Abstract: In the setting of multi-instance learning, each object is represented by a bag composed of multiple instances instead of by a single instance in a traditional learning setting. Previous works in this area only concern multi-instance prediction problems where each bag is associated with a binary (classification) or real-valued (regression) label. However, unsupervised multi-instance learning where bags are without labels has not been studied. In this paper, the problem of unsupervised multi-instance learning is addressed where a multi-instance clustering algorithm named Bamic is proposed. Briefly, by regarding bags as atomic data items and using some form of distance metric to measure distances between bags, Bamic adapts the popular k -Medoids algorithm to partition the unlabeled training bags into k disjoint groups of bags. Furthermore, based on the clustering results, a novel multi-instance prediction algorithm named Bartmip is developed. Firstly, each bag is re-represented by a k-dimensional feature vector, where the value of the i-th feature is set to be the distance between the bag and the medoid of the i-th group. After that, bags are transformed into feature vectors so that common supervised learners are used to learn from the transformed feature vectors each associated with the original bag's label. Extensive experiments show that Bamic could effectively discover the underlying structure of the data set and Bartmip works quite well on various kinds of multi-instance prediction problems.

Abstract: This study presents an ontology-based computational intelligent multi-agent system for Capability Maturity Model Integration (CMMI) assessment. An ontology model is developed to represent the CMMI domain knowledge that will be adopted by the computational intelligent multi-agent. The CMMI ontology is predefined by domain experts, and created by the ontology generating system. The computational intelligent multi-agent comprises a natural language processing agent, an ontological reasoning agent and a summary agent. The multi-agent deals with the evaluation reports from the natural language processing agent, infers the term relation strength between the ontology and the evaluation report, and then summarizes the main sentences of the evaluation report. The summary reports are meanwhile transmitted back to the domain expert, which makes the domain expert further adjust the CMMI ontology. Experimental results indicate that the ontology-based computational intelligent multi-agent can effectively summarize the evaluation reports for the CMMI assessment.

Abstract: This paper introduces an extension to the well-established Resource-Constrained Project Scheduling Problem for the comprehensive description of disruption management problems. This conceptual framework employs the concept of alternative activities to consider both the temporal shift of activities or the reallocation of resources and switches from one valid process variant to another one. Activities can be serialized or parallelized, process steps can be inserted or removed and durations as well as resource requirements can be modified dynamically during optimization. Focusing on the domain of the aircraft turnaround as the most important airport ground process, we illustrate how the Extended RCPSP (x-RCPSP) can be applied for decision support. A specific evolutionary algorithm is presented that identifies good-quality solutions to relatively large disruption management problems within only a few seconds. The results of the evaluation illustrate fast convergence on good or optimal schedules and serve as a basis for the development of future problem solving algorithms.

Abstract: Appraisal theories in psychology study facial expressions in order to deduct information regarding the underlying emotion elicitation processes. Scherer's component process model provides predictions regarding particular face muscle deformations that are attributed as reactions to the cognitive appraisal stimuli in the study of emotion episodes. In the current work, MPEG-4 facial animation parameters are used in order to evaluate these theoretical predictions for intermediate and final expressions of a given emotion episode. We manipulate parameters such as intensity and temporal evolution of synthesized facial expressions. In emotion episodes originating from identical stimuli, by varying the cognitive appraisals of the stimuli and mapping them to different expression intensities and timings, various behavioral patterns can be generated and thus different agent character profiles can be defined. The results of the synthesis process are consequently applied to Embodied Conversational Agents (ECAs), aiming to render their interaction with humans, or other ECAs, more affective.

Abstract: Frequent itemset mining methods basically address time scalability and greatly rely on available physical memory. However, the size of real-world databases to be mined is exponentially increasing, and hence main memory size is a serious bottleneck of the existing methods. So, it is necessary to develop new methods that do not fully rely on physical memory; new methods that utilize the secondary storage in the mining process should be the target. This motivates the work described in this paper; we mainly propose (Disk Resident Frequent Pattern) DRFP-Growth as a disk based approach similar to FP-Growth. DRFP-growth uses DRFP-tree, which is treated exactly as FP-tree when constructed in main memory and gets into a modified structure when it turns into disk resident to overcome the main memory bottleneck. This way, we are able to mine for frequent itemsets from databases of arbitrary sizes without being restricted by the available physical memory. In other words, we initially try to mine the database using the original FP-growth; we expand into the secondary memory only if we run out of physical memory. So, DRFP-growth is very comparable to FP-growth for small databases and high support threshold values. On the other hand, using DRFP-growth, we are still able to mine huge databases for low support threshold values (the only limitation is the available secondary storage rather than physical memory). The reported test results demonstrate how the proposed approach succeeds for cases where main memory based approaches fail.

Abstract: This paper applies divide and conquer approach in an iterative way to handle the clustering process. The target is a parallelized effective and efficient approach that produces the intended clustering result. We achieve scalability by first partitioning a large dataset into subsets of manageable sizes based on the specifications of the machine to be used in the clustering process; then cluster the partitions separately in parallel. The centroid of each obtained cluster is treated like the root of a tree with instances in its cluster as leaves. The partitioning and clustering process is iteratively applied on the centroids with the trees growing up until we get the final clustering; the outcome is a forest with one tree per cluster. Finally, a conquer process is performed to get the actual intended clustering, where each instance (leaf node) belongs to the final cluster represented by the root of its tree. We use multi-objective genetic algorithm combined with validity indices to decide on the number of classes. This approach fits well for interactive online clustering. It facilitates for incremental clustering because chunks of instances are clustered as stand alone sets, and then the results are merged with existing clusters. This is attractive and feasible because we consider the clustering of only centroids after the first clustering stage. The reported test results demonstrate the applicability and effectiveness of the proposed approach.

Abstract: We propose a partial information state-based framework for collaborative dialogue and argument between agents. We employ a three-valued based nonmonotonic logic, NML3, for representing and reasoning about Partial Information States (PIS). NML3 formalizes some aspects of revisable reasoning and it is sound and complete. Within the framework of NML3, we present a formalization of some basic dialogue moves and the rules of protocols of some types of dialogue. The rules of a protocol are nonmonotonic in the sense that the set of propositions to which an agent is committed and the validity of moves vary from one move to another. The use of PIS allows an agent to expand consistently its viewpoint with some of the propositions to which another agent, involved in a dialogue, is overtly committed. A proof method for the logic NML3 has been successfully implemented as an automatic theorem prover. We show, via some examples, that the tableau method employed to implement the theorem prover allows an agent, absolute access to every stage of a proof process. This access is useful for constructive argumentation and for finding cooperative and/or informative answers.

Abstract: Customers interacting with online selling platforms require the assistance of sales support systems in the product and service selection process. Knowledge-based recommenders are specific sales support systems which involve online customers in dialogs with the goal to support preference forming processes. These systems have been successfully deployed in commercial environments supporting the recommendation of, e.g., financial services, e-tourism services, or consumer goods. However, the development of user interface descriptions and knowledge bases underlying knowledge-based recommenders is often an error-prone and frustrating business. In this paper we focus on the first aspect and present an approach which supports knowledge engineers in the identification of faults in user interface descriptions. These descriptions are the input for a model-based diagnosis algorithm which automatically identifies faulty elements and indicates those elements to the knowledge engineer. In addition, we present results of an empirical study which demonstrates the applicability of our approach.

Abstract: Earlier works on detecting spam e-mails usually compare the contents of e-mails against specific keywords, which are not robust as the spammers frequently change the terms used in e-mails. We have presented in this paper a novel featuring method for spam filtering. Instead of classifying e-mails according to keywords, this study analyzes the spamming behaviors and extracts the representative ones as features for describing the characteristics of e-mails. An back-propagation neural network is designed and implemented, which builds classification model by considering the behavior-based features revealed from e-mails’ headers and syslogs. Since spamming behaviors are infrequently changed, compared with the change frequency of keywords used in spams, behavior-based features are more robust with respect to the change of time; so that the behavior-based filtering mechanism outperform keyword-based filtering. The experimental results indicate that our methods are more useful in distinguishing spam e-mails than that of keyword-based comparison.

Abstract: Fraudulent and malicious web sites pose a significant threat to desktop security, integrity, and privacy This paper examines the threat from different perspectives We harvested URLs linking to web sites from different sources and corpora, and conducted a study to examine these URLs in-depth For each URL, we extract its domain name, determine its frequency, IP address and geographic location, and check if the web site is accessible Using 3 search engines (Google, Yahoo!, and Windows Live), we check if the domain name appears in the search results; and using McAfee SiteAdvisor, we determine the domain name's safety rating Our study shows that users can encounter URLs pointing to fraudulent and malicious web sites not only in spam and phishing messages but in legitimate email messages and the top search results returned by search engines To provide better countermeasures against these threats, we present a proxy-based approach to dynamically block access to fraudulent and malicious web sites based on the safety ratings set by McAfee SiteAdvisor

Abstract: This article addresses the problem of detecting configurations and activities of small groups of people in an augmented environment. The proposed approach takes a continuous stream of observations coming from different sensors in the environment as input. The goal is to separate distinct distributions of these observations corresponding to distinct group configurations and activities. This article describes an unsupervised method based on the calculation of the Jeffrey divergence between histograms over observations. These histograms are generated from adjacent windows of variable size slid from the beginning to the end of a meeting recording. The peaks of the resulting Jeffrey divergence curves are detected using successive robust mean estimation. After a merging and filtering process, the retained peaks are used to select the best model, i.e. the best allocation of observation distributions for a meeting recording. These distinct distributions can be interpreted as distinct segments of group configuration and activity. To evaluate this approach, 5 small group meetings, one seminar and one cocktail party meeting have been recorded. The observations of the small groups meetings and the seminar were generated by a speech activity detector, while the observations of the cocktail party meeting were generated by both the speech activity detector and a visual tracking system. The authors measured the correspondence between detected segments and labeled group configurations and activities. The obtained results are promising, in particular as the method is completely unsupervised.

Abstract: Non-repudiation of a mobile payment transaction ensures that when a buyer (B) sends some messages to a seller (S), neither B nor S can deny having participated in this transaction. An evidence of a transaction is generated by wireless PKI mechanism such that B and S cannot repudiate sending and receiving the purchase order respectively. The buyer generates a mobile agent which carries encrypted purchase order to the seller. This mobile agent is also issued a proxy certificate by the buyer; this certificate guarantees the binding relationship between them. One trusted third party acts as a lightweight notary for evidence generation. One advantage of this agent-based non-repudiation protocol is to reduce inconvenience for mobile clients such as connection time; it causes difficulty for fair transaction for mobile payments.

Abstract: In this article we discuss the problem of inferring threats in an urban environment, where the knowledge of the environment involves multiple types of intelligence and infrastructure data, and is by nature uncertain or approximate. We use a collection of situation-aware agents to infer potential threats in such environments, where agents are responsible for event correlation and situation assessment. We review the weaknesses of a current approach to threat assessment in Homeland Security and then describe our agent-based approach. The key innovations of our agent-based approach are: an ontological commitment to events and situations, fuzzy event correlation, fuzzy situation assessment, adaptability and learning during threat assessment operations, and an enhancement of traditional belief-desire-intention (BDI) agents with situation awareness. We describe the properties of situation-aware BDI agents and discuss the implementation of them on a variety of BDI agent platforms. Lastly, we discuss the interoperability of these platforms and address the issue of scalability through coupling to large-scale peer-to-peer overlays.

Abstract: Recently, several standards have emerged for ontology markup languages that can be used to formalize all kinds of knowledge. However, there are no widely accepted standards yet that define APIs to manage ontological data. Processing ontological information still suffers from the heterogeneity imposed by the plethora of available ontology management systems. Moreover, ubiquitous computing environments usually comprise software components written in a variety of different programming languages, which makes it particularly difficult to establish a common ontology management API with programming language agnostic semantics. We implemented an ontological Knowledge Base Server, which can expose the functionality of arbitrary off-the-shelf ontology management systems via a formally specified and well defined API. A case study was carried out in order to demonstrate the feasibility of our approach to use a formally specified ontology management API to implement a registry for ubiquitous computing systems.

Abstract: In this paper, we propose an agent-based geo-simulation framework EKEMAS to assist human planners when planning under strong spatial constraints in a real large-scale space. The approach consists in drawing a parallel between the real environment (for example, a forest in fire) and the simulated environment based on GIS data. This virtual environment uses software agents which are aware of the space and equipped with advanced spatial reasoning capabilities. In addition, we suggest some enhancements for the Continual Planning approach. Our aim is to demonstrate how EKEMAS, when coupled with a continual planning approach and agent’s spatial reasoning capabilities, can assist human planners overcoming obstacles related to real world constraints: dynamic, uncertain, and spatially constrained environment. We illustrate this idea on the forest firefighting problem and we use MAGS as a simulation platform and Prometheus as a fire simulator. Finally, and since plans in the studied case (wildfire fighting) are mainly paths, we also propose a new approach based on agent geo-simulation in order to solve particular Pathfinding problems.

Abstract: In order to meet the need for higher equipment availability and lower maintenance cost, much attention is being paid to the development of prognostic systems. Such systems support a proactive maintenance strategy by continuously monitoring the components of interest and predicting their failures sufficiently in advance to avoid disruptions during operation. Recent research demonstrated the potential of a comprehensive data mining methodology for building prognostic models from readily available operational and maintenance data. This approach builds a binary classifier that can determine the likelihood of a failure within a broad target window but cannot provide precise time to failure (TTF) estimations. This paper introduces a two-stage classification approach that helps improve the precision of TTF estimations. The new approach uses the initial methodology to learn a variety of base classifiers and then relies on meta-learning to integrate them. The paper details the model building process and demonstrates the usefulness of the proposed approach through a real-world prognostic application.

Abstract: The first stage in the design of a user interface is the quest for its `typical user', an abstract generalization of each user of the application. However, in web systems and other scenarios where the application can be used by dozens of different kinds of users, the identification of this `typical user' is quite difficult, if not impossible. Our proposal is to avoid the construction of interactive dialogs during the design stage, building them dynamically once the specific cognitive, perceptual and motor requirements of the current user are known: that is, during the execution stage. This is the approach used by GADEA, an intelligent user interface management system (UIMS) able to separate the functionality of an application from its interface in real time. The system adapts the components of the interface depending on the information stored in a user model which is continuously updated by a small army of data-gathering agents.

Abstract: This paper investigates the effectiveness of using the Contract Net Protocol, an auction type system, for controlling task allocation among a group of robots, and presents and evaluates a strategy of using Artificial Neural Networks to formulate adaptive bids within the framework of the Contract Net Protocol. The robots were used in a foraging environment and showed that excellent communication among robots leads to a need for a social control mechanism for managing the robots, such as the Contract Net Protocol. The experiments also confirmed that a moderate benefit can be gained by using adaptive bidding within the framework of the Contract Net Protocol.

Abstract: This paper presents the original and versatile architecture of a modular neural network and its application to super-resolution. Each module is a small multilayer perceptron, trained with the Levenberg-Marquardt method, and is used as a generic building block. By connecting the modules together to establish a composition of their individual mappings, we elaborate a lattice of modules that implements full connectivity between the pixels of the low-resolution input image and those of the higher-resolution output image. After the network is trained with patterns made up of low and high-resolution images of objects or scenes of the same kind, it will be able to enhance dramatically the resolution of a similar object's representation. The modular nature of the architecture allows the training phase to be readily parallelized on a network of PCs. Finally, it is shown that the network performs global-scale reconstruction of human faces from very low resolution input images.

Abstract: Being trapped in local optima within clustering search space currently is nontrivial difficulty. In order to relieve such a difficulty, even using genetic algorithm to optimize the initial clusters for fuzzy c-means is still unsatisfied. Since genetic algorithm intensifies only the current best solution, it will easily gets trapped in local minima. The ant colony system, dissimilarly to genetic algorithm, recognizes that the solutions near the best solution are also good ones and they bring about smoothness of solution. This paper proposes a modified fuzzy ant clustering. Such a presented method is a combination of genetic algorithm, ant colony system and fuzzy c-means. It is employed in creating fuzzy color histogram in image retrieval application. The performance measurement relates to the percentages of accuracy of image retrieval. Experimental results show that the proposed approach yields the best results among others with respect to sensitivity and robustness on dealing with lighting intensity changes, quantization errors, also changes in number of images and in size of color space, even the certain-range variation of a particular parameter of clustering.

Abstract: The problem of merging multiple-source uncertain information is a crucial issue in many applications. This paper proposes an analysis of possibilistic merging operators where uncertain information is encoded by means of product-based (or quantitative) possibilistic networks. We first show that the product-based merging of possibilistic networks having the same DAG structures can be easily achieved in a polynomial time. We then propose solutions to merge possibilistic networks having different structures and where the union of their graphs is free of cycles. Then we show how to deal with merged networks having cycles. Lastly, we handle the sub-normalization problem which reflects the presence of conflicts between different sources.

Abstract: This paper is devoted to an industrial case study focused on the issue of how to enhance an existing knowledge management tool (ITM) with reasoning capabilities, by introducing a semantic query mechanism as well as validation and inference services. ITM knowledge representation language is based on topic maps. We show that these topic maps (and especially those describing the domain ontology and annotation base) can be naturally mapped to the $\mathcal {SG}$ family, a sublanguage of conceptual graphs. This mapping equips ITM with a reasoning service. We finally present a media monitoring system benefiting from this transformation and combining ITM with the conceptual graph engine CoGITaNT.

Abstract: Numerous paper-based newspapers have been transformed into a digital format and published on the Internet. Digital newspapers are gradually becoming a popular electronic media for conveying information immediately. Google developed a powerful news service, Google news alert, based on the Google news aggregator for tracking user-interested new events utilizing a keywords matching approach. However, this service only monitors and tracks news events using the keyword-matching scheme; consequently, the Google news alert retrieves many irrelevant news events and sends them to users. In other words, the current service cannot monitor news events via a specific news topic; although recall rate is high, the precision rate is low when tracking user-interested news events. Thus, this study presents a novel personalized e-news monitoring agent system that employs the topic-tracking-based approach, improving the flaw of the keyword-based approach, for tracking user-interested news events on Google News site. The proposed scheme simultaneously considers both similarities and the semantic relationships among news topics to track news events. Additionally, to further support the promotion of the accuracy rate in tracking user-interested Chinese news events, the Chinese word segmentation system ECScanner (An Extension Chinese Lexicon Scanner) with new word extension is proposed for the Chinese word segmentation process. Experimental results demonstrated that the proposed scheme, based on topic-based approach, is superior to the keyword-based approach used by Google news alert in terms of precision rate, and retains a high recall rate when tracking user-interested news events. Compared with the conventional Chinese word segmentation system CKIP (Chinese Knowledge Information Processing), experimental results also confirmed that using the proposed ECScanner with novel extension mechanism for new words improves the accuracy rate in tracking user-interested news events.

Abstract: The work presented here is about employing a theory of updates to study geometrically observable changes that occur in spatial information about image sequences of a dynamic scene. The logical framework consists of a formalism for specifying the geometrical content of a scene, as well as the changes that occur in this geometry, and an algorithm for constructing a description for such changes from logical deductions. In this approach, a database state represents the available sensor data at a particular time instant. Transitions in sensor data are modeled by changes in the database and interpreted based on axioms encoding commonsense spatial reasoning. The main contribution of this work is that it provides the theoretical foundations for symbolically interpreting long sequences of sensor data transitions. For testing the framework and its implementation, the problem of interpreting rotational movements of objects in a sequence of images was used. Our experiments show that the system correctly interprets rotational movements for objects of different colors and provides satisfactory results for interpreting such movements from perceptually indistinguishable objects.

Abstract: Peptide-MHC binding is an important prerequisite event and has immediate consequences to immune response. Those peptides binding to MHC molecules can activate the T-cell immunity, and they are useful for understanding the immune mechanism and developing vaccines for diseases. Accurate prediction of the binding between peptides and MHC-II molecules has long been a challenge in bioinformatics. Recently, instead of differentiating peptides as binder or non-binder, researchers are more interested in making predictions directly on peptide binding affinities. In this paper, we investigate the use of relevance vector machine to quantitatively predict the binding affinities between MHC-II molecules and peptides. In our scheme, a new encoding scheme is used to generate the input vectors, and then by using relevance vector machine we develop the prediction models on the basis of binding cores, which are recognized in an iterative self-consistent way. When applied to three MHC-II molecules DRB1*0101, DRB1*0401 and DRB1*1501, our method produces consistently better performance than several popular quantitative methods, in terms of cross-validated squared error, cross-validated correlation coefficient, and area under ROC curve. All evidences indicate that our method is an effective tool for MHC-II binding affinity prediction.

Abstract: We propose a framework for constructing kernels that take advantage of local correlations in sequential data. The kernels designed using the proposed framework measure parse similarities locally, within a small window constructed around each matching feature. Furthermore, we propose to incorporate positional information inside the window and consider different ways to do this. We applied the kernels together with regularized least-squares (RLS) algorithm to the task of dependency parse ranking using the dataset containing parses obtained from a manually annotated biomedical corpus of 1100 sentences. Our experiments show that RLS with kernels incorporating positional information perform better than RLS with the baseline kernel functions. This performance gain is statistically significant.

Abstract: Volatility clustering degrades the efficiency and effectiveness of time series prediction and gives rise to large residual errors. This is because volatility clustering suggests a time series where successive disturbances, even if uncorrelated, are yet serially dependent. Traditional time-series forecast model such as grey model (GM) or auto-regressive moving-average (ARMA) has often encountered the overshoot effect, thus leading to the deterioration of its predictive accuracy. To overcome the overshoot and volatility clustering problems at the same time, an adaptive neuro-fuzzy inference system (ANFIS) is combined with a nonlinear generalized autoregressive conditional heteroscedasticity (NGARCH) model that is adapted by quantum minimization (QM) so as to tackle the problem of overshooting situation and time-varying conditional variance residual errors. The proposed method significantly reduces large residual errors in forecasts because the overshoot and volatility clustering effects are regulated to trivial levels. Two experiments using real financial and geographic data series, respectively, compare the proposed method and a number of well-known alternative methods. Results show that forecasting performance by the proposed method produces superior results, with good speed of computation. Goodness of fit of the proposed method is tested by Ljung-Box Q-test. It is concluded that the ANFIS/NGARCH composite model adapted by QM performs very well for improved predictive accuracy of irregular non-periodic short-term time series forecast and will be of interest to the science of statistical prediction of time series.

Abstract: A new hierarchical Walsh memory which can store and quickly recognize any number of patterns is proposed. A Walsh function based associative memory was found to be capable of storing and recognizing patterns in parallel via purely a software algorithmic technique (namely, without resorting to parallel hardware) while the memory itself only takes a single pattern space of computer memory, due to the Walsh encoding of each pattern. This type of distributed associative memory lends itself to high speed pattern recognition and has been reported earlier in a single memory version. In this paper, the single memory concept has first been extended to a parallel memory module and then to a tree-shaped hierarchy of these parallel modules that are capable of storing and recognizing any number of patterns for practical large scale data applications exemplified by image and speech recognition. The memory hierarchy was built by successively applying k-means clustering to the training data set. In the proposed architecture, the clustered data subsets are stored respectively into a parallel memory module where the module allocation is optimized using the genetic algorithm to realize a minimal implementation of the memory structure. The system can recognize all the training patterns with 100% accuracy and further, can also generalize on similar data. In order to demonstrate its efficacy with large scale real world data, we stored and recognized over 500 faces while at same time, achieving much reduced recognition time and storage space than template matching.

Abstract: This article introduces the adaptive controller for a class of nonlinear discrete-time systems based on the sliding shuttering condition and the self adjustable network called Multi-Input Fuzzy Rules Emulated Network (MIFREN). By using only the online learning phase, MIFREN's functional is the nonlinear discrete-tine function approximation and the disturbance estimation together. The proposed theorem is introduced for the designing procedure of all controller's parameters and MIFREN's adaptation gain. Simulation results demonstrate the justification of the theorem for the tracking performance and the unknown disturbance rejection.