Genetic based discrete particle swarm optimization for Elderly Day Care Center timetabling

The timetabling problem of local Elderly Day Care Centers (EDCCs) is formulated into a weighted maximum constraint satisfaction problem (Max-CSP) in this study. The EDCC timetabling problem is a multi-dimensional assignment problem, where users (elderly) are required to perform activities that require different venues and timeslots, depending on operational constraints. These constraints are categorized into two: hard constraints, which must be fulfilled strictly, and soft constraints, which may be violated but with a penalty. Numerous methods have been successfully applied to the weighted Max-CSP; these methods include exact algorithms based on branch and bound techniques, and approximation methods based on repair heuristics, such as the min-conflict heuristic. This study aims to explore the potential of evolutionary algorithms by proposing a genetic-based discrete particle swarm optimization (GDPSO) to solve the EDCC timetabling problem. The proposed method is compared with the min-conflict random-walk algorithm (MCRW), Tabu search (TS), standard particle swarm optimization (SPSO), and a guided genetic algorithm (GGA). Computational evidence shows that GDPSO significantly outperforms the other algorithms in terms of solution quality and efficiency.     

A smart classifier for extracting environmental data from digital image time-series: Applications for PhenoCam data in a tidal salt marsh

PhenoCams are part of a national network of automated digital cameras used to assess vegetation phenology transitions. Effectively analyzing PhenoCam time-series involves eliminating scenes with poor solar illumination or high cover of non-target objects such as water. We created a smart classifier to process images from the “GCESapelo” PhenoCam, which photographs a regularly-flooded salt marsh. The smart classifier, written in R, assigns pixels to target (vegetation) and non-target (water, shadows, fog and clouds) classes, allowing automated identification of optimal scenes for evaluating phenology. When compared to hand-classified validation images, the smart classifier identified scenes with optimal vegetation cover with 96% accuracy and other object classes with accuracies ranging from 86 to 100%. Accuracy for estimating object percent cover ranged from 74 to 100%. Pixel-classification with the smart classifier outperformed previous approaches (i.e. indices based on average color content within ROIs) and reduced variance in phenology index time-series. It can be readily adapted for other applications.     

A methodological approach to the design of optimising control strategies for sewer systems

This study focuses on designing an optimisation based control for sewer system in a methodological way and linking it to a regulatory control. Optimisation based design is found to depend on proper choice of a model, formulation of objective function and tuning of optimisation parameters. Accordingly, two novel optimisation configurations are developed, where the optimisation either acts on the actuators or acts on the regulatory control layer. These two optimisation designs are evaluated on a sub-catchment of the sewer system in Copenhagen, and found to perform better than the existing control; a rule based expert system. On the other hand, compared with a regulatory control technique designed earlier in Mollerup et al. (2015), the optimisation showed similar performance with respect to minimising overflow volume. Hence for operation of small sewer systems, regulatory control strategies can offer promising potential and should be considered along more advanced strategies when identifying novel solutions.     

Synthesizing safe control-command systems out of reusable components

This paper presents a safe design method for control-command embedded systems. It investigates the problem of building control-command systems out of Commercial off the shelf (COTS) components. The design method proposed uses in synergy the formal verification (FV) and the Discrete Controller Synthesis (DCS) techniques. COTS are formally specified using temporal logic and/or executable observers. New functions are built by assembling COTS together. As the COTS assembly operation is seldom error-free, behavioral incompatibilities may persist between COTS. For these reasons, COTS assemblies need to be formally verified and if errors are found, an automatic correction is attempted using DCS. The control-command code generated by DCS needs hardware specific post-processing: a structural decomposition, followed by a controllability assessment, followed by a dedicated formal verification step, ensuring that no spurious behavior is added by DCS. The resulting system is ready for hardware (e.g. FPGA) implementation.     

Anticipatory assistance-as-needed control algorithm for a multijoint upper limb robotic orthosis in physical neurorehabilitation

Robotic devices are becoming a popular alternative to the traditional physical therapy as a mean to enhance functional recovery after stroke; they offer more intensive practice opportunities without increasing time spent on supervision by the treating therapist. An ideal behavior for these systems would consist in emulating real therapists by providing anticipated force feedback to the patients in order to encourage and modulate neural plasticity. However, nowadays there are no systems able to work in an anticipatory fashion. For this reason, the authors propose an anticipatory assistance-as-needed control algorithm for a multijoint robotic orthosis to be used in physical ABI neurorehabilitation. This control algorithm, based on a dysfunctional-adapted biomechanical prediction subsystem, is able to avoid patient trajectory deviations by providing them with anticipatory force-feedback. The system has been validated by means of a robotic simulator.Obtained results demonstrate through simulations that the proposed assistance-as-needed control algorithm is able to provide anticipatory actuation to the patients, avoiding trajectory deviations and tending to minimize the degree of actuation. Thus, the main novelty and contribution of this work is the anticipatory nature of the proposed assistance-as-needed control algorithm, that breaks with the current robotic control strategies by not waiting for the trajectory deviations to take place. This new actuation paradigm avoids patient slacking and increases both participation and muscle activity in such a way that neural plasticity is encouraged and modulated to reinforce motor recovery.     

Advanced decision control system for effluent violations removal in wastewater treatment plants

This paper presents the application of control strategies for wastewater treatment plants with the goal of effluent limits violations removal as well as achieving a simultaneous improvement of effluent quality and reduction of operational costs. The evaluation is carried out with the Benchmark Simulation Model No. 2. The automatic selection of the suitable control strategy is based on risk detection of effluent violations by Artificial Neural Networks. Fuzzy Controllers are implemented to improve the denitrification or nitrification process based on the proposed objectives. Model Predictive Control is applied for the improvement of dissolved oxygen tracking.     

Differential geometry based active fault tolerant control for aircraft

This work shows how to use a differential geometry tool to design a novel nonlinear active fault tolerant flight control system for aircraft. The proposed control scheme consists of two main subsystems: a controller, which is designed for the nominal plant, and a fault detection and diagnosis module, which provides fault estimation. A further feedback loop exploits the fault estimation to accommodate faults affecting the system. The estimate convergence and the stability of the active fault tolerant flight controller are theoretically proved. Finally, high fidelity simulations show the effectiveness of the scheme.     

Impact of Internet gambling on problem gambling among adolescents in Italy: Findings from a large-scale nationally representative survey

AimsThe primary aim of the present study was to understand the impact of online gambling on gambling problems in a large-scale nationally representative sample of Italian youth, and to identify and then further examine a subgroup of online gamblers who reported higher rates of gambling problems.DesignData from the ESPAD^®Italia2013 (European School Survey Project on Alcohol and Other Drugs) Study were used for analyses of adolescent Internet gambling.SettingSelf-administered questionnaires were completed by a representative sample of high school students, aged 15–19 years.ParticipantsA total of 14,778 adolescent students.MeasurementsRespondents’ problem gambling severity; gambling behavior (participation in eight different gambling activities, the number of gambling occasions and the number of online gambling occasions, monthly gambling expenditure); Socio-demographics (e.g., family structure and financial status); and control variables were measured individually (i.e., use of the Internet for leisure activities and playing video games).FindingsRates of problem gambling were five times higher among online gamblers than non-online gamblers. In addition, factors that increased the risk of becoming a problem online gambler included living with non-birth parents, having a higher perception of financial family status, being more involved with gambling, and the medium preferences of remote gamblers (e.g., Internet cafes, digital television, and video game console).ConclusionsThe online gambling environment may pose significantly greater risk to vulnerable players. Family characteristics and contextual elements concerning youth Internet gambling (e.g., remote mediums) may play a key role in explaining problem online gambling among adolescents.     

Vehicle tractive force prediction with robust and windup-stable Kalman filters

Vehicle control systems need to prognosticate future vehicle states in order to improve energy efficiency. This paper compares four approaches that are used to identify the parameters of a longitudinal vehicle dynamics model used for the prediction of vehicle tractive forces. All of the identification approaches build on a standard Kalman filter. Measurement signals are processed using the polynomial function approximation technique to remove noise and compute smooth derivative values of the signals. Experimental results illustrate that the approach using multiple Stenlund–Gustafsson M-Kalman filters (multiple robust and windup-stable Kalman filters) reaches the best performance and robustness in predicting the vehicle tractive forces.     

Activity theory as a framework for building adaptive e-learning systems: A case to provide empirical evidence

We apply activity theory (AT) to design adaptive e-learning systems (AeLS). AT is a framework to study human’s behavior at learning; whereas, AeLS enhance students’ apprenticeship by the personalization of teaching–learning experiences. AeLS depict users’ traits and predicts learning outcomes. The approach was successfully tested: Experimental group took lectures chosen by the anticipation AT principle; whilst, control group received randomly selected lectures. Learning achieved by experimental group reveals a correlation quite significant and high positive; but, for control group the correlation it is not significant and medium positive. We conclude: AT is a useful framework to design AeLS and provide student-centered education.     

Stream flow predictions using nature-inspired Firefly Algorithms and a Multiple Model strategy – Directions of innovation towards next generation practices

Stream flow prediction is studied by Artificial Intelligence (AI) in this paper using Artificial Neural Network (ANN) as a hybrid of Multi-Layer Perceptron (MLP) with the Levenberg–Marquardt (LM) backpropagation learning algorithm (MLP-LM) and (ii) MLP integrated with the Fire-Fly Algorithm (MLP-FFA). Monthly stream flow records used in this prediction problem comprise two stations at Bear River, the U.S.A., for the period of 1961–2012. Six different model structures are investigated for both MLP-LM and MLP-FFA models and their results were analysed using a number of performance measures including Correlation Coefficients (CC) and the Taylor diagram. The results indicate a significant improvement is likely in predicting downstream flows by MLP-FFA over that by MLP-LM, attributed to identifying the global minimum. In addition, an emerging multiple model (ensemble) strategy is employed to treat the outputs of the two MLP-LM and MLP-FFA models as inputs to an ANN model. The results show yet another further possible improvement. These two avenues for improvements identify possible directions towards next generation research activities.     

An extended systematic literature review on provision of evidence for safety certification

ContextCritical systems in domains such as aviation, railway, and automotive are often subject to a formal process of safety certification. The goal of this process is to ensure that these systems will operate safely without posing undue risks to the user, the public, or the environment. Safety is typically ensured via complying with safety standards. Demonstrating compliance to these standards involves providing evidence to show that the safety criteria of the standards are met.ObjectiveIn order to cope with the complexity of large critical systems and subsequently the plethora of evidence information required for achieving compliance, safety professionals need in-depth knowledge to assist them in classifying different types of evidence, and in structuring and assessing the evidence. This paper is a step towards developing such a body of knowledge that is derived from a large-scale empirically rigorous literature review.MethodWe use a Systematic Literature Review (SLR) as the basis for our work. The SLR builds on 218 peer-reviewed studies, selected through a multi-stage process, from 4963 studies published between 1990 and 2012.ResultsWe develop a taxonomy that classifies the information and artefacts considered as evidence for safety. We review the existing techniques for safety evidence structuring and assessment, and further study the relevant challenges that have been the target of investigation in the academic literature. We analyse commonalities in the results among different application domains and discuss implications of the results for both research and practice.ConclusionThe paper is, to our knowledge, the largest existing study on the topic of safety evidence. The results are particularly relevant to practitioners seeking a better grasp on evidence requirements as well as to researchers in the area of system safety. As a major finding of the review, the results strongly suggest the need for more practitioner-oriented and industry-driven empirical studies in the area of safety certification.     

Double-model adaptive fault detection and diagnosis applied to real flight data

The existing multiple model-based estimation algorithms for Fault Detection and Diagnosis (FDD) require the design of a model set, which contains a number of models matching different fault scenarios. To cope with partial faults or simultaneous faults, the model set can be even larger. A large model set makes the computational load intensive and can lead to performance deterioration of the algorithms. In this paper, a novel Double-Model Adaptive Estimation (DMAE) approach for output FDD is proposed, which reduces the number of models to only two, even for the FDD of partial and simultaneous output faults. Two Selective-Reinitialization (SR) algorithms are proposed which can both guarantee the FDD performance of the DMAE. The performance is tested using a simulated aircraft model with the objective of Air Data Sensors (ADS) FDD. Another contribution is that the ADS FDD using real flight data is addressed. Issues related to the FDD using real flight test data are identified. The proposed approaches are validated using real flight data of the Cessna Citation II aircraft, which verified their effectiveness in practice.     

Global parameter optimization for biokinetic modeling of simple batch experiments

Environmental process modeling is challenged by the lack of high quality data, stochastic variations, and nonlinear behavior. Conventionally, parameter optimization is based on stochastic sampling techniques to deal with the nonlinear behavior of the proposed models. Despite widespread use, such tools cannot guarantee globally optimal parameter estimates. It can be especially difficult in practice to differentiate between lack of algorithm convergence, convergence to a non-global local optimum, and model structure deficits. For this reason, we use a deterministic global optimization algorithm for kinetic model identification and demonstrate it with a model describing a typical batch experiment. A combination of interval arithmetic, reformulations, and relaxations allows globally optimal identification of all (six) model parameters. In addition, the results suggest that further improvements may be obtained by modification of the optimization problem or by proof of the hypothesized pseudo-convex nature of the problem suggested by our results.     

Effect of handle design on movement dynamics and muscle co-activation in a wrist flexion task

Arm and wrist manipulanda are commonly used as input devices in teleoperation and gaming applications, establish a physical interface to patients in several rehabilitation robots, and are applied as advanced research tools in biomechanics and neuroscience. Despite the fact that the physical interface, i.e. the handle through which the wrist/hand is attached to the manipulator, may influence interaction and movement behavior, the effects of handle design on these parameters has received little attention. Yet, a poor handle design might lead to overexertion and altered movement dynamics, or result in misinterpretation of results in research studies. In this study, twelve healthy subjects performed repetitions of a wrist flexion task against a dynamic load generated by a 1-DOF robotic wrist manipulandum. Three different handle designs were qualitatively and quantitatively evaluated based on wrist movement kinematics and dynamics, patterns of finger and wrist muscle activity, and ergonomics criteria such as perceived comfort and fatigue. The three proposed designs were further compared to a conventional joystick-like handle. Task performance as well as kinematic and kinetic parameters were found to be unaffected by handle design. Nevertheless, differences were found in perceived task difficulty, comfort and levels of muscle activation of wrist and finger muscles, with significantly higher muscle activation when using a joystick-like design, where the handle is completely enclosed by the hand. Comfort was rated high for the flat handle, adapted to the natural curvature of the hand with the fingers extended. These results may inform for the design of handles serving as physical interface in teleoperation applications, robot-assisted rehabilitation and biomechanics/neuroscience research.     

Use of freely available datasets and machine learning methods in predicting deforestation

The range and quality of freely available geo-referenced datasets is increasing. We evaluate the usefulness of free datasets for deforestation prediction by comparing generalised linear models and generalised linear mixed models (GLMMs) with a variety of machine learning models (Bayesian networks, artificial neural networks and Gaussian processes) across two study regions. Freely available datasets were able to generate plausible risk maps of deforestation using all techniques for study zones in both Mexico and Madagascar. Artificial neural networks outperformed GLMMs in the Madagascan (average AUC 0.83 vs 0.80), but not the Mexican study zone (average AUC 0.81 vs 0.89). In Mexico and Madagascar, Gaussian processes (average AUC 0.89, 0.85) and structured Bayesian networks (average AUC 0.88, 0.82) performed at least as well as GLMMs (average AUC 0.89, 0.80). Bayesian networks produced more stable results across different sampling methods. Gaussian processes performed well (average AUC 0.85) with fewer predictor variables.     

Nonlinear aircraft sensor fault reconstruction in the presence of disturbances validated by real flight data

This paper proposes an approach for Inertial Measurement Unit sensor fault reconstruction by exploiting a ground speed-based kinematic model of the aircraft flying in a rotating earth reference system. Two strategies for the validation of sensor fault reconstruction are presented: closed-loop validation and open-loop validation. Both strategies use the same kinematic model and a newly-developed Adaptive Two-Stage Extended Kalman Filter to estimate the states and faults of the aircraft. Simulation results demonstrate the effectiveness of the proposed approach compared to an approach using an airspeed-based kinematic model. Furthermore, the major contribution is that the proposed approach is validated using real flight test data including the presence of external disturbances such as turbulence. Three flight scenarios are selected to test the performance of the proposed approach. It is shown that the proposed approach is robust to model uncertainties, unmodeled dynamics and disturbances such as time-varying wind and turbulence. Therefore, the proposed approach can be incorporated into aircraft Fault Detection and Isolation systems to enhance the performance of the aircraft.     

Narrowband signal detection techniques in shallow ocean by acoustic vector sensor array

This paper presents the formulation and performance analysis of four techniques for detection of a narrowband acoustic source in a shallow range-independent ocean using an acoustic vector sensor (AVS) array. The array signal vector is not known due to the unknown location of the source. Hence all detectors are based on a generalized likelihood ratio test (GLRT) which involves estimation of the array signal vector. One non-parametric and three parametric (model-based) signal estimators are presented. It is shown that there is a strong correlation between the detector performance and the mean-square signal estimation error. Theoretical expressions for probability of false alarm and probability of detection are derived for all the detectors, and the theoretical predictions are compared with simulation results. It is shown that the detection performance of an AVS array with a certain number of sensors is equal to or slightly better than that of a conventional acoustic pressure sensor array with thrice as many sensors.     

Development of predictive models for the estimation of the probability of suffering fear of falling and other fall risk factors based on posturography parameters in community-dwelling older adults

Falls pose an important problem for older adults. Balance training is one of the main prevention strategies, but there is a lack of objective measurement methods that would allow the effectiveness of the treatments employed to be assessed. This study aimed to analyse the relationship between posturographic parameters and risk factors associated with falling, including the fear of falling (FoF). Forty-one healthy community-dwelling older adults were surveyed on their perception of problems considered to be fall risk factors. Balance measurement with posturography was performed. The relationships between risk factors and falls and risk factors and posturography were analysed by means of cross-tabulation and logistic regression, respectively. Experimental results showed a significant relationship between some of the posturographic parameters and various fall risk factors. Stability limits were related to FoF, and results from the Romberg test with eyes closed with and without foam correlated with problems in kneeling/crouching. The results from the Romberg test with eyes closed and foam correlated with osteoarthritis. Equations were developed to estimate the probability of having such problems. In conclusion, posturography is useful for the estimation of fall risk conditions in relation to three important fall risk factors (FoF, osteoarthritis and problems in kneeling/crouching), and it could be used for targeting, training and studying progress after the use of different treatments.Relevance to industryPosturography can be used as an assessment tool to analyse the effects of those treatments aimed at preventing falls. Furthermore, the equations derived from our results can be used along with posturographic variables to assess patient progress.     

Simulating agricultural land rental markets by combining agent-based models with traditional economics concepts: The case of the Argentine Pampas

Land exchange through rental transactions is a central process in agricultural systems. The land tenure regimes emerge from land transactions and structural and land use changes are tied to the dynamics of the land market. We introduce LARMA, a LAnd Rental MArket model embedded within the Pampas Model (PM), an agent-based model of Argentinean agricultural systems. LARMA produces endogenous formation of land rental prices. LARMA relies on traditional economic concepts for LRP formation but addresses some drawbacks of this approach by being integrated into an agent-based model that considers heterogeneous agents interacting with one another. PM-LARMA successfully reproduced the agricultural land tenure regimes and land rental prices observed in the Pampas. Including adaptive, heterogeneous and interacting agents was critical to this success. We conclude that agent-based and traditional economic models can be successfully combined to capture complex emergent land tenure and market price patterns while simplifying the overall model design.