Predicting User Actions Using Interface Agents with Individual User Models

An underlying problem of current interface agent research is the failure to adequately address effective and efficient knowledge representations and associated methodologies suitable for modeling the users' interactions with the system. These user models lack the representational complexity to manage the uncertainty and dynamics involved in predicting user intent and modeling user behavior. A utility theory-based approach is presented for effective user intent prediction by incorporating the ability to explicitly model users' goals, the uncertainty in the users' intent in pursuing these goals, and the dynamics of users' behavior. We present an interface agent architecture, CIaA, that incorporates our approach and discuss the integration of CIaA with three disparate domains — a probabilistic expert system shell, a natural language input database query system, and a virtual space plane —that are being used as test beds for our interface agent research.

Multi-agent systems exhibit unexpected, emergent behavior as a result of the complexity of agent behaviors and their interactions. Despite significant research interest in the past decades, computational methods to identify and analyze emergence as it happens are still needed. This paper proposes a software architecture for identifying emergent behavior in a multi-agent system as it happens, using interval-based snapshots and emergent behavior metrics. We propose various distance functions to compare between the multi-agent system under analysis and systems that have been previously shown to exhibit emergent behavior.

A formalization of multi-agent systems (MAS) as hidden Markov models (HMM) is proposed and investigated from a view point of interaction among agents and environments. Conventional formalizations of agents as HMM do not take changes of environments in account, so that it is hard to analyze behaviors of agents that act in dynamic environments. The proposed formalization enables HMM to handles changes of environment and interaction among agents via environment directly inside of state-transitions. I first investigate HMM that represents changes of the environment in the same state-transitions of agent itself. Then I derive a structured model in which environment, agent, and another agent are treated as separated state-transitions and coupled with each other. For this model, in order to reduce the number of parameters, I introduce “symmetricity” among agents. Moreover, I discuss relation between reducing dependency in transitions and assumption of cooperative behaviors in MAS.

Predicting user behavior is an important issue in Human Computer Interaction ([5]) research, having an essential role when developing intelligent user interfaces. A possible solution to deal with this challenge is to build an intelligent interface agent ([8]) that learns to identify patterns in users behavior. The aim of this paper is to introduce a new agent based approach in predicting users behavior, using a probabilistic model. We propose an intelligent interface agent that uses a supervised learning technique in order to achieve the desired goal. We have used Aspect Oriented Programming ([7]) in the development of the agent in order to benefit of the advantages of this paradigm. Based on a newly defined evaluation measure, we have determined the accuracy of the agent's prediction on a case study.

Optimization of performance in collective systems often requires altruism. Emergence and stabilization of altruistic behaviors are difficult because the agents incur a cost when behaving altruistically. In this paper we propose a biologically inspired strategy to learn stable altruistic behaviors in artificial multi-agent systems, namely reciprocal altruism. Our multi-agent system is made up of autonomous agents with a behavior-based architecture. Agents learn the most suitable cooperative strategy for different environments by means of a reinforcement learning algorithm. Each agent receives a reinforcement signal that only measures its individual performance. Simulation results show how the multi-agent system learns stable altruistic behaviors, so reaching optimal (or near-to-optimal) performances in unknown and changing environments.

Typical tag recommendation systems for photos shared on social networks such as Flickr, use visual content analysis, collaborative filtering or personalization strategies to produce annotations. However, the dependence on manual intervention and the knowledge of sufficient personal preferences coupled with the folksonomic issues limit the scope of these strategies. In this paper, we present a fully automatic and folksonomically scalable tag recommendation model that can recommend tags for a user's photos without an explicit knowledge of the user's personal tagging preferences. The model is learned using the collective tagging behavior of other users in the user's local interaction network, which we believe approximates the user's preferences, at least partially. The tag recommendation model generates content-based annotations and then uses a Naive Bayes formulation to translate these annotations to a set of folksonomic tags selected from the tags used by the users in the local interaction network. Quantitative and qualitative comparisons with 890 Flickr networks show that this approach is highly useful for tag recommendation in the presence of insufficient information of a user's own preferences.

With the constant development of socialist modernization construction in our country, our country's computer information technology has made effective progress, and makes the world into an information age. People's production and life style experience a series of change. However, with the emergence of information diversity and multi-user mode, traditional computer information technology already can't satisfy people's needs, and the development and application of cloud computing technology come to the stage. This article focuses on analyzing the big data user behavior engine design under cloud computing technology, covering big data flow management, multi-user system design, and other aspects to explore the effect of the system test. In recent years, China's mobile Internet technology has made full development, which makes the Internet operators in our country face a new development opportunity and began from traffic management to flow management. The law of user behavior is analyzed to explore the real demand of market and the users. In order to fully meet the changing needs of users, operators must constantly develop and launch new products and strengthen the function of computer technology. Cloud computing technology is such kind of engine system which can satisfy the analysis and processing of huge amounts of data. RESEARCH ON CLOUD COMPUTING SYSTEM OVERALL DESIGN The overall architecture of cloud computing system This study mainly uses cloud computing technology’s huge amounts of data computing to set up complete mobile Internet data mining analysis system. Realize the analysis for Internet user behavior engine, and according to the user's preferences online habits and behavior, provide users with targeted personalized service and form a unified organic whole of data collection, analysis and service type and marketing strategy to improve enterprise's marketing efficiency. In addition, cloud computing system mainly realizes data collection with the help of FTP server, and makes distributed computing and data batch processing at the system interface. Large data shall be deposited in Hbase database. The system can not only realize mass data storage, but those unstructured data storage. Then through Hive integration layer and summary EIL processing, use MapReduce data analysis model to transmit the processing result into the database. The system’s overall structure is shown in Figure 1: 3rd International Conference on Materials Engineering, Manufacturing Technology and Control (ICMEMTC 2016) © 2016. The authors Published by Atlantis Press 1351 Figure 1 The overall architecture of cloud computing system System topology and function distribution System topology mainly refers that a server is taken as Hapdoop platform’s master node server, and the others are Hapdoop platform’s node servers. In general, node server can be dynamically extended according to the actual need, and the master node server not only assigns tasks and flow to node server, but also monitors the work execution of the node server. More than one node server participates to complete the task, and it can improve data processing efficiency. The master node server’s software running status is shown in Figure 2: Figure 2 Master node server function structure

Implementing collective behaviour in cooperative multi-agent systems requires several practical constraints to be addressed. In some environments, communication bandwidth is a critical constraint which may compromise the intended cooperative behaviour. This paper introduces a bio-inspired model which invokes collective behaviour in a multi-agent system using passive sensing without any explicit inter-agent communication. An agent looks for the majority of its neighbours either in its left or its right half space using two sensors. For a source localization problem, we compare performance of the proposed model using passive sensing against the well known school-of-fish collective behaviour models using ideal explicit inter-agent communication. For different cue strengths and neighbourhood radii, our results show that the proposed strategy boosts higher levels of group cohesion to make up for the information loss and in certain conditions performs better than the other collective behaviour models.

The behavior of users concerning mobile Internet varies significantly throughout the day. Results from existing studies—which generally simply segment one day into morning, afternoon, and evening—often provide inaccurate predictions of the behavior of users. To improve prediction accuracy, we propose a segment-based multi-state Markov (SBMSM) model for the dynamic time interval segmentation of the sequential behavior of users. The specific procedure of this proposed model can be described as follows: first, we divide each user’s behaviors into minimum unit according to time dimension; then, we merge adjacent time intervals or ensure they are constant according to the similarities in behavior; and finally, a multi-state Markov (MSM) model is trained using the newly constructed data individually. The experimental results illustrate that for 95.78% of users, an SBMSM model performs much better than a naive MSM model and hidden Markov model.

UD-HMM: An unsupervised method for shilling attack detection based on hidden Markov model and hierarchical clustering

Cultural ecosystem services, a complex interplay between humans and landscapes, significantly influence identity, well-being, and social connections. These services, provided through natural and cultural landscapes, can be better understood through spatial data. Using geotagged photos from Flickr, this study delves into user behavior and preferences in Denizli, Türkiye. The aim is to enrich sustainable landscape management by mapping temporal and spatial changes in visitor patterns. The spatial distribution patterns revealed that user activities are predominantly scattered around the city center, historical sites, cultural hubs, and facilities-equipped recreational places. The findings unveiled a concentration in the northwest region in terms of cultural heritage, aesthetic, and recreational values. The period when visitors shared the most photos was between July and October. The study's originality lies in its unique approach to mapping visitor-preferred hotspots and landscape values at the provincial scale, identifying previously unmentioned locations such as Maymun Mountain and the Dodurgalar district. The research underscores the importance of integrating natural and cultural landscape values into urban management and ensuring coordinated efforts to maintain the uniqueness of cities. The practical implications of this study are significant, as they provide valuable insights for urban planners and policymakers interested in sustainable landscape management. Despite the methodological constraints of geotagged social media data, it remains a more time and cost-effective tool. It provides abundant and up-to-date information on user preferences and movements, enabling analysis of spatial and temporal patterns.

Large-scale data has been generated in the real daily life by many kinds of electric devices. We can utilize such data to construct computational human models that predict user's behavior, consumer's preference, and so on. Probabilistic models, statistical learning and probabilistic inference method can be applied for computational human modeling. In this paper, examples of applications using Bayesian networks are shown. Bayesian networks have advantage that can represent mutual interaction for situation depend user's preference models. One good example is a contents recommendation depends on different situations and users. In order to get large-scale data corresponding to many kinds of different situations, point of act data collection scheme during service providing is necessary. We call this data collection scheme 'research as a service'. This human modeling framework is also discussed as a key technology for service engineering to improve productivity of service industry.

In this paper, we discuss a Work Process Agent (WPA) that enables users to access a range of services for achieving their tasks with service composition based on planning in ubiquitous computing environment. WPA is a smart assistant application specializing in information service which needs to provide each user's own user model and make the model be adapted to the user's preferences dynamically. With WPA, users can achieve their task in a simple way. WPA employs a special BDI-based coordinator agent with planning for coordinating the individual WPA and external services. The plan-based service composition model works at abstraction level of process. This model makes it possible to reuse the frames of plans by making it independent from domain.

Studies have been made on computer systems based on the user model reflecting the behavior of the users, aiming at the human interface which is easy to use. Recently, it has been proposed that individual models be constructed for the users, rather than a model where the only one “typical” human model represents the user in general. A case has not been observed, however, where the individual model is utilized fully in the interactive computer system which actually requires such an approach. From such a viewpoint, this paper proposes a generation of suitable messages utilizing the individual user model, by restricting the problem to the generation of the messages from the computer side in the construction of a program in the interactive programming environment. The features of the user model which will be useful in such a problem, are pointed out. The points in this study are that the skill of the user concerning the system is separated into the general understanding level and the knowledge of the individual functions; utilization of the information obtained by the operating system and for the language processor; and object‐oriented user model whose contents are always updated. A human interface was implemented experimentally which indicates the individual user, the error message from Lisp interpreter according to each situation. We have conducted an experiment by using the interface. The usefulness of our method was demonstrated by the result of experiment.

Aiming at the data security problem of the system in the network environment, this paper uses the hidden Markov model to analyze the user's access behavior in the network system and identify the malicious user behavior. First, the behavior characteristics of network users are analyzed, and then according to the related characteristics of hidden Markov, the observation order symbol and hidden state in the model are determined, and the user's access behavior is mapped into a hidden Markov chain. We give detailed experiments to prove the feasibility of applying the hidden Markov model to network user behavior authentication, and compare with other methods to get the accuracy of the model.