Traumatic brain injury (TBI) is the leading cause of death and disability in children and young adults worldwide. Cognitive rehabilitation (CR) plans consist of a sequence of CR tasks targeting main cognitive functions. There is not enough on-field experience yet regarding which specific intervention (tasks or exercise assignment) is more appropriate to help therapists to design plans with significant effectiveness on patient improvement. The selection of specific tasks to be prescribed to the patient and the order in which they might be executed is currently decided by the therapists based on their experience. In this paper a new data mining methodology is proposed, combining several tools from Artificial Intelligence, clustering and post-processing analysis to identify regularities in the sequences of tasks in such a way that treatment profiles (classes) can be discovered. Due to the cumulative effect of rehabilitation tasks, small variations within the sequence of tasks performed by the patient do not significantly change the final outcomes in rehabilitation and makes it difficult to find discriminant rules by using the traditional machine learning inductive methods. However, by relaxing the formalization of the problem to find patterns that might include small variations, and introducing motif discovery techniques in the proposed methodology, the complexity of the neurorehabilitation phenomenon can be better captured and a global structure of successful treatment task sequences can be devised. Following this, the relationship between the discovered patterns and the CR treatment response are analyzed, offering a richer perspective than that provided by the single task focus traditionally used in the CR field. The paper provides a definition of the whole methodological approach proposed from a formal point of view, and its application to a real dataset. Comparisons with traditional AI approaches are also presented and the contribution of the proposed methodology to the AI field discussed.
This paper presents a control scheme which uses a combination of linear Model Predictive Control (MPC) and a Constraint Satisfaction Problem (CSP) to solve the non-linear operational optimal control of Drinking Water Networks (DWNs). The methodology has been divided into two functional layers: first, a CSP algorithm is used to transfer non-linear DWNs pressure equations into linear constraints on flows and tank volumes, which can enclose the feasible solution set of the hydraulic non-linear problem during the optimization process. Then, a linear MPC with tightened constraints produced in the CSP layer is solved to generate control strategies which optimize the control objectives. The proposed approach is simulated using Epanet to represent the real DWNs. Non-linear MPC is used for validation. To illustrate the performance of the proposed approach, a case study based on the Richmond water network is used and a realistic example, D-Town benchmark network, is added as a supplementary case study.
This paper presents a new approach to plan high-level manipulation actions for cleaning surfaces in household environments, like removing dirt from a table using a rag. Dragging actions can change the distribution of dirt in an unpredictable manner, and thus the planning becomes challenging. We propose to define the problem using explicitly uncertain actions, and then plan the most effective sequence of actions in terms of time. However, some issues have to be tackled to plan efficiently with stochastic actions. States become hard to predict after executing a few actions, so replanning every few actions with newer perceptions gives the best results, and the trade-off between planning time and plan quality is also important. Finally a learner is integrated to provide adaptation to changes, such as different rag grasps, robots, or cleaning surfaces.
We demonstrate experimentally, using two different robot platforms, that planning is more advantageous than simple reactive strategies for accomplishing complex tasks, while still providing a similar performance for easy tasks. We also performed experiments where the rag grasp was changed, and thus the behaviour of the dragging actions, showing that the learning capabilities allow the robot to double its performance with a new rag grasp after a few cleaning iterations.
In this work, a fault diagnosis methodology termed VisualBlock-Fuzzy Inductive Reasoning, i.e. VisualBlock-FIR, based on fuzzy and pattern recognition approaches is presented and applied to PEM fuel cell power systems. The innovation of this methodology is based on the hybridization of an artificial intelligence methodology that combines fuzzy approaches with well known pattern recognition techniques. To illustrate the potentiality of VisualBlock-FIR, a non-linear fuel cell simulator that has been proposed in the literature is employed. This simulator includes a set of five fault scenarios with some of the most frequent faults in fuel cell systems. The fault detection and identification results obtained for these scenarios are presented in this paper. It is remarkable that the proposed methodology compares favorably to the model-based methodology based on computing residuals while detecting and identifying all the proposed faults much more rapidly. Moreover, the robustness of the hybrid fault diagnosis methodology is also studied, showing good behavior even with a level of noise of 20 dB.
In this paper, an integrated data validation/reconstruction and fault diagnosis approach is proposed for critical infrastructure systems. The proposed methodology is implemented in a two-stage approach. In the first stage, sensor communication faults are detected and corrected, in order to facilitate a reliable dataset to perform system fault diagnosis in the second stage. On the one hand, sensor validation and reconstruction are based on the combined use of spatial and time series models. Spatial models take advantage of the (mass-balance) relation between different variables in the system, whilst time series models take advantage of the temporal redundancy of the measured variables by means of Holt-Winters time series models. On the other hand, fault diagnosis is based on the learning-in-model-space approach that is implemented by fitting a series of models using a series of signal segments selected with a sliding window. In this way, each signal segment can be represented by one model. To rigorously measure the ‘distance’ between models, the distance in the model space is defined. The deterministic reservoir computing approach is used to approximate a model with the input–output dynamics that exploits spatial–temporal correlations existing in the original data. Finally, the proposed approach is successfully applied to the Barcelona water network.
Ramisa, A.; Alenyà, G.; Moreno-Noguer, F.; Torras, C. Engineering applications of artificial intelligence Vol. 35, p. 246-258 DOI: 10.1016/j.engappai.2014.06.025 Data de publicació: 2014 Article en revista
Robotic handling of textile objects in household environments is an emerging application that has recently received considerable attention thanks to the development of domestic robots. Most current approaches follow a multiple re-grasp strategy for this purpose, in which clothes are sequentially grasped from different points until one of them yields a desired configuration.
In this work we propose a vision-based method, built on the Bag of Visual Words approach, that combines appearance and 3D information to detect parts suitable for grasping in clothes, even when they are highly wrinkled.
We also contribute a new, annotated, garment part dataset that can be used for benchmarking classification, part detection, and segmentation algorithms. The dataset is used to evaluate our approach and several state-of-the-art 3D descriptors for the task of garment part detection. Results indicate that appearance is a reliable source of information, but that augmenting it with 3D information can help the method perform better with new clothing items.
We propose a cognitive system that combines artificial intelligence techniques for planning and learning to execute tasks involving delayed and variable correlations between the actions executed and their expected effects. The system is applied to the task of controlling the growth of plants, where the evolution of the plant attributes strongly depends on different events taking place in the temporally distant past history of the plant. The main problem to tackle is how to efficiently detect these past events. This is very challenging since the inclusion of time could make the dimensionality of the search space extremely large and the collected training instances may only provide very limited information about the relevant combinations of events. To address this problem we propose a learning method that progressively identifies those events that are more likely to produce a sequence of changes under a plant treatment. Since the number of experiences is very limited compared to the size of the event space, we use a probabilistic estimate that takes into account the lack of experience to prevent biased estimations. Planning operators are generated from most accurately predicted sequences of changes. Planning and learning are integrated in a decision-making framework that operates without task interruptions by allowing a human gardener to instruct the treatments when the knowledge acquired so far is not enough to make a decision.
Grosso, J.M.; Ocampo-Martinez, C.A.; Puig, V. Engineering applications of artificial intelligence Vol. 26, num. 7, p. 1741-1750 DOI: 10.1016/j.engappai.2013.03.003 Data de publicació: 2013 Article en revista
This paper presents a constrained Model Predictive Control (MPC) strategy enriched with soft-control techniques as neural networks and fuzzy logic, to incorporate self-tuning capabilities and reliability aspects for the management of drinking water networks (DWNs). The control system architecture consists in a multilayer controller with three hierarchical layers: learning and planning layer, supervision and adaptation layer, and feedback control layer. Results
of applying the proposed approach to the Barcelona DWN show that the quasi-explicit nature of the proposed adaptive predictive controller leads to improve the computational time, especially when the complexityof the problem structure can vary while tuning the receding horizons.
This paper presents a constrained Model Predictive Control (MPC) strategy enriched with soft-control techniques as neural networks and fuzzy logic, to incorporate self-tuning capabilities and reliability aspects for the management of drinking water networks (DWNs). The control system architecture consists in a multilayer controller with three hierarchical layers: learning and planning layer, supervision and adaptation layer, and feedback control layer. Results of applying the proposed approach to the Barcelona DWN show that the quasi-explicit nature of the proposed adaptive predictive controller leads to improve the computational time, especially when the complexity of the problem structure can vary while tuning the receding horizons.
Bautista, J.; Cano, A.; Companys, R.; Ribas, I. Engineering applications of artificial intelligence Vol. 25, num. 6, p. 1235-1245 DOI: 10.1016/j.engappai.2011.09.001 Data de publicació: 2012-09-25 Article en revista
We present some results attained with two variants of Bounded Dynamic Programming algorithm to solve the Fm|block|Cmax problem using as an experimental data the well-known Taillard instances. We have improved the best known solutions for 17 of Taillard's instances, including the 10 instances from set 12.
Aulinas, M.; Tolchinsky, F.; Turon, C.; Poch, M.; Cortes, U. Engineering applications of artificial intelligence Vol. 25, num. 2, p. 317-325 DOI: 10.1016/j.engappai.2011.09.016 Data de publicació: 2012-03 Article en revista
The daily operation of wastewater treatment plants (WWTPs) in unitary sewer systems of industrialized areas is of special concern. Severe problems can occur due to the characteristics of incoming flow. In order to avoid decision that leads to hazardous situations, guidelines and regulations exist. However, there are still no golden standards by which to a priori decide whether a WWTP can cope with critical discharges. Strict adherence to regulations may not always be convenient, since special circumstances may motivate operators to accept discharges that are above established thresholds or to reject discharges that comply with guidelines. Nonetheless, such decisions must be well justified. This paper proposes an argumentation-based model by which to formulate a flexible decision-making process. An example of the model application describes how experts deliberate the safety of a discharge and adapt each decision to the particular characteristics of the industrial discharge and the WWTP.
Tornil-Sin, S.; Ocampo-Martinez, C.A.; Puig, V.; Escobet, T. Engineering applications of artificial intelligence Vol. 25, num. 1, p. 1-10 DOI: 10.1016/j.engappai.2011.07.007 Data de publicació: 2012-02 Article en revista
This paper presents three proposals of multiobjective memetic algorithms to solve a more realistic extension of a classical industrial problem: time and space assembly line balancing. These three proposals are, respectively, based on evolutionary computation, ant colony optimisation, and greedy randomised search procedure. Different variants of these memetic algorithms have been developed and compared in order to determine the most suitable intensification–diversification trade-off for the memetic search process. Once a preliminary study on nine well-known problem instances is accomplished with a very good performance, the proposed memetic algorithms are applied considering real-world data from a Nissan plant in Barcelona (Spain). Outstanding approximations to the pseudo-optimal non-dominated solution set were achieved for this industrial case study.
Sarrate, R.; Aguilar, J.; Nejjari, F. Engineering applications of artificial intelligence Vol. 20, num. 8, p. 1152-1162 DOI: 10.1016/j.engappai.2007.02.008 Data de publicació: 2007-12 Article en revista
Puig, V.; Witczak, M.; Nejjari, F.; Quevedo, J.; Korbicz, J. Engineering applications of artificial intelligence Vol. 20, num. 7, p. 886-897 DOI: 10.1016/j.engappai.2006.12.005 Data de publicació: 2007-02 Article en revista
This paper proposes a new passive robust fault detection scheme using non-linear models that include parameter uncertainty. The non-linear model considered here is described by a group method of data handling (GMDH) neural network. The problem of passive robust fault detection using models including parameter uncertainty has been mainly addressed by checking if the measured behaviour is inside the region of possible behaviours based on the so-called forward test since it bounds the direct image of an interval function. The main contribution of this paper is to propose a new backward test, based on the inverse image of an interval function, that allows checking if there exists a parameter in the uncertain parameter set that is consistent with the measured system behaviour. This test is implemented using interval constraint satisfaction algorithms which can perform efficiently in deciding if the measured system state is consistent with the GMDH model and its associated uncertainty. Finally, this approach is tested on the servoactuator being a FDI benchmark in the European Project DAMADICS.
Serra, P.; Sànchez-Marrè, M.; Lafuente Sancho, Francisco Javier; Cortes, U.; Poch, M. Engineering applications of artificial intelligence Vol. 7, num. 1, p. 23-30 DOI: 10.1016/0952-1976(94)90039-6 Data de publicació: 1994-02 Article en revista
A malfunction of a wastewater treatment plant is a major social and biological problem. Poorly treated waste water outside the plant could provoke dangerous consequences for human beings as well as the environment itself. The conventional control systems, that are usually applied in this field, have to cope with some difficulties: complexity of the system, an ill-structured domain, qualitative information, uncertainty or approximate knowledge, real-time dynamic system, . . . This paper shows an application of artificial intelligence in order to help the operators of wastewater treatment plants in their task of process control. The main goal is to build a knowledge-based tool useful for the diagnosis and management of wastewater treatment plants. First, a survey of wastewater treatment plants describes the complexity of the system being modelled and outlines its difficulties. The development of the application, and the methodology employed in it, are discussed. A new methodology called LINNEO+ is introduced. It is used for the automatic knowledge acquisition process in order to build up a Knowledge Base. The prototype architecture constructed -DEPUR- is detailed, together with some obtained results