Simulate User Behavior Research Articles

An agent-based workflow for evaluating interpersonal visibility in healthcare environment

ABSTRACT Healthcare environment design evaluation (HEDE) can help create a safe environment, and interpersonal visibility among users is a key metric for assessing the safety of HEDE due to its role in caregiving observation. Traditional tools for visibility evaluation mainly focus on physical obstructions, neglecting the impact of the user’s mobility behavior, which is common in the healthcare environment. To address this challenge, this study developed a five-step workflow to evaluating interpersonal visibility among mobile users in healthcare environment: 1) collection of empirical behavior data from users; 2) construction of user journeys; 3) validation of agent-based simulation (ABS) reliability; 4) utilization of ABS to simulate user behavior in a virtual environment; and 5) computation of total visibility duration and time intervals between users using the parametric computation tool. This workflow was tested in 25 long-term care facilities for the elderly with dementia and subsequently evaluated by experts. The evaluation results confirm the effectiveness of this workflow. The core contribution and novelty of this workflow lie in its integration of ABS and parametric computation, which enables the evaluation of interpersonal visibility among mobile users, thereby contributing to the safety of the healthcare environment.

F3l: an automated and secure function-level low-overhead labeled encrypted traffic dataset construction method for IM in Android

Fine-grained function-level encrypted traffic classification is an essential approach to maintaining network security. Machine learning and deep learning have become mainstream methods to analyze traffic, and labeled dataset construction is the basis. Android occupies a huge share of the mobile operating system market. Instant Messaging (IM) applications are important tools for people communication. But such applications have complex functions which frequently switched, so it is difficult to obtain function-level labels. The existing function-level public datasets in Android are rare and noisy, leading to research stagnation. Most labeled samples are collected with WLAN devices, which cannot exclude the operating system background traffic. At the same time, other datasets need to obtain root permission or use scripts to simulate user behavior. These collecting methods either destroy the security of the mobile device or ignore the real operation features of users with coarse-grained. Previous work (Chen et al. in Appl Sci 12(22):11731, 2022) proposed a one-stop automated encrypted traffic labeled sample collection, construction, and correlation system, A3C, running at the application-level in Android. This paper analyzes the display characteristics of IM and proposes a function-level low-overhead labeled encrypted traffic datasets construction method for Android, F3L. The supplementary method to A3C monitors UI controls and layouts of the Android system in the foreground. It selects the feature fields of attributes of them for different in-app functions to build an in-app function label matching library for target applications and in-app functions. The deviation of timestamp between function invocation and label identification completion is calibrated to cut traffic samples and map them to corresponding labels. Experiments show that the method can match the correct label within 3 s after the user operation.

A joint machine learning and optimization approach for incremental expansion of electric vehicle charging infrastructure

As Electric vehicle (EV) adoption increases worldwide, public charging infrastructure must be expanded to meet the growing charging demand. Furthermore, insufficient and improperly deployed public charging infrastructure poses a real risk of slowing EV adoption. The infrastructure thus needs to be expanded intelligently and flexibly while accounting for uncertain dynamics in future charging demand. Nevertheless, current methods for demand-based expansion often rely on rigid and error-prone tools, such as travel surveys and simple rules of thumb. The former is more appropriate for long-term, equilibrium scenarios, where we consider the charging network as a whole rather than incrementally expanding it. At the same time, the latter relies on business experience in a rapidly changing field. We propose a predictive optimization approach for intelligent incremental expansion of charging infrastructure. At each time step, we estimate the future charging demand through a Gaussian Process, which is subsequently used in a linear chance-constrained optimization method to expand the charging infrastructure incrementally. To develop and validate this framework, we account for environmental feedback by simulating user behavior changes based on historical charging records and considering an optimized charging network at every iteration. We apply this approach to a case study of EV charging in Dundee, Scotland. We compare different strategies and reasons for their pros and cons for monthly incremental expansion of the charging network. In particular, combining machine learning and optimization results in the cheapest expansion and one that serves the most demand.

Research on the Innovation of UAV Products for Urban Traffic Accidents based on Interaction Design

To improve the efficiency of traffic accident handling and reduce the inconvenience and casualties caused by accidents. Analyze traffic accident handling methods and existing products, extract design goals, simulate user behavior and emotional changes, and innovate interaction models in traffic accident scenarios. The article uses traffic drones' product design as an example to show the product appearance and technical detail design. Obtaining a UAV that can efficiently handle traffic accidents This case can provide a reference for improving traffic accident handling efficiency and future related product innovation.

Pre-Occupancy Evaluation based on user behavior prediction in 3D virtual simulation

Abstract Because Post-Occupancy Evaluation (POE), one of the most commonly used design evaluation methods, is conducted by users after the completion of construction, it has time and cost limitations for the improvement of physical conditions. To solve this problem, this study proposes a method of Pre-Occupancy Evaluation (PrOE) which can evaluate and improve a design prior to construction by simulating user behavior in the virtual space of the design. A user model, space model and evaluation logic model are used for the evaluation simulation. In the simulation, a virtual user perceives 3D spatial objects within a target virtual space and performs reactions to the perceived objects according to an evaluation logic. The evaluation logic model consists of spatial properties that influence user behavior, and their assessed values. To verify the proposed method, burglary prediction in an urban block was carried out as a case study. The proposed PrOE can overcome the limitation of the conventional approach of design evaluation in that it evaluates designs in advance by reflecting on user requirements, thus making efficient design improvements possible.

Infrastructure to simulate intelligent agents in cloud environments

Nowadays there is a clear trend towards using methods and tools that can help the development of Simulation Systems. In this regard, Multiagent System (MAS) is a key technology that allows simulating user behavior. When the user is the focus of the simulation, Ambient Intelligent (AmI) increases in importance. AmI is an emerging multidisciplinary area based on ubiquitous computing that aims to adapt the environment to the needs of the user. Moreover, Cloud Computing is revolutionizing the services provided through the Internet, continually adapting itself in order to maintain the quality of its services. This study presents a multiagent based middleware for the simulation of agent behavior in cloud environments, and uses this information to adapt to the environment as AmI proposed. The main challenge of this work is the design and development of a new middleware that makes possible the communication between the technology in charge of the development of MAS and the technology in charge of the simulation, visualization and analysis of the behavior of the agents using the potential of cloud computing. The platform makes the computation and communication possible by following the principles proposed by AmI.

Goal attainment on long tail web sites: An information foraging approach

The long tail has attracted substantial theoretical as well as practical interest, yet there have been few empirical studies that have explicitly examined the factors that drive online conversions at these sites. This research tests several hypotheses derived from Information Foraging Theory (IFT) that pertain to goal achievement on long tail Web sites. IFT introduced concepts of information patches and information scent to model information seeking behavior of individuals, but has mostly been tested in production rule environments where the theory is used to simulate user behavior. Testing IFT-driven hypotheses on real data required learning information patches and scents using an inductive approach and in this paper we adapt existing algorithms for these discovery tasks. Our results based on clickstream data from forty-seven small business Web sites show both the existence of valuable information patches and information scent trails as well as their importance in explaining conversion on these sites. The majority of the hypotheses were supported and we discuss the implications of this for researchers and practitioners.

Understanding Cognitive Strategy With Adaptive Automation in Dual-Task Performance Using Computational Cognitive Models

The objectives of this study were to investigate the effects of advance auditory cuing of control mode changes in an adaptively automated system on human performance and to explain cognitive behaviors at mode changes by using a computational cognitive model. A dual-task piloting simulation, involving tracking and tactical decision making, was developed to collect human performance data with auditory cuing or no cuing of mode transitions in the tactical task. Computational GOMS (goal, operators, methods, and selection) language models were coded to simulate user behavior on the basis of expectation of increased memory transactions (between long-term and working stores) at mode transitions. The models were applied to the same task simulation and scenarios performed by the humans. Human performance data did not reveal differences between cued and no-cue trials possibly because of distraction from the tracking (secondary loading) task. Comparison of results for human and model output demonstrated the model to be descriptive of the pattern of human performance across conditions but not accurate in predicting timing of memory use in preparing for manual control. A refined GOMS language model was coded on the basis of a modified assumption that memory stores are used on an ad hoc basis after high-workload mode transitions and with consideration of human parallel processing in dual-task performance. Results revealed the refined model to have greater plausibility for representing actual behavior. The manner of operator use of memory stores for controlling an adaptive system provides insight into the impact of cuing of mode transitions and a basis for future systems design.

Computational GOMSL Modeling towards Understanding Cognitive Strategy in Dual-Task Performance with Automation

The objective of this study was to assess the use of a computational cognitive model for describing human performance with an adaptively automated system, with and without advance cueing of control mode transitions. A dual-task piloting simulation was developed to collect human performance data under auditory cueing or no cueing of automated or manual control. GOMSL models for simulating user behavior were constructed based on a theory of increased memory transactions at mode transitions. The models were applied to the same task simulation and scenarios performed by the humans. Comparison of results on human and model output demonstrated the model to be generally descriptive of performance; however, it was not accurate in predicting timing of memory use in preparing for manual control. Interestingly, the human data didn't reveal differences between cued and no cue trials. A refined GOMSL model was developed by modifying assumptions on the timing and manner of memory use, and considering human parallel processing in dual-task performance. Results revealed the refined model to be more plausible for representing behavior. Computational cognitive modeling appears to be a viable approach to represent operator performance in adaptive systems.

Towards a multi-agent model for visualizing simulated user behavior to support the assessment of design performance

We introduce the outline of a multi-agent model that can be used for visualizing simulated user behavior to support the assessment of design performance. We will consider various performance indicators of building environments, which are related to user reaction to design decisions. This system may serve as a media tool in the design process for a better understanding of what the design will look like, especially for those cases where design or planning decisions will affect the behavior of individuals. The system is based on cellular automata and multi-agent simulation technology. The system simulates how agents move around in a particular 3D (or 2D) environment, in which space is represented as a lattice of cells. Agents represent objects or people with their own behavior, moving over the network. Each agent will be located in a simulated space, based on the cellular automata grid. Each iteration of the simulation is based on a parallel update of the agents conforming local rules. Agents positioned within an environment will need sensors to perceive their local neighborhood and some means with which to affect the environment. In this way, autonomous individuals and the interaction between them can be simulated by the system. As a result, designers can use the system to assess the likely consequences of their design decisions on user behavior. We think that the system provides a potentially valuable tool to support design and decision-making processes, related to user behavior in architecture and urban planning.

Towards Usable Icon Sets: A Case Study from Telecommunications Engineering

Converging experimental tasks were used to address the development of usable interactive icon sets for telecommunications network applications. Naming and matching addressed the individual informativeness value of an icon, with naming reflecting natural context response biases and familiarity contributions more than matching. Naming also allowed intrusions to be identified early. Preference ratings simulated user behavior with iconic menus, and provided discriminability data that could help to select icons where naming and matching revealed only failures. Issues resolved and revealed during this work are discussed.