Conformance checking is a crucial aspect of process mining, enabling organizations to identify deviations between actual process behavior and modeled expectations. At the heart of conformance checking lies the concept of optimal alignments, which provide a detailed, cost-minimized mapping of observed behavior to expected behavior. Optimal alignments facilitate the identification of root causes of non-conformity and guide corrective actions. This is a critical area where Artificial Intelligence (AI) plays a pivotal role in driving effective process improvement. However, computing optimal alignments poses significant computational challenges due to the vast search space inherent in declarative process models. Consequently, existing approaches often struggle with scalability and efficiency, limiting their applicability in real-world settings. This paper introduces DeclareAligner , a novel algorithm that uses the A* search algorithm, an established AI pathfinding technique, to tackle the problem from a fresh perspective leveraging the flexibility of declarative models. Key features of DeclareAligner include only performing actions that actively contribute to fixing constraint violations, utilizing a tailored heuristic to navigate towards optimal solutions, and employing early pruning to eliminate unproductive branches, while also streamlining the process through preprocessing and consolidating multiple fixes into unified actions. The proposed method is evaluated using 8054 synthetic and real-life alignment problems, demonstrating its ability to efficiently compute optimal alignments by significantly outperforming the current state of the art. By enabling process analysts to more effectively identify and understand conformance issues, DeclareAligner has the potential to drive meaningful process improvement and management.

This paper describes a new Fine-Tuning approach for Few-Shot object detection in Videos that exploits spatio-temporal information to boost detection precision. Despite the progress made in the single image domain in recent years, the few-shot video object detection problem remains almost unexplored. A few-shot detector must quickly adapt to a new domain with a limited number of annotations per category. Therefore, it is not possible to include videos in the training set, hindering the spatio-temporal learning process. We propose augmenting each training image with synthetic frames to train the spatio-temporal module of our method. This module employs attention mechanisms to mine relationships between proposals across frames, effectively leveraging spatio-temporal information. A spatio-temporal double head then localizes objects in the current frame while classifying them using both context from nearby frames and information from the current frame. Finally, the predicted scores are fed into a long-term object-linking method that generates object tubes across the video. By optimizing the classification score based on these tubes, our approach ensures spatio-temporal consistency. Classification is the primary challenge in few-shot object detection. Our results show that spatio-temporal information helps to mitigate this issue, paving the way for future research in this direction. FTFSVid achieves 41.9 AP50 on the Few-Shot Video Object Detection (FSVOD-500) and 42.9 AP50 on the Few-Shot YouTube Video (FSYTV-40) dataset, surpassing our spatial baseline by 4.3 and 2.5 points. Additionally, FTFSVid outperforms previous few-shot video object detectors by 3.2 points on FSVOD-500 and 14.5 points on FSYTV-40, setting a new state-of-the-art.

Few-shot object detection involves adapting an existing detector to a set of unseen categories with few annotated examples. This data limitation makes these methods to underperform those trained on large labeled datasets. In many scenarios, there is a high amount of unlabeled data that is never exploited. Thus, we propose to e xPAND the initial novel set by mining pseudo-labels. From a raw set of detections, xPAND obtains reliable pseudo-labels suitable for training any detector. To this end, we propose two new modules: Class and Box confirmation. Class Confirmation aims to remove misclassified pseudo-labels by comparing candidates with expected class prototypes. Box Confirmation estimates IoU to discard inadequately framed objects. Experimental results demonstrate that xPAND enhances the performance of multiple detectors up to +5.9 nAP and +16.4 nAP50 points for MS-COCO and PASCAL VOC, respectively, establishing a new state of the art. Code: https://github.com/PAGF188/xPAND . • We propose xPAND, a mining pipeline that generates high-quality diverse pseudo-labels. • xPAND refines a raw set of pseudo-labels using class and box confirmation modules. • Class module removes misclassified objects by comparing them with expected prototypes. • Box Confirmation estimates IoU to discard inadequately framed objects. • Results show that xPAND sets a new state of the art for both MS-COCO and VOC datasets.

Conformance checking techniques compare how a process is supposed to be executed according to a model with how it is executed in reality according to an event log. Alignment-based approaches are the most successful solutions for conformance checking. Optimal alignments are a way of finding the best match between the real and the modeled behavior and identifying the differences. However, finding these optimal alignments is a challenging task, especially for complex cases where the log and the model have many events and paths. The difficulty lies in the computational complexity required to find these alignments. To address this problem, we propose an efficient algorithm named REACH based on the A* search algorithm. The core components of the proposal are the use of a partial reachability graph for faster execution of process models for alignment computation and a set of optimization techniques for reducing the number of states explored by the A* algorithm. These improve performance by both reducing the required computation time per state and the number of states to process respectively. To evaluate the performance and scalability, we conducted tests using 227 pairs of logs and models, comparing the results obtained with those from 10 state-of-the-art approaches. Results show that REACH outperforms the other proposals in runtimes, and even aligns logs and models that no other algorithm is able to align.

Abstract This paper addresses the problem of exploiting spatiotemporal information to improve small object detection precision in video. We propose a two-stage object detector called FANet based on short-term spatiotemporal feature aggregation and long-term object linking to refine object detections. First, we generate a set of short tubelet proposals. Then, we aggregate RoI pooled deep features throughout the tubelet using a new temporal pooling operator that summarizes the information with a fixed output size independent of the tubelet length. In addition, we define a double head implementation that we feed with spatiotemporal information for spatiotemporal classification and with spatial information for object localization and spatial classification. Finally, a long-term linking method builds long tubes with the previously calculated short tubelets to overcome detection errors. The association strategy addresses the generally low overlap between instances of small objects in consecutive frames by reducing the influence of the overlap in the final linking score. We evaluated our model in three different datasets with small objects, outperforming previous state-of-the-art spatiotemporal object detectors and our spatial baseline.

Object detection accuracy on small objects, i.e., objects under 32 × 32 pixels, lags behind that of large ones. To address this issue, innovative architectures have been designed and new datasets have been released. Still, the number of small objects in many datasets does not suffice for training. The advent of the generative adversarial networks (GANs) opens up a new data augmentation possibility for training architectures without the costly task of annotating huge datasets for small objects. In this paper, we propose a full pipeline for data augmentation for small object detection which combines a GAN-based object generator with techniques of object segmentation, image inpainting, and image blending to achieve high-quality synthetic data. The main component of our pipeline is DS-GAN, a novel GAN-based architecture that generates realistic small objects from larger ones. Experimental results show that our overall data augmentation method improves the performance of state-of-the-art models up to 11.9% [email protected] on UAVDT and by 4.7% [email protected] on iSAID, both for the small objects subset and for a scenario where the number of training instances is limited.

Maintaining the identity of multiple objects in real-time video is a challenging task, as it is not always feasible to run a detector on every frame. Thus, motion estimation systems are often employed, which either do not scale well with the number of targets or produce features with limited semantic information. To solve the aforementioned problems and allow the tracking of dozens of arbitrary objects in real-time, we propose SiamMOTION. SiamMOTION includes a novel proposal engine that produces quality features through an attention mechanism and a region-of-interest extractor fed by an inertia module and powered by a feature pyramid network. Finally, the extracted tensors enter a comparison head that efficiently matches pairs of exemplars and search areas, generating quality predictions via a pairwise depthwise region proposal network and a multi-object penalization module. SiamMOTION has been validated on five public benchmarks, achieving leading performance against current state-of-the-art trackers. Code available at: https://www.github.com/lorenzovaquero/SiamMOTION

Depth estimation and all-in-focus image restoration from defocused RGB images are related problems, although most of the existing methods address them separately. The few approaches that solve both problems use a pipeline processing to derive a depth or defocus map as an intermediary product that serves as a support for image deblurring, which remains the primary goal. In this paper, we propose a new Deep Neural Network (DNN) architecture that performs in parallel the tasks of depth estimation and image deblurring, by attaching them the same importance. Our Two-headed Depth Estimation and Deblurring Network (2HDED:NET) is an encoder-decoder network for Depth from Defocus (DFD) that is extended with a deblurring branch, sharing the same encoder. The network is tested on NYU-Depth V2 dataset and compared with several state-of-the-art methods for depth estimation and image deblurring.

Many computer vision applications require real-time processing speeds, which prevents them from running an object detector on all frames of the sequence. In such circumstances, it is necessary to resort to motion estimation techniques in order to maintain the identity of the targets. This can be carried out by instantiating multiple single object trackers, if there are few targets, or through methods that globally extract the frame features, in order to share computations. The problem with the latter is that they yield features with limited semantic information and detect changes in the scene by performing multi-scale tests, which is inefficient and prone to errors. To solve these problems and provide accurate tracking for multiple objects in real-time, we propose SiamFAST. SiamFAST includes: a feature-pyramid-based region-of-interest extractor that produces quality features for both object exemplars and search areas; a pairwise depthwise region proposal network to compute fast similarities for several dozens of objects; and a multi-object penalization module in order to suppress the effect of distractors. SiamFAST has been validated on three public benchmarks, achieving leading performance against current state-of-the-art trackers.

Automated process discovery is a process mining operation that takes as input an event log of a business process and generates a diagrammatic representation of the process. In this setting, a common diagrammatic representation generated by commercial tools is the directly-follows graph (DFG). In some real-life scenarios, the DFG of an event log contains hundreds of edges, hindering its understandability. To overcome this shortcoming, process mining tools generally offer the possibility of filtering the edges in the DFG. We study the problem of efficiently filtering the DFG extracted from an event log while retaining the most frequent relations. We formalize this problem as an optimization problem, specifically, the problem of finding a sound spanning subgraph of a DFG with a minimal number of edges and a maximal sum of edge frequencies. We show that this problem is an instance of an NP-hard problem and outline several polynomial-time heuristics to compute approximate solutions. Finally, we report on an evaluation of the efficiency and optimality of the proposed heuristics using 13 real-life event logs.

Abstract In this work, we present a complete system to produce an automatic linguistic reporting about the customer activity patterns inside open malls, a mixed distribution of classical malls joined with the shops on the street. These reports can assist to design marketing campaigns by means of identifying the best places to catch the attention of customers. Activity patterns are estimated with process mining techniques and the key information of localization. Localization is obtained with a parallelized solution based on WiFi fingerprint system to speed up the solution. In agreement with the best practices for human evaluation of natural language generation systems, the linguistic quality of the generated report was evaluated by 41 experts who filled in an online questionnaire. Results are encouraging, since the average global score of the linguistic quality dimension is 6.17 (0.76 of standard deviation) in a 7-point Likert scale. This expresses a high degree of satisfaction of the generated reports and validates the adequacy of automatic natural language textual reports as a complementary tool to process model visualization.

Most video analytics applications rely on object detectors to localize objects in frames. However, when real-time is a requirement, running the detector at all the frames is usually not possible. This is somewhat circumvented by instantiating visual object trackers between detector calls, but this does not scale with the number of objects. To tackle this problem, we present SiamMT, a new deep learning multiple visual object tracking solution that applies single-object tracking principles to multiple arbitrary objects in real-time. To achieve this, SiamMT reuses feature computations, implements a novel crop-and-resize operator, and defines a new and efficient pairwise similarity operator. SiamMT naturally scales up to several dozens of targets, reaching 25 fps with 122 simultaneous objects for VGA videos, or up to 100 simultaneous objects in HD720 video. SiamMT has been validated on five large real-time benchmarks, achieving leading performance against current state-of-the-art trackers.

Real-time visual object tracking provides every object of interest with a unique identity and a trajectory across video frames. This is a fundamental task of many video analytics applications, such as traffic monitoring or video surveillance in general. The development of real-time multiple object tracking systems on low-power edge devices as IoT nodes, without compromising accuracy, is a challenge due to the limited computing capacity of said devices. This might rule out the best in-class computer vision solutions, which, nowadays, are based on deep learning, and thus, they are very hardware demanding. This article meets this challenge with a multiple object detection and tracking system that employs cutting-edge deep learning architectures on an embedded GPU while operating in real time. For this purpose, a system has been designed that extends a joint architecture of tracking and detection by adding a module comprised of appearance-based and movement-based trackers that allow to maintain the identity of the objects of interest for longer periods of time while alleviating the burden of the detector. Our system is mapped onto an embedded GPU platform, cutting down power consumption significantly with respect to a server GPU. Tracking performance metrics show a 51.1% in multiple object tracking accuracy (MOTA) on the MOT16 data set. This, in conjunction with a real-time processing speed of 25.2 FPS for up to 45 simultaneous objects and low-power consumption of 15 W, make our system an ideal solution for a wide range of video analytics applications.

We present a new network architecture able to take advantage of spatio-temporal information available in videos to boost object detection precision. First, box features are associated and aggregated by linking proposals that come from the same anchor box in the nearby frames. Then, we design a new attention module that aggregates short-term enhanced box features to exploit long-term spatio-temporal information. This module takes advantage of geometrical features in the long-term for the first time in the video object detection domain. Finally, a spatio-temporal double head is fed with both spatial information from the reference frame and the aggregated information that takes into account the short- and long-term temporal context. We have tested our proposal in five video object detection datasets with very different characteristics, in order to prove its robustness in a wide number of scenarios. Non-parametric statistical tests show that our approach outperforms the state-of-the-art. Our code is available at https://github.com/daniel-cores/SLTnet.

Object detection through convolutional neural networks is reaching unprecedented levels of precision. However, a detailed analysis of the results shows that the accuracy in the detection of small objects is still far from being satisfactory. A recent trend that will likely improve the overall object detection success is to use the spatial information operating alongside temporal video information. This paper introduces STDnet-ST, an end-to-end spatio-temporal convolutional neural network for small object detection in video. We define small as those objects under 16×16 px, where the features become less distinctive. STDnet-ST is an architecture that detects small objects over time and correlates pairs of the top-ranked regions with the highest likelihood of containing those small objects. This permits to link the small objects across the time as tubelets. Furthermore, we propose a procedure to dismiss unprofitable object links in order to provide high quality tubelets, increasing the accuracy. STDnet-ST is evaluated on the publicly accessible USC-GRAD-STDdb, UAVDT and VisDrone2019-VID video datasets, where it achieves state-of-the-art results for small objects.

The detection of small objects is of particular interest in many real applications. In this paper, we propose STDnet-ST, a novel approach to small object detection in video using spatial information operating alongside temporal video information. STDnet-ST is an end-to-end spatio-temporal convolutional neural network that detects small objects over time and correlates pairs of the top-ranked regions with the highest likelihood of containing small objects. This architecture links the small objects across the time as tubelets, being able to dismiss unprofitable object links in order to provide high-quality tubelets. STDnet-ST achieves state-of-the-art results for small objects on the publicly available USC-GRAD-STDdb and UAVDT video datasets.

Visual object tracking is of great interest in many applications, as it preserves the identity of an object throughout a video. However, while real applications demand systems capable of real-time-tracking multiple objects, multi-object tracking solutions usually follow the tracking-by-detection paradigm, thus they depend on running a costly detector in each frame, and they do not allow the tracking of arbitrary objects, i.e., they require training for specific classes. In response to this need, this work presents the architecture of SiamMT, a system capable of efficiently applying individual visual tracking techniques to multiple objects in real-time. This makes it the first deep-learning-based arbitrary multi-object tracker. To achieve this, we propose global frame features extraction by using a fully-convolutional neural network, followed by the cropping and resizing of the different object search areas. The final similarity operation between these search areas and the target exemplars is carried out with an optimized pairwise cross-correlation. These novelties allow the system to track multiple targets in a scalable manner, achieving 25 fps with 60 simultaneous objects for VGA videos and 40 objects for HD720 videos, all with a tracking quality similar to SiamFC.

In this work we present a state lattice based approach for motion planning in mobile robotics. Sensing and motion uncertainty are managed at planning time to obtain safe and optimal paths. To do this reliably, our approach estimates the probability of collision taking into account the robot shape and the uncertainty in heading. We also introduce a novel graduated fidelity approach and a multi-resolution heuristic which adapt to the obstacles in the map, improving the planning efficiency while maintaining its performance. Results for different environments, shapes and motion models are reported, including experiments with real robots.

Self-regulated learning involves students taking the responsibility of their own learning. Self-regulated learning students usually adopt a variety of learning strategies and behaviors, such as the performance of forethought-performance-reflection cycles or the regular and sequenced work over time, that eventually enable them to achieve a more significant and long-lasting learning. In this paper, we explore if these particular behaviors and strategies can be analyzed through the application of process mining techniques taking as data the events registered during the performance of learning activities. The discovery of the underlying processes followed by students can open new approaches to study the real self-regulated strategies used by students. The paper reviews the techniques and tools available to perform the process mining of events related to self-regulated learning and describes some initial works in this area. Furthermore, as an initial empirical study, we analyze the process followed by students regarding the visualization of videos provided in a first-year engineering subject. The obtained results are studied taking into account the grades obtained by the students. The results show that the students that obtained the best grades follow more varied routes than the students that obtained the worst grades. In addition, the best ones are more regular over time regarding weekly video visualization, mainly at the beginning of the term, while the worst ones visualize the videos mainly at the second part of the term.

The reduction of energy consumption in buildings is one of the goals to improve energy efficiency. One way to achieve energy savings in buildings is to develop intelligent control heating strategies that are able to reduce the power consumption by predicting the behavior of the thermal dynamics under different control schemes. One way to accomplish this is by means of learning fuzzy rules using the data collected from different sensors installed in buildings to generate regression models that are accurate and interpretable, so the generated models can be understood by the experts who approve the energy-saving schemes. However, one important issue is the generation of accurate knowledge bases of fuzzy rules for regression that can scale with the large amount of information generated by the many sensors installed in buildings, which will continue to grow in the coming years. For this purpose, in this paper we evaluate the scalability of two genetic fuzzy systems, FRULER and S-FRULER in the domain of thermal dynamics in buildings, using real data from a residential college at the USC.

In this paper we present a hybrid approach for automatic composition of Web services that generates semantic input-output based compositions with optimal end-to-end QoS, minimizing the number of services of the resulting composition. The proposed approach has four main steps: (1) generation of the composition graph for a request; (2) computation of the optimal composition that minimizes a single objective QoS function; (3) multi-step optimizations to reduce the search space by identifying equivalent and dominated services; and (4) hybrid local-global search to extract the optimal QoS with the minimum number of services. An extensive validation with the datasets of the Web Service Challenge 2009-2010 and randomly generated datasets shows that: (1) the combination of local and global optimization is a general and powerful technique to extract optimal compositions in diverse scenarios; and (2) the hybrid strategy performs better than the state-of-the-art, obtaining solutions with less services and optimal QoS.

In genetic fuzzy systems (GFS) the size of the problem has a huge influence in the performance of the obtained models, since i) the fuzzy rule bases learned suffer from exponential rule explosion when the number of variables increases, and ii) the convergence time increments with the number of examples. In this paper we present S-FRULER, a scalable distributed version of FRULER which is a GFS that learns simple and linguistic TSK-1 knowledge bases for regression problems. S-FRULER obtains models with high accuracy and low complexity, whilst reducing the algorithm runtime. S-FRULER focuses on splitting the problem into smaller partitions and incorporates a feature selection process for reducing the number of variables used in each partition. Each partition is then solved independently using the FRULER algorithm. The Reduce function obtains linguistic TSK fuzzy rule bases from the information generated in each partition. S-FRULER has been validated in terms of scalability, precision and complexity using 10 large-scale datasets and has been compared with three state of the art GFSs. Experimental results show that S-FRULER scales well while achieving simple models with a linguistic approach and a precision comparable with approximative models.

In this paper we present a theoretical analysis of graph-based service composition in terms of its dependency with service discovery. Driven by this analysis we define a composition framework by means of integration with fine-grained I/O service discovery that enables the generation of a graph-based composition which contains the set of services that are semantically relevant for an input-output request. The proposed framework also includes an optimal composition search algorithm to extract the best composition from the graph minimising the length and the number of services, and different graph optimisations to improve the scalability of the system. A practical implementation used for the empirical analysis is also provided. This analysis proves the scalability and flexibility of our proposal and provides insights on how integrated composition systems can be designed in order to achieve good performance in real scenarios for the web.

One of the most suited techniques for comparing results obtained from computational intelligence algorithms is the statistical hypothesis testing. This method can be used to contrast if the difference between the algorithm with the best results and other algorithms is actually significant. In this paper, we present STAC (Statistical Tests for Algorithms Comparison), a new platform for statistical analysis to verify the results obtained from computational intelligence algorithms. STAC consists of three different layers for performing statistical tests: a Python library, a set of web services and a web client. We show several use cases, in which both non-expert and expert users interact with the web client and use the web services in different programming languages.

In many real problems the regression models have to be accurate but, also, interpretable in order to provide qualitative understanding of the system. In this realm, the use of fuzzy rule base systems, particularly TSK, is widely extended. TSK rules combine the interpretability and expressiveness of rules with the ability of fuzzy logic for representing uncertainty, and the precision of the polynomials in the consequents. In this paper we present a new genetic fuzzy system to automatically learn accurate and simple linguistic TSK fuzzy rule bases that accurately model regression problems. In order to reduce the complexity of the learned models while keeping a high accuracy, we propose a Genetic Fuzzy System which consists of three stages: instance selection, multi-granularity fuzzy discretization of the input variables, and the evolutionary learning of the rule base using Elastic Net regularization. This proposal was validated using 28 real-world datasets and compared with three state of the art genetic fuzzy systems. Results show that our approach obtains the simplest models while achieving a similar accuracy to the best approximative models.

In this paper we present the Soft Learn Activity Reporter (SLAR) service which automatically generates textual short-term reports about learners' behavior in virtual learning environments. Through this approach, we show how textual reporting is a coherent way of providing information that can complement (and even enhance) visual statistics and help teachers to understand in a comprehensible manner the behavior of their students during the course. This solution extracts relevant information from the students' activity and encodes it into intermediate descriptions using linguistic variables and temporal references, which are subsequently translated into texts in natural language. The examples of application on real data from an undergraduate course supported by the Soft Learn platform show that automatic textual reporting is a valuable complementary tool for explaining teachers and learners the information comprised in a Learning Analytics Dashboard.

This paper presents a hybrid approach for automatic composition of Web services that generates semantic input-output matching compositions minimizing the number of services and optimizing the global QoS. The proposed approach has four main steps: 1) generation of the composition graph for a request, 2) computation of the optimal QoS of the composition graph, 3) multi-step optimizations of the graph to identify equivalent and dominated services, and 4) hybrid local-global search to extract the optimal QoS with the minimum number of services. A validation with the datasets of the Web Service Challenge 2009-2010 is also provided.

Prediction of students' performance is one of the most explored issues in educational data mining. To predict if students will achieve the outcomes of the subject based on the previous results enables teachers to adapt the learning design of the subject to the teaching-learning process. However, this adaptation is even more relevant if we could predict the fulfillment of the educational objectives of a subject, since teachers should focus the adaptation on the learning resources and activities related to those educational objectives. In this paper, we present an experiment where a support vector machine is applied as a classifier that predicts if the different educational objectives of a subject are achieved or not. The inputs of the problem are the marks obtained by the students in the questionnaires related to the learning activities that students must undertake during the course. The results are very good, since the classifiers predict the achievement of the educational objectives with precision over 80%.

In self-regulated learning, evaluation is a complex task of the teaching process, but even more if students have social media that allow them to build their personal learning environment in different ways. In these kind of virtual environments a large amount of data that needs to be assessed by teachers is generated, and therefore they require tools that facilitate the assessment task. In this paper, we present an experiment with a process mining-based learning analytics tool, called SoftLearn, that helps teachers to assess the student's activity in self-regulated learning. The subject of this experiment is taught in blended learning mode with weekly classroom sessions, and the students use a social network software, called ELGG, as an e-portfolio in which they reflect their individual knowledge process construction. The results show that the use of this tool reduces significantly the assessment time and helps teachers to understand the learning process of the students.

One of the most challenging issues in learning analytics is the development of techniques and tools that facilitate the evaluation of the learning activities carried out by learners. In this paper, we faced this issue through a process mining-based platform, called Soft Learn, that is able to discover complete, precise and simple learning paths from event logs. This platform has a graphical interface that allows teachers to better understand the real learning paths undertaken by learners.

The tradeoff between bias and variance is a well-known problem in machine learning, since algorithms are expected to achieve a reduced training error without going into overfitting. In Genetic Fuzzy Systems (GFSs), overfitting is usually avoided through the control of the number of rules and/or the number of labels. However, in many machine learning approaches, variance is reduced through the use of a validation set. Inspired by this idea, we propose in this paper an Instance Selection (IS) algorithm for regression problems called Class Conditional Instance Selection for Regression (CCISR) which is based on CCIS [1]. The output of CCISR is used in a GFS to obtain Rule Bases with a low variance, as the rules are generated with an ad hoc data driven method guided by the selected instances, but the error is still measured with the full training dataset. The combined system has been tested over 12 publicly available datasets, and results were compared with other GFSs. Our approach is capable of achieving a reduction in the number of rules while maintaining a good accuracy.

Service Oriented Architectures and web service technology are becoming popular in recent years. As more web services can be used over the Internet, the need to find efficient algorithms for web services composition that can deal with large amounts of services becomes important. These algorithms must deal with different issues like performance, semantics or user restrictions. In this paper we present an A* algorithm which solves the problem of semantic input-output message structure matching for web service composition. Given are quest, a service dependency graph with a subset of the original services from an external repository is dynamically generated. Then, the A* search algorithm is used to find a minimal composition that satisfies the user request. Moreover, in order to improve the performance, a set of dynamic optimization techniques has been implemented over the search process. A full experimental validation with eight different public repositories has been done showing a good performance as in all tests as the algorithm finds a valid solution with minimal number of services and execution path.

Web services are interfaces that describe a collection of operations that are network-accessible through standardized Web protocols. When a required operation is not found, several services can be compounded to get a composite service that performs the desired task. To find this composite service, a search process over a huge search space must be performed. The algorithm that composes the services must select the adequate atomic processes and, also, must choose the correct way to combine them using the different available control structures. In this paper a genetic programming algorithm for Web services composition is presented. The algorithm has a context-free grammar to generate the valid structures of the composite services. Moreover, it includes a method to update the attributes of each node. A full experimental validation with a repository of 1,000 Web services has been done, showing a great performance as the algorithm finds a valid solution in all the tests.

Fuzzy quantification supplies powerful tools for handling linguistic expressions. Nevertheless, its advantages are usually shown at the theoretical level without a proper empirical validation. In this work, we review the application of fuzzy quantification in two application domains. We provide empirical evidence on the adequacy of fuzzy quantification to support different tasks in the context of mobile robotics and information retrieval. This practical perspective aims at exemplifying the actual benefits that real application can get from fuzzy quantifiers. © 2009 Wiley Periodicals, Inc.

A methodology for learning behaviors in mobile robotics has been developed. It consists of a technique to automatically generate input–output data plus a genetic fuzzy system that obtains cooperative weighted rules. The advantages of our methodology over other approaches are that the designer has to choose the values of only a few parameters, the obtained controllers are general (the quality of the controller does not depend on the environment), and the learning process takes place in simulation, but the controllers work also on the real robot with good performance. The methodology has been used to learn the wall-following behavior, and the obtained controller has been tested using a Nomad 200 robot in both simulated and real environments. © 2009 Wiley Periodicals, Inc.

Machine scheduling is a critical problem in industries where products are custom-designed. The wide range of products, the lack of previous experiences in manufacturing, and the several conflicting criteria used to evaluate the quality of the schedules define a huge search space. Furthermore, production complexity and human influence in each manufacturing step make time estimations difficult to obtain thus reducing accuracy of schedules. The solution described in this paper combines evolutionary computing and neural networks to reduce the impact of (i) the huge search space that the multi-objective optimization must deal with and (ii) the inherent problem of computing the processing times in a domain like custom manufacturing. Our hybrid approach obtains near optimal schedules through the Non-dominated Sorting Genetic Algorithm II (NSGA-II) combined with time estimations based on multilayer perceptron networks.

Detection of people and other moving objects is fundamental for the development of tasks by an autonomous mobile robot, and principally for human-robot interaction. In this paper we present an evolutionary algorithm to learn a pattern classifier system based on the quantified fuzzy temporal rules (QFTRs) model, for the detection of moving objects using laser range finders data. QFTRs are able to analyze the persistence of the fulfillment of a condition in a temporal reference by using fuzzy quantifiers. Experimental results with a Pioneer II robot in a typical hallway environment show an excellent classification rate in a real and complex situation with people moving in several groups in the surrounding.

This paper presents a methodology for the design of fuzzy controllers with good interpretability in mobile robotics. It is composed of a technique to automatically generate a training data set plus an efficient algorithm to learn fuzzy controllers. The proposed approach obtains a highly interpretable knowledge base in a very reduced time, and the designer only has to define the number of membership functions and the universe of discourse of each variable, together with a scoring function. In addition, the learned fuzzy controllers are general because the training set is composed of a number of automatically generated examples that cover the universe of discourse of each variable uniformly and with a predefined precision. The methodology has been applied to the design of a wall-following and moving object following behavior. Several tests in simulated environments using the Nomad 200 robot software and a comparison with another learning method show the performance and advantages of the proposed approach.

Mobile robots operating in populated environments typically can improve their service and navigation behavior when they know where people are in their vicinity and in which direction they are heading. In this paper we present an algorithm for tracking clusters of people using multiple hypothesis tracking (MHT). The motivation for our approach is that tracking clusters of objects instead of the individual objects enhances the reliability and robustness of the tracking especially when the objects move in groups. To efficiently keep track of multiple objects and clusters, our approach uses MHT in combination with Murty's algorithm. The set of hypothesis for each iteration is constructed in two consecutive steps: one for solving the data association problem, taking also into account the frequent occlusions between the objects, and the second one for considering the joining of different clusters. Our approach has been implemented and tested on a real robot and in a typical hallway environment. Experimental results demonstrate that our approach can robustly deal with several groups of people and is able to reliably manage the splits and joins of clusters

The work presents the design of a fuzzy controller for the wall-following behavior in mobile robotics using the COR (cooperative rules) methodology with ant colony optimization. The system has been tested in several simulated environments using the Nomad 200 robot software, and compared with other controller based on genetic algorithms. The proposed approach obtains a highly interpretable knowledge base in a reduced time, and the designer only has to define the number of membership functions and the universe of discourse of each variable.

The paper describes a fuzzy control system for the avoidance of moving objects by a robot. The objects move with no type of restriction, varying their velocity and making turns. Due to the complex nature of this movement, it is necessary to realize temporal reasoning with the aim of estimating the trend of the moving object. A new paradigm of fuzzy temporal reasoning, which we call fuzzy temporal rules (FTRs), is used for this control task. The control system has over 117 rules, which reflects the complexity of the problem to be tackled. The controller has been subjected to an exhaustive validation process and examples are shown of the results obtained.