, emotion, and personalization by analyzing the broad influence of big data clustering technology and visual communication on the design concept and design method of commercial website interface design. Then, focusing on the information of visual graphic elements in web interface design and discussing how structures, images, words, emotions, and other elements can convey information more effectively through graphic means, the information in the web interface is creatively divided into two types: implicit and explicit. The database for the interface interaction system is built as part of this paper, which also uses fuzzy clustering to organize the data from the interface retrieval database and the hierarchical structure design method of process constraints to carry out interface information interaction and big data fusion processing. According to experiments, this algorithm’s accuracy can reach 95.75%, which is about 11% higher than that of other approaches. This study can offer a workable design strategy for a business website’s user interface.

Detecting and Responding to Information Overload With an Adaptive User Interface

OBJECTIVE

The objective of this study was to develop and evaluate an adaptive user interface that could detect states of operator information overload and calibrate the amount of information on the screen.

BACKGROUND

Machine learning can detect changes in operating context and trigger adaptive user interfaces (AUIs) to accommodate those changes. Operator attentional state represents a promising aspect of operating context for triggering AUIs. Behavioral rather than physiological indices can be used to infer operator attentional state.

METHOD

In Experiment 1, a network analysis task sought to induce states of information overload relative to a baseline. Streams of interaction data were taken from these two states and used to train machine learning classifiers. We implemented these classifiers in Experiment 2 to drive an AUI that automatically calibrated the amount of information displayed to operators.

RESULTS

Experiment 1 successfully induced information overload in participants, resulting in lower accuracy, slower completion time, and higher workload. A series of machine learning classifiers detected states of information overload significantly above chance level. Experiment 2 identified four clusters of users who responded significantly differently to the AUIs. The AUIs benefited performance, completion time, and workload in three clusters.

CONCLUSION

Behavioral indices can successfully detect states of information overload and be used to effectively drive an AUI for some user groups. The success of AUIs may be contingent on characteristics of the user group.

APPLICATION

This research applies to domains seeking real-time assessments of user attentional or psychological state.

Visual displays for cyber network defense

Five computer network Defence displays (one Alphanumeric and four graphical displays: Radial Traffic Analyser, Bar Graph, Cube, and Treemap) were evaluated. Two experiments were conducted using different methodological procedures. Participants responded to questions that were structured to approximate various ways in which analysts might need to consider network traffic. Numerous significant effects were obtained and a fairly clear rank ordering of performance for the four graphical displays was obtained across experiments (from best to worst): Bar Graph, Cube, Radial Traffic Analyser, and Treemap. The results are interpreted from the perspective of ecological interface design: the quality of performance is directly related to the quality of semantic mapping between work domain, display, and human constraints. Factors that may have contributed to the poor performance for the Radial Traffic Analyser and Treemap displays are discussed. General implications for display and interface design are provided. Practitioner summary: Proposed displays for computer network Defence are evaluated; the results are interpreted from the perspective of ecological interface design. The associated design principles are applicable to all analogical graphical displays. Abbreviation: CND: cyber network defence; CSE: cognitive systems engineering; EID: ecological interface design; ICMP: internet control message protocol; IP: internet protocol; RTA: radial traffic analyzer; TCP: transmission control protocol; UDP: user datagram protocol.