A model predictive control method based on recursive backpropagation neural network and genetic algorithm is proposed for a class of nonlinear systems with time delays and uncertainties. In the offline modeling stage, a multistep-ahead predictor with GA-RBP neural network is designed, where GA-BP neural network is used as a one-step prediction model and GA is employed to train the initial weights and bias of the BP neural network. The incorporation of GA into RBP can reduce the possibility (...) of the BP neural network falling into a local optimum instead of reaching global optimization. In the online optimizing stage, a multistep-ahead GA-RBP neural network predictor and an improved gradient descent method are proposed to efficiently solve the online optimization problem of nonlinear MPC by minimizing a modified quadratic criterion. The designed MPC strategy can avoid information loss while linearizing the controlled system and computing the Hessian matrix and its inverse matrix. Experimental results show that the proposed approach can reduce the computational burden and improve the performance of MPC for the solution of nonlinear controlled systems. (shrink)

Native language listeners engage in predictive processing in many processing situations and adapt their predictive processing to the statistics of the input. In contrast, second language listeners engage in predictive processing in fewer processing situations. The current study uses eye-tracking data from two experiments in bilinguals’ native language (L1) and second language (L2) to explore their predictive processing based on contrastive pitch accent cues, and their adaptation in the face of prediction errors. The results of the (...) first experiment show inhibition effects for unpredicted referents in both the L1 and the L2 that can be modeled with a Bayesian adaptation model, suggesting that bilinguals adapt their prediction in the face of prediction errors in a way that is compatible with the model. In contrast, the results of the second experiment, after a training phase that increased the predictive validity of the cue, show inhibition effects for unpredicted referents only in the L1, but not in the L2. In addition, the Bayesian adaptation model significantly predicts only the L1, but not the L2 data. The results are discussed with respect to adaptation to the statistical properties of the input. (shrink)

In air traffic control, the airspace is divided into several smaller sectors for better management of air traffic and air traffic controller workload. Such sectors are usually managed by a team of two air traffic controllers: planning controller and executive controller. D-side controller is responsible for processing flight-plan information to plan and organize the flow of traffic entering the sector. R-side controller deals with ensuring safety of flights in their sector. A better understanding and predictability (...) of D-side controller actions, for a given traffic scenario, may help in automating some of its tasks and hence reduce workload. In this paper, we propose a learning model to predict D-side controller actions. The learning problem is modeled as a supervised learning problem, where the target variables are D-side controller actions and the explanatory variables are the aircraft 4D trajectory features. The model is trained on six months of ADS-B data over an en-route sector, and its generalization performance was assessed, using crossvalidation, on the same sector. Results indicate that the model for vertical maneuver actions provides highest prediction accuracy. Besides, the model for speed change and course change action provides predictability accuracy of 80% and 87%, respectively. The model to predict the set of all the actions for each flight achieves an accuracy of 70% implying for 70% of flights; D-side controller’s action can be predicted from trajectory information at sector entry position. In terms of operational validation, the proposed approach is envisioned as ATCO assisting tool, not an autonomous tool. Thus, there is always ATCO discretion element, and as more ATCO actions are collected, the models can be further trained for better accuracy. For future work, we will consider expanding the feature set by including parameters such as weather and wind. Moreover, human in the loop simulation will be performed to measure the effectiveness of the proposed approach. (shrink)

Vocal imitation in songbirds exhibits interesting parallels to infant speech development and is currently the model system of choice for exploring the behavioural, molecular and electrophysiological substrates of vocal learning. Among songbirds, the Zebra Finch ( Taeniopygia guttata ) is currently used as the `flying mouse' of birdsong research. Only males sing and they develop their song primarily during a short sensitive period in early life. They learn their speciesspecific song patterns by memorizing and imitating the songs of conspecifics, (...) mainly adults. Since Immelmann's pioneering work, thousands of zebra finches have been raised in strictly controlled auditory environments to examine how their experience affected their songs. In this article, I review the different experimental procedures that have been used in the laboratory to study the social influences on song learning in the Zebra Finch. Poor song learning was observed using passive playback of taped songs, whereas self-eliciting exposure using operant tutoring techniques induced significant learning, but with a high interindividual variability. The success of the training paradigm is often measured by the quality of imitation of the songs to which the young bird is exposed. Using empirical evidence from the field and the laboratory, I will also discuss this issue, by summarizing possible advantages and disadvantages of producing a perfect imitation. So far, the best method to get a close copy of a song model in the Zebra Finch is to place a single young bird with an adult male. This situation, which is rather unnatural, does not meet the criteria for precise control necessary in experimental conditions. Optimizing the methods used to train a zebra finch to learn a song, in order to be able to predict the imitation success, will improve our understanding of the dynamics of vocal production learning. It would also consolidate this species as a research model of relevance to human speech development and disorders. Keywords: Zebra Finch; birdsong; learning; development; memory; social influences. (shrink)

This simulation study is a fuzzy model-based neural network control method. The basic idea is to consider the application of a special type of neural networks based on radial basis function, which belongs to a class of associative memory neural networks. The novelty of this approach is the use of an RBF neural network controller in a model reference adaptive control architecture, based on a one-step-ahead Takagi–Sugeno fuzzy model. The objective is to control the concentration (...) in a continuous stirred-tank reactor highly non-linear system and to assure its stability by limiting the temperature rise generated from the irreversible exothermic reaction. This contribution will help to reduce environmental impact of chemical waste. (shrink)

An implicit ambiguity in the field of prediction-based decision-making concerns the relation between the concepts of prediction and decision. Much of the literature in the field tends to blur the boundaries between the two concepts and often simply refers to ‘fair prediction’. In this paper, we point out that a differentiation of these concepts is helpful when trying to implement algorithmic fairness. Even if fairness properties are related to the features of the used prediction model, what is more properly (...) called ‘fair’ or ‘unfair’ is a decision system, not a prediction model. This is because fairness is about the consequences on human lives, created by a decision, not by a prediction. In this paper, we clarify the distinction between the concepts of prediction and decision and show the different ways in which these two elements influence the final fairness properties of a prediction-based decision system. As well as discussing this relationship both from a conceptual and a practical point of view, we propose a framework that enables a better understanding and reasoning of the conceptual logic of creating fairness in prediction-based decision-making. In our framework, we specify different roles, namely the ‘prediction-modeler’ and the ‘decision-maker,’ and the information required from each of them for being able to implement fairness of the system. Our framework allows for deriving distinct responsibilities for both roles and discussing some insights related to ethical and legal requirements. Our contribution is twofold. First, we offer a new perspective shifting the focus from an abstract concept of algorithmic fairness to the concrete context-dependent nature of algorithmic decision-making, where different actors exist, can have different goals, and may act independently. In addition, we provide a conceptual framework that can help structure prediction-based decision problems with respect to fairness issues, identify responsibilities, and implement fairness governance mechanisms in real-world scenarios. (shrink)

What makes a word easy to learn? Early‐learned words are frequent and tend to name concrete referents. But words typically do not occur in isolation. Some words are predictable from their contexts; others are less so. Here, we investigate whether predictability relates to when children start producing different words (age of acquisition; AoA). We operationalized predictability in terms of a word's surprisal in child‐directed speech, computed using n‐gram and long‐short‐term‐memory (LSTM) language models. Predictability derived from LSTMs was generally a better (...) predictor than predictability derived from n‐gram models. Across five languages, average surprisal was positively correlated with the AoA of predicates and function words but not nouns. Controlling for concreteness and word frequency, more predictable predicates and function words were learned earlier. Differences in predictability between languages were associated with cross‐linguistic differences in AoA: the same word (when it was a predicate) was produced earlier in languages where the word was more predictable. (shrink)

This paper provides an overview of developments in a dual processing theory of automatic and controlled processing that began with the empirical and theoretical work described by Schneider and Shiffrin (1977) and Shiffrin and Schneider (1977) over a quarter century ago. A review of relevant empirical findings suggests that there is a set of core behavioral phenomena reflecting differences between controlled and automatic processing that must be addressed by a successful theory. These phenomena relate to: consistency in training, serial versus (...) parallel processing, level of effort, robustness to stressors, degree of control, effects on long‐term memory, and priority encoding. We detail a computational model of controlled processing, CAP2, that accounts for these phenomena as emergent properties of an underlying hybrid computational architecture. The model employs a large network of distributed data modules that can categorize, buffer, associate, and prioritize information. Each module is a connectionist network with input and output layers, and each module communicates with a central Control System by outputting priority and activity report signals, and by receiving control signals. The Control System is composed of five processors including a Goal Processor, an Attention Controller, an Activity Monitor, an Episodic Store, and a Gating & Report Relay. The transition from controlled to automatic processing occurs in this model as the data modules become capable of transmitting their output without mediation by the Control System. We describe recent progress in mapping the components of this model onto specific neuroanatomical substrates, briefly discuss the potential for applying functional neuroimaging techniques to test the model's predictions, and its relation to other models. (shrink)

BackgroundThis study explored the proportion of variance in depressive symptoms explained by processes targeted by BA (activation, behavioral avoidance, anticipatory pleasure, and brooding), and processes targeted by cognitive control training (cognitive control, attentional biases, and brooding).MethodsFive hundred and twenty adults were recruited. They completed a spatial cueing task as a measure of attentional biases and a cognitive task as a measure of cognitive control and completed self-report measures of activation, behavioral avoidance, anticipatory pleasure, brooding, and depressive symptoms. With path analysis (...) models, we explored the relationships between these predictors and depressive symptoms.ResultsBA processes were significant predictors of depressive symptoms, and activation partially predicted anticipatory pleasure, which in turn predicted depressive symptoms. However, cognitive control and attentional biases predicted neither brooding nor depressive symptoms. A comprehensive model including all processes fit the data but did not explain more of the variance in brooding or depressive symptoms than a model including only BA processes.LimitationsThe spatial cueing task was associated with low reliability and the use of a non-clinical sample limited the generalizability of the conclusions.ConclusionActivation, behavioral avoidance, brooding, and anticipatory pleasure are relevant processes to target in order to reduce depressive symptoms, while cognitive control and attentional biases are not. (shrink)

Sense of agency refers to the ability to influence one’s functioning and environment, relating to self-efficacy and wellbeing. In youth, agency may be challenged by external demands or redefinition of self-image. Music, having heightened relevance for the young, has been argued to provide feelings of self-agency for them. Yet, there is little empirical research on how music impacts adolescents’ daily sense of agency. The current study investigated whether music listening influences adolescents’ perceived agency in everyday life and which individual and (...) contextual determinants would explain such an influence. Participants were 44 adolescents (48% female, 36% with training in music, mean age 14), recruited through local schools. The mobile Experience Sampling app MuPsych was used to collect brief self-reports of personal music listening experiences during daily life. This method assessed the change in the listener’s perceived control over both their emotional states (Internal Agency), and their external environment (External Agency), over five minutes of music listening. Also measured were changes in mood states, and contextual variables (social situation, concurrent activity, and reason for listening). The impact of music on the sense of agency was analyzed using multilevel structural equation modelling. There was no general increase of agency across all music episodes, but agency fluctuations were determined by specific individual and contextual factors. Music training predicted increases in both internal and external agency during music listening, and external agency increased more for male participants. Certain context features such as listening alone, paying attention to music, and listening for enjoyment were related to greater increases in agency. Increases in agency significantly correlated with increases in mood valence. Our findings confirmed the plasticity and situational embeddedness of the sense of agency. Music indeed can support agency, but the impact is dependent on specific individual and contextual factors. Sense of agency can be seen as a health resource and significant part of youth development, and current findings provide new insight into when and by whom such affordance is likely to be employed. (shrink)

As the stock market is an important part of the national economy, more and more investors have begun to pay attention to the methods to improve the return on investment and effectively avoid certain risks. Many factors affect the trend of the stock market, and the relevant information has the nature of time series. This paper proposes a composite model CNN-BiSLSTM to predict the closing price of the stock. Bidirectional special long short-term memory improved on bidirectional long short-term memory (...) adds 1 − tanh function in the output gate which makes the model better predict the stock price. The model extracts advanced features that influence stock price through convolutional neural network, and predicts the stock closing price through BiSLSTM after the data processed by CNN. To verify the effectiveness of the model, the historical data of the Shenzhen Component Index from July 1, 1991, to October 30, 2020, are used to train and test the CNN-BiSLSTM. CNN-BiSLSTM is compared with multilayer perceptron, recurrent neural network, long short-term memory, BiLSTM, CNN-LSTM, and CNN-BiLSTM. The experimental results show that the mean absolute error, root-mean-squared error, and R-square evaluation indicators of the CNN-BiSLSTM are all optimal. Therefore, CNN-BiSLSTM can accurately predict the closing price of the Shenzhen Component Index of the next trading day, which can be used as a reference for the majority of investors to effectively avoid certain risks. (shrink)

Multimodal neuroimaging provides a rich source of data for identifying brain regions associated with disease progression and aging. However, present studies still typically analyze modalities separately or aggregate voxel-wise measurements and analyses to the structural level, thus reducing statistical power. As a central example, previous works have used two quantitative MRI parameters—R2* and quantitative susceptibility —to study changes in iron associated with aging in healthy and multiple sclerosis subjects, but failed to simultaneously account for both. In this article, we propose (...) a unified framework that combines information from multiple imaging modalities and regularizes estimates for increased interpretability, generalizability, and stability. Our work focuses on joint region detection problems where overlap between effect supports across modalities is encouraged but not strictly enforced. To achieve this, we combine L1, total variation, and L2 group lasso penalties. While the TV penalty encourages geometric regularization by controlling estimate variability and support boundary geometry, the group lasso penalty accounts for similarities in the support between imaging modalities. We address the computational difficulty in this regularization scheme with an alternating direction method of multipliers optimizer. In a neuroimaging application, we compare our method against independent sparse and joint sparse models using a dataset of R2* and QS maps derived from MRI scans of 113 healthy controls: our method produces clinically-interpretable regions where specific iron changes are associated with healthy aging. Together with results across multiple simulation studies, we conclude that our approach identifies regions that are more strongly associated with the variable of interest, more accurate, and more stable with respect to training data variability. This work makes progress toward a stable and interpretable multimodal imaging analysis framework for studying disease-related changes in brain structure and can be extended for classification and disease prediction tasks. (shrink)

With renewable energy being increasingly connected to power grids, pumped storage plants play a very important role in restraining the fluctuation of power grids. However, conventional control strategy could not adapt well to the different control tasks. This paper proposes an intelligent nonlinear model predictive control strategy, in which hydraulic-mechanical and electrical subsystems are combined in a synchronous control framework. A newly proposed online sequential extreme learning machine algorithm with forgetting factor is introduced to learn the dynamic behaviors (...) of the coupling system. Specifically, the initial learning parameters are optimized by prior-knowledge learning and a new self-adaptive adjustment strategy is also put forward. Subsequently, the stair-like control strategy and artificial sheep algorithm are used in rolling the optimization mechanism to replace the existing complex differential geometric solutions. Comparative experiments are carried out under different working conditions based on a PSP in China. The results show that the influence from coupling factors can be considerable and the proposed MPC strategy indicates superiority in voltage and load adjustment as well as the frequency oscillation suppression. (shrink)

Automatic control of physiological variables is one of the most active areas in biomedical engineering. This paper is centered in the prediction of the analgesic variables evolution in patients undergoing surgery. The proposal is based on the use of hybrid intelligent modelling methods. The study considers the Analgesia Nociception Index to assess the pain in the patient and remifentanil as intravenous analgesic. The model proposed is able to make a one-step-ahead prediction of the remifentanil dose corresponding to the current (...) state of the patient. The input information is the previous remifentanil dose, the ANI variable and the electromyogram signal. Modelling techniques used are Artificial Neural Networks and Support Vector machines for Regression combined with clustering methods. Both training and validation were done with a real dataset from different patients. Results obtained show the potential of this methodology to calculate the drug dose corresponding to a given analgesic state of the patient. (shrink)

: The concept of Self-Control carried by contemporary criminology has been put forward in order to catch up with increasing crime rates in society, to prevent crime, and to function in anger control. Works done in this area also include measures that must be taken early in the course of a kind of education to prevent crime in general. we see that in some countries Social and Emotional Learning programs are used in areas such as character education, prevention of violence, (...) anti-drug measures and school discipline. In the Islamic world, the self-control from the earliest times has been dealt with and dealt with as a religious matter. Many of the verses of God and the words of the Prophet are directed at controlling one's self, controlling one's emotions and anger. It has been reported to believers that a way of earning God's love and compassion is self-control. Despite being encouraged by various Islamic sciences, one of the main themes of Islamic mysticism is self-control. Therefore, Islam is one of the main subjects of self-control in education understanding. Summary: In the early 1990s, Michael R. Gottfredson and Travis Hirschi's "General Theory of Crime" made considerable progress in the theory of control theory and demonstrated remarkable results based on experiments. Along with these, we see that in some countries Social and Emotional Learning programs are used in areas such as character education, prevention of violence, anti-drug measures and school discipline. In 2002 UNESCO undertook the introduction of this program in order to serve the above purposes and sent letters to the education ministries of approximately 140 countries. Today, there are studies aiming to educate the sensation itself instead of using emotion to train. Self-regulation refers to being able to control our emotions and manage them. Some emotions develop over time during the child's brain and biological development and reach maturity level when the development of the nervous system is complete. Pratt and some other researchers found that communalization with parents and neighbourhood conditions predicted the diversity of self-control. They argue that community-level control and socialization are equally important factors contributing to the development of self-control. It has been seen as a virtue for the liberation of man's self and his desires. This virtue was met with the term Sophrosyne in ancient Greek, which means that "one lives his life diligently and intelligently; harmonious balance and wisdom." The Romans and the old Christian church have called it Temperantia, restricting emotional excesses. The subject of self-control and balancing of emotions is also studied in Islamic religion under the name of "Nafs Struggle". In fact, beliefs are emotional patterns. In order for human beings to be able to place their thoughts and beliefs in their native place, they have to be transformed into emotional patterns. For example, "goodness is good to do" expresses a thought. To add the emotional dimension to it, it must be reinforced by confirming that it is nice to do good to people. Emotions that begin to direct man's behaviours certainly shape him according to a reference value. These reference values or, in other words, standard values are determined and imposed by religions or are derived from the moral code of the community. Some scholars have also defined religion as a moral field that regulates psychological and behavioural tendencies by rewarding grieving actions and punishing those who are contrary to common good. Therefore, religion also includes moral concepts; it also affects supernatural thoughts. It is thought that religion, in turn, arouses beliefs and attitudes that prevent personal violence, impiety and dishonesty. In fact, what we call conscience is that the external control power becomes an internal control mechanism. To put it more precisely, it means internalizing these values of powers that represent authority that imposes external controlling thoughts and emotions. Therefore, our conscience in the social and physical environment constitutes the conscience of the things we have developed and the accusations that we have developed. The development of conscience in a person is also linked to the development of education and responsibility he has received. The main goal of religious education is to place the belief in God and to adopt and sustain a whole of values based on God's existence. For a person to know and feel the presence of a person who always sees and controls him will always lead him to a more controlled and supervised life. He who believes that God sees and hears people and that he will be punished or rewarded according to his bad and good behaviours, of course, seeks to control himself. Because in the method of reward and punishment, the aim is to create a mental condition for him by encouraging and loving something. Also, as a result of this operation, the brain learns to set limits on behaviour. This is conscious behaviour. Since consciousness is the information we have about ourselves, we are consciously observing and studying ourselves. The thing that distinguishes human beings from other beings is that they are aware of what they are aware of and that they realize it. If we did not have such a property, it would not be moral and we could not control ourselves. We can only find ourselves in ourselves and without any intermediary. These tools are not only scientific instruments, but also five senses, imaginations and thoughts, which are tools of the mind. Besides, when we add the ability of a person to evaluate and observe himself as an external object, wisdom can be understood when God suggests that we should think about our own nafs. The conscious person who thinks about himself is the one who takes charge of himself and accounts for his soul. To address this, the Messenger of God said: "The wise man,, draws his soul into account and works for the post-mortem; and if he is weak, he will obey God's will and ask for God." The Messenger recommends that a person be curled into himself and think and perceive about the soul, with the following words: "Do not go round with your heart, multiply your condolences and cry." Of course, many arguments have been put in place to ensure that self-control of the person in religious life is ensured. One of these is a feeling. Because the sense of shame requires to be embarrassed by other people, and to behave oneself. The Messenger, when he saw someone among ansar counselling to his brother about the modesty, said, "Certainly, it is by faith." Because the feeling of embarrassment is fed by the fear that the deprivation of social good will live on man. In personal relationships, a person is bound to put a limit on his behaviour in order not to offend others. The sensation of emotion is a feeling of emotion recorded in the frontal area of the brain, covering the social skills. The opposite of shame is insensitivity, impudence and irresponsibility. (shrink)

Inner speech has been shown to vary in form along several dimensions. Along condensation, condensed inner speech forms have been described, that are supposed to be deprived of acoustic, phonological and even syntactic qualities. Expanded forms, on the other extreme, display articulatory and auditory properties. Along dialogality, inner speech can be monologal, when we engage in internal soliloquy, or dialogal, when we recall past conversations or imagine future dialogs involving our own voice as well as that of others addressing us. (...) Along intentionality, it can be intentional (when we deliberately rehearse material in short-term memory) or it can arise unintentionally (during mind wandering). We introduce the ConDialInt model, a neurocognitive predictive control model of inner speech that accounts for its varieties along these three dimensions. ConDialInt spells out the condensation dimension by including inhibitory control at the conceptualization, formulation or articulatory planning stage. It accounts for dialogality, by assuming internal model adaptations and by speculating on neural processes underlying perspective switching. It explains the differences between intentional and spontaneous varieties in terms of monitoring. We present an fMRI study in which we probed varieties of inner speech along dialogality and intentionality, to examine the validity of the neuroanatomical correlates posited in ConDialInt. Condensation was also informally tackled. Our data support the hypothesis that expanded inner speech recruits speech production processes down to articulatory planning, resulting in a predicted signal, the inner voice, with auditory qualities. Along dialogality, covertly using an avatar’s voice resulted in the activation of right hemisphere homologs of the regions involved in internal own-voice soliloquy and in reduced cerebellar activation, consistent with internal model adaptation. Switching from first-person to third-person perspective resulted in activations in precuneus and parietal lobules. Along intentionality, compared with intentional inner speech, mind wandering with inner speech episodes was associated with greater bilateral inferior frontal activation and decreased activation in left temporal regions. This is consistent with the reported subjective evanescence and presumably reflects condensation processes. Our results provide neuroanatomical evidence compatible with predictive control and in favor of the assumptions made in the ConDialInt model. (shrink)

Actions that are intended to produce harmful consequences can fail to achieve their desired effects in numerous ways. We refer to action sequences in which harmful intentions are thwarted as deviant causal chains. The culpable control model of blame (CCM)is a useful tool for predicting and explaining the attributions that observers make of the actors whose harmful intentions go awry. In this paper, we describe six types of deviant causal chains; those in which: an actor’s attempt is obviated by (...) the intervention of another person or the environment; the intended effects could not have been produced regardless of the actor’s behavior; other causes diminish the actor’s causal role; the actor brings about foreseen but undesired consequences as a result of pursuing his or her focal goal; the focal action produces a chain of increasingly remote causal events; and the actor derives unforeseen benefits from his or her nefarious actions. A basic assumption of the CCM in these cases is that attributions for the participants’ actions will depend on positive and negative evaluations of their intentions and behaviors. We describe empirical findings that are consistent with this assumption, and predict other findings for causal deviance phenomena that have not yet been investigated empirically. (shrink)

In the chemical production process, the temperature of the continuous reactor has nonlinear characteristics such as large inertia. An improved autodisturbance control method is proposed. By improving the tracking differentiator with adjustable parameters, the expanded state observer and the control structure obtained an improved automatic disturbance rejection control model and realized the optimal control of the nonlinear and large-delay systems. On the process control training system, the experiment of the continuous system process flow is compared with the anti-interference of (...) the Smith predictive compensation system, which uses an optimal set of data. The reactor temperature fluctuates, but the self-resistance is improved. The optimal overshoot of the disturbance is close to 0. Compared with the original antidisturbance controller, the antidisturbance time is not affected by the number of iterations, which reduces the high requirements on the accuracy of the parameters. Therefore, the improved automatic disturbance rejection control improves the operation and enhances the ability to resist external disturbance that changes the controlled object. (shrink)

This document describes the implementation of a conical tank control system using an adaptive neurofuzzy system. For implementation, an indirect approach is used where the controller is optimized using the model obtained during the plant identification carried out using data obtained during the system operation. Furthermore, implementation includes training of neuro fuzzy-systems and application to control a conical tank. Regarding plant identification, preliminary training takes place using data obtained for different input values. The controller configuration is established (...) considering the analogy with a discrete-time linear system. The simulation shows that the control system manages to approach the desired response given by the considered reference model. (shrink)

This paper reports the experience of using the PAELLA algorithm as a helper tool in robust regression instead of as originally intended for outlier identification and removal. This novel usage of the algorithm takes advantage of the occurrence vector calculated by the algorithm in order to strengthen the effect of the more reliable samples and lessen the impact of those that otherwise would be considered outliers. Following that aim, a series of experiments is conducted in order to learn how to (...) better use the information contained in the occurrence vector. Using a contrively difficult artificial data set, a reference predictive model is fit using the whole raw dataset. The second experiment reports the results of fitting a similar predictive model but discarding the samples marked as outliers by PAELLA. The third experiment uses the occurrence vector provided by PAELLA in order to classify the observations in multiple bins and fit every possible model changing which bins are considered for fitting and which are discarded in that particular model. The fourth experiment introduces a sampling process before fitting in which the occurrence vector represents the likelihood of being considered in the training data set. The fifth experiment considers the sampling process as an internal step to be performed interleaved between the training epochs. The last experiment compares our approach using weighted neural networks to a state of the art method. (shrink)

In recent years, the green aviation technology draws more attention, and more hybrid power units have been applied to the aerial vehicles. To achieve the high performance and long lifetime of components during varied working conditions, the effective regulation of the energy management is necessary for the vehicles with hybrid power unit. In this paper, power prediction-based model predictive control for energy management strategy is proposed for the vehicle equipped with HPU based on turboshaft engine in order to (...) maintain proper battery’s state of charge and decrease turboshaft engine’s exhaust gas temperature. First, a modeling approach based on data-driven method is adopted to obtain the mathematical model of turboshaft engine considering time delay and inertial of states. An integrated power predictor consisting of the classification of input status and the subpredictors are developed based on the deep learning method to improve the accuracy of the prediction model of the model predictive control. Subsequently, an EMS based on MPC using the proposed power predictor is introduced to regulate the SOC of battery and the EGT of turboshaft engine. The comparison with experimental results shows the high accuracy of mathematical model of turboshaft engine. The simulation results show the effectiveness of the proposed EMS for the vehicle, and the effects of different weight coefficients of objective function on the proposed EMS are discussed. (shrink)

Recently, the pandemic caused by COVID-19 is severe in the entire world. The prevention and control of crimes associated with COVID-19 are critical for controlling the pandemic. Therefore, to provide efficient and convenient intelligent legal knowledge services during the pandemic, we develop an intelligent system for legal information retrieval on the WeChat platform in this paper. The data source we used for training our system is “The typical cases of national procuratorial authorities handling crimes against the prevention and control of (...) the new coronary pneumonia pandemic following the law”, which is published online by the Supreme People’s Procuratorate of the People’s Republic of China. We base our system on convolutional neural network and use the semantic matching mechanism to capture inter-sentence relationship information and make a prediction. Moreover, we introduce an auxiliary learning process to help the network better distinguish the relation between two sentences. Finally, the system uses the trained model to identify the information entered by a user and responds to the user with a reference case similar to the query case and gives the reference legal gist applicable to the query case. (shrink)

Connected vehicle fleets have formed significant component of industrial internet of things scenarios as part of Industry 4.0 worldwide. The number of vehicles in these fleets has grown at a steady pace. The vehicles monitoring with machine learning algorithms has significantly improved maintenance activities. Predictive maintenance potential has increased where machines are controlled through networked smart devices. Here, benefits are accrued considering uptimes optimization. This has resulted in reduction of associated time and labor costs. It has also provided significant (...) increase in cost benefit ratios. Considering vehicle fault trends in this research predictive maintenance problem is addressed through hybrid deep learning-based ensemble method (HDLEM). The ensemble framework which acts as predictive analytics engine comprises of three deep learning algorithms viz modified cox proportional hazard deep learning (MCoxPHDL), modified deep learning embedded semi supervised learning (MDLeSSL) and merged LSTM (MLSTM) networks. Both sensor as well as historical maintenance data are collected and prepared using benchmarking methods for HDLEM training and testing. Here, times between failures (TBF) modeling and prediction on multi-source data are successfully achieved. The results obtained are compared with stated deep learning models. This ensemble framework offers great potential towards achieving more profitable, efficient and sustainable vehicle fleet management solutions. This helps better telematics data implementation which ensures preventative management towards desired solution. The ensemble method's superiority is highlighted through several experimental results. (shrink)

Machine learning (ML) has emerged as a promising tool in psychiatry, revolutionising diagnostic processes and patient outcomes. In this paper, I argue that while ML studies show promising initial results, their application in mimicking clinician-based judgements presents inherent limitations (Shatte et al. in Psychol Med 49:1426–1448. https://doi.org/10.1017/S0033291719000151, 2019). Most models still rely on DSM (the Diagnostic and Statistical Manual of Mental Disorders) categories, known for their heterogeneity and low predictive value. DSM's descriptive nature limits the validity of psychiatric diagnoses, (...) which leads to overdiagnosis, comorbidity, and low remission rates. The application in psychiatry highlights the limitations of supervised ML techniques. Supervised ML models inherit the validity issues of their training data set. When the model's outcome is a DSM classification, this can never be more valid or predictive than the clinician’s judgement. Therefore, I argue that these models have little added value to the patient. Moreover, the lack of known underlying causal pathways in psychiatric disorders prevents validating ML models based on such classifications. As such, I argue that high accuracy in these models is misleading when it is understood as validating the classification. In conclusion, these models will not will not offer any real benefit to patient outcomes. I propose a shift in focus, advocating for ML models to prioritise improving the predictability of prognosis, treatment selection, and prevention. Therefore, data selection and outcome variables should be geared towards this transdiagnostic goal. This way, ML can be leveraged to better support clinicians in personalised treatment strategies for mental health patients. (shrink)

The accurate annotation of an unknown protein sequence depends on extant data of template sequences. This could be empirical or sets of reference sequences, and provides an exhaustive pool of probable functions. Individual methods of predicting dominant function possess shortcomings such as varying degrees of inter-sequence redundancy, arbitrary domain inclusion thresholds, heterogeneous parameterization protocols, and ill-conditioned input channels. Here, I present a rigorous theoretical derivation of various steps of a generic algorithm that integrates and utilizes several statistical methods to (...) predict the dominant function in unknown protein sequences. The accompanying mathematical proofs, interval definitions, analysis, and numerical computations presented are meant to offer insights not only into the specificity and accuracy of predictions, but also provide details of the operatic mechanisms involved in the integration and its ensuing rigor. The algorithm uses numerically modified raw hidden markov model scores of well defined sets of training sequences and clusters them on the basis of known function. The results are then fed into an artificial neural network, the predictions of which can be refined using the available data. This pipeline is trained recursively and can be used to discern the dominant principal function, and thereby, annotate an unknown protein sequence. Whilst, the approach is complex, the specificity of the final predictions can benefit laboratory workers design their experiments with greater confidence. -/- . (shrink)

The dominant model for interpreting brain imaging experiments assumes that the brain is organized to support mental processes that control behavior. However functional neuroimaging experiments, particularly of cognitive tasks, have not shown a high level of reproducibility and localization. This lack of clear functional segregation has been blamed on limitations in imaging technology and non linearity and regional overlap in how the brain implements these processes. However the validity of the underlying cognitive models used to describe the brain have (...) rarely been questioned or directly tested against imaging results. We propose an alternative model of brain function which correlates observed human behavior directly with measured brain activity without assumptions about intervening cognitive processes, that we term the Non-Cognitive Behavioral Model (NBM). Our model derives from Behavioral Psychology but is extended to include brain activations in addition to behavior as an observable. A further extension is the role of neuroplasticity as opposed to innate cognitive processes in the development of the brains support of cognitive behavior. Applications of NBM to neuroimaging studies are described and contrasted with the standard methodology which we refer to as the Standard Cognitive Model (SCM). In one application, the NBM correctly predicted the global, total energy consumption as the brain parameter that best correlates with a person being in the state of consciousness, a correlation missed by studies using the SCM due to its assumption that global activity does not support cognitive processes. Neuroplasticity is shown to provide a natural explanation of findings that object recognition activating the fusiform facial area comes from expertise through raining as opposed to the SCM explanation of an innate cognitive process specialized for face recognition. The conclusions are generalized to explain the poor reproducibility of cognitive processes reported in functional neuroimaging and to suggest how such studies can be used to better explain how the brain supports behavior. (shrink)

The complex characteristics of the gas turbine in a combined cycle unit have brought great difficulties in its control process. Meanwhile, the increasing emphasis on the efficiency, safety, and cleanliness of the power generation process also makes it significantly important to put forward advanced control strategies to satisfy the desired control demands of the gas turbine system. Therefore, aiming at higher control performance of the gas turbine in the gas-steam combined cycle process, a novel fuzzy model predictive control (...) strategy based on the fuzzy selection mechanism and simultaneous heat transfer search algorithm is presented in this paper. The objective function of rolling optimization in this novel FMPC consists of two parts which represent the state optimization and output optimization. In the weight coefficient selection of those two parts, the fuzzy selection mechanism is introduced to overcome the uncertainties existing in the system. Furthermore, on account of the rapidity of the control process, the SHTS algorithm is used to solve the optimization problem rather than the traditional quadratic programming method. The validity of the proposed method is confirmed through simulation experiments of the gas turbine in a combined power plant. The simulation results demonstrate the remarkable superiorities of the adopted algorithm with higher control precision and stronger disturbance rejection ability as well as less optimization time. (shrink)

In this paper, an active frequency control strategy of wind turbines based on model predictive control is proposed by using the power margin of wind turbines operating in load shedding mode. The frequency response model of the microgrid system with the load shedding of the wind turbines is used to predict the output power and system frequency deviation of the wind turbine. According to the prediction information, the output power control signal of the model predictive (...) controller in the wind turbine can be optimized. On this basis, a wind turbine active participation frequency control strategy based on model predictive control is designed by rolling prediction and optimization. The wind turbine power control signal after the strategy is used to adjust the output power of the wind turbine and balance the change of the active power of the system to reduce the frequency deviation. (shrink)

The spacing effect is among the most widely replicated empirical phenomena in the learning sciences, and its relevance to education and training is readily apparent. Yet successful applications of spacing effect research to education and training is rare. Computational modeling can provide the crucial link between a century of accumulated experimental data on the spacing effect and the emerging interest in using that research to enable adaptive instruction. In this paper, we review relevant literature and identify 10 criteria for rigorously (...) evaluating computational models of the spacing effect. Five relate to evaluating the theoretic adequacy of a model, and five relate to evaluating its application potential. We use these criteria to evaluate a novel computational model of the spacing effect called the Predictive Performance Equation. Predictive Performance Equation combines elements of earlier models of learning and memory including the General Performance Equation, Adaptive Control of Thought—Rational, and the New Theory of Disuse, giving rise to a novel computational account of the spacing effect that performs favorably across the complete sets of theoretic and applied criteria. We implemented two other previously published computational models of the spacing effect and compare them to PPE using the theoretic and applied criteria as guides. (shrink)

This paper addresses the robust output feedback model predictive control schemes for networked control systems with input quantization. The logarithmic quantizer is considered in this paper, and the sector bound approach is applied, which appropriately treats the quantization error as a sector-bounded uncertainty. The presented method involves an offline designed state observer using linear matrix inequality and online robust output feedback MPC algorithms which optimize one free control move followed by the output feedback using the estimated state. Moreover, (...) due to the uncertainty of estimation error, a technique of refreshing the bound of estimation error which involves the quantization error is provided so as to guarantee the recursive feasibility of the optimization problem. The proposed MPC schemes inherit the characteristics of the synthesis approach of MPC, guaranteeing the recursive feasibility of the optimization problem and the stability of a closed-loop system, and explicitly account for quantization error. Two simulation examples are given to illustrate the effectiveness of the proposed methods. (shrink)

While temporal preparation has frequently been examined through the manipulation of foreperiods, the role of force level during temporal preparation remains underexplored. In our study, we propose to manipulate mental training of attentional control in order to shed light on the role of the force level and autonomic nervous system in the temporal preparation of an action. Forty subjects, divided into mental training group (n = 20) and without mental training group (n = 20), participated in this study. The influence (...) of the attentional control and force levels on the autonomic nervous system were measured using the skin conductance response and the heart rate variability; the accuracy of the motor responses was measured using a method derived from machine learning. Behaviorally, only the mental training group reinforced its motor and attentional control. When using short foreperiod durations and high force level, motor and attentional control decreased, consistent with the dominant sympathetic system. This resulted in an increased anticipation rate of responses with a higher reaction time compared to the long foreperiods duration and low force level, in which the reaction time significantly decreased, with enhancement of the expected force level, showing consistency with the dominant parasympathetic system. Interestingly, results revealed a predictive relationship between the sympathovagal balance and motor and attentional control during the long foreperiods and low force level. Finally, results demonstrate that attentional mental training leads to the reinforcement of interactions between the autonomic nervous system and attentional processes which are involved in the temporal preparation of a force task. (shrink)

Past research shows that the bilingual experience may enhance cognitive executive function. In this experiment, we evaluated cognitive control in bilinguals relative to monolinguals by using a dimensional overlap model to predict performance in a task composed of Stroop and Simon stimuli. A group of 24 Spanish monolinguals and 24 bilinguals with differing first languages and all having Spanish as a second language did a picture naming task and a task composed of Stroop and Simon stimuli, where the effect (...) of different overlap conditions between stimuli and responses were examined. The tasks were performed in Spanish for both groups and performance was indexed with behavioral and electrophysiological measures. We hypothesized that the bilinguals’ daily language practice in L2 reflected overlap conditions similar to the Simon task. Both naming a picture in L2 and the Simon task would involve conflict at the response level. L2 picture naming entails interference between two potential oral responses, to name in L2 vs. L1. Similarly, incongruent stimuli in the Simon task produce interference because the irrelevant dimension overlap with an incorrect response. In contrast, the manual Stroop task involves a different type of conflict between two overlapping stimulus dimensions. We predicted for these reasons a superior performance in Simon tasks over Stroop tasks for bilinguals, while monolinguals were expected to have a similar performance in both tasks. We also expected to see a correlation between the performance on the picture naming task and the Simon task in bilinguals. However, the behavioral results did not confirm these hypotheses. In fact, both groups had similar congruency effects as measured by reaction times and error rates, and there was no correlation between the picture naming and Simon task in bilinguals. Despite this, the electrophysiological data suggested a relationship between the picture naming task and the P300 congruency effect in bilinguals. Our findings provide insights into the neurocognitive bases of language and serve as a research avenue for language behaviors in bilinguals. (shrink)

The demonstration of a sequential congruency effect in sequence learning has been offered as evidence for control processes that act to inhibit automatic response tendencies via unconscious conflict monitoring. Here we propose an alternative interpretation of this effect based on the associative learning of chains of sequenced contingencies. This account is supported by simulations with a Simple Recurrent Network, an associative model of sequence learning. We argue that the control- and associative-based accounts differ in their predictions concerning the magnitude (...) of the sequential congruency effect across training. These predictions are tested by reanalysing data from a study by Shanks, Wilkinson, and Channon . The results support the associative learning account which explains the sequential congruency effect without appealing to control processes. (shrink)

The key to action control is one’s ability to adequately predict the consequences of one’s actions. Predictive processing theories assume that forward models enable rapid “preplay” to assess the match between predicted and intended action effects. Here we propose the novel hypothesis that “reading” another’s action intentions requires a rich forward model of that agent’s action. Such a forward model can be obtained and enriched through learning by either practice or simulation. Based on this notion, we ran (...) a series of studies on soccer goalkeepers and novices, who predicted the intended direction of penalties being kicked at them in a computerized penalty-reading task. In line with hypotheses, extensive practice in penalty kicking improved performance in penalty reading among goalkeepers who had extensive prior experience in penalty blocking but not in penalty kicking. A robust benefit in penalty reading did not result from practice in kinesthetic motor imagery of penalty kicking in novice participants. To test whether goalkeepers actually use such penalty-kicking imagery in penalty reading, we trained a machine-learning classifier on multivariate fMRI activity patterns to distinguish motor-imagery-related from attention-related strategies during a penalty-imagery training task. We then applied that classifier to fMRI data related to a separate penalty-reading task and showed that 2/3 of all correctly read penalty kicks were classified as engaging the motor-imagery circuit rather than merely the attention circuit. This study provides initial evidence that, in order to read our opponent’s action intention, it helps to observe their action kinematics, and use our own forward model to predict the sensory consequences of “our” penalty kick if we were to produce these action kinematics ourselves. In sum, it takes practice as a penalty kicker to become a penalty killer. (shrink)

The interdisciplinary research area Cognitive Interaction Technology (CIT) aims to understand and support interactions between human users and other elements of socio-technical systems. Important reasons for the new interest in understanding CIT in sport psychology are the impressive development of cognitive robotics and advanced technologies such as virtual or augmented reality systems, cognitive glasses or neurotechnology settings. The present article outlines this area of research, addresses ethical issues, and presents an empirical study in the context of a new measurement and (...) assessment system for training in karate. Recent advances in the field of cognitive assistance systems enabled largely automatized assessments of individual mental representation structures for action sequences, such as choreographed movement patterns in dance or martial arts. Empirical investigations with karate practitioners of different skill levels demonstrate that advanced software-based survey and algorithmic analysis procedures based on cognitive models generate individualized performance predictions for a movement sequence from theKanku-dai kata(a pre-defined karate movement sequence), which correlated significantly not only with formal expertise (kyu/danrank) but also with the actual likelihood of mistakes in action execution. This information could prospectively be used to define individual training goals for deliberate practice and incorporated into cognitive interaction technology to provide appropriate feedback. We argue that the development of cognitive interaction systems for sport should explicitly take ethical issues into consideration and present a particular developed engineering approach. The potential benefits of such an assistance system for intermediate and advanced practitioners include more effective and flexible practice, as well as supportive effects, and more flexible training schedules. Furthermore, we argue that researchers from the field of sport psychology can benefit from advances in technological systems that enhance the understanding of mental and motor control in skilled voluntary action. (shrink)

With the continual development of artificial intelligence and smart computing in recent years, quantitative approaches have become increasingly popular as an efficient modeling tool as they do not necessitate complicated mathematical models. Many nations have taken steps, such as transitioning to online schooling, to decrease the harm caused by coronaviruses. Inspired by the demand for technology in early education, the present research uses a radial basis function neural network modeling technique to predict preschool instructors’ technology usage in classes based on (...) recognized determinant characteristics of technology acceptance. In this regard, this study utilized the RBFNN approach to predict preschool teachers’ technology acceptance behavior, based on the theory of planned behavior, which states that behavioral achievement, in our case the actual technology use in class, depends on motivation, intention and ability, and behavioral control. Thus, this research design is based on an adapted version of the technology acceptance model with eight dimensions: D1. Perceived usefulness, D2. Perceived ease of use, D3. Perceived enjoyment, D4. Intention to use, D5. Actual use, D6. Compatibility, D7. Attitude, and D8. Self-efficacy. According to the TAM, actual usage is significantly predicted by the other seven dimensions used in this research. Instead of using the classical multiple linear regression statistical processing of data, we opted for a NN based on the RBF approach to predict the actual usage behavior. This study included 182 preschool teachers who were randomly chosen from a project-based national preschool teacher training program and who responded to our online questionnaire. After designing the RBF function with the actual usage as an output variable and the other seven dimensions as input variables, in the model summary, we obtained in the training sample a sum of squares error of 37.5 and a percent of incorrect predictions of 43.3%. In the testing sample, we obtained a sum of squares error of 14.88 and a percent of incorrect predictions of 37%. Thus, we can conclude that 63% of the classified data are correctly assigned to the models’ dependent variable, i.e., actual technology use, which is a significant rate of correct predictions in the testing sample. This high significant percentage of correct classification represents an important result, mainly because this is the first study to apply RBFNN’s prediction on psychological data, opening up a new interdisciplinary field of research. (shrink)

Prior research found correlations between reflection test performance and philosophical tendencies among laypeople. In two large studies (total N = 1299)—one pre-registered—many of these correlations were replicated in a sample that included both laypeople and philosophers. For example, reflection test performance predicted preferring atheism over theism and instrumental harm over harm avoidance on the trolley problem. However, most reflection-philosophy correlations were undetected when controlling for other factors such as numeracy, preferences for open-minded thinking, personality, philosophical training, age, and gender. Nonetheless, (...) some correlations between reflection and philosophical views survived this multivariate analysis and were only partially confounded with either education or self-reported reasoning preferences. Unreflective thinking still predicted believing in God whereas reflective thinking still predicted believing that (a) proper names like ‘Santa’ do not necessarily refer to entities that actually exist and (b) science does reveal the fundamental nature of the world. So some robust relationships between reflection and philosophical tendencies were detected even among philosophers, and yet there was clearly more to the link between reflection and philosophy. To this end, demographic and metaphilosophical hypotheses are considered. (shrink)

A fuzzy predictive fault-tolerant control scheme is proposed for a wide class of discrete-time nonlinear systems with uncertainties, interval time-varying delays, and partial actuator failures as well as unknown disturbances, in which the main opinions focus on the relevant theory of FPFTC based on Takagi-Sugeno fuzzy model description of these systems. The T-S fuzzy model represents the discrete-time nonlinear system in the form of the discrete uncertain time-varying delay state space, which is firstly constructed by a set (...) of local linear models and the nonlinear membership functions. The novel improved state space model can be further obtained by extending the output tracking error to the constructed model. Then the fuzzy predictive fault-tolerant control law based on this extended model is designed, which can increase more control degrees of freedom. Utilizing Lyapunov-Krasovskill theory, less conservative delay-range-dependent stable conditions in terms of linear matrix inequality constraints are given to ensure the asymptotically robust stability of closed-loop system. Meanwhile, the optimized cost function and H-infinity performance index are introduced to the stable conditions to guarantee the robust performance and antidisturbance capability. The simulation results on the temperature control of a strong nonlinear continuous stirred tank reactor show that the proposed control scheme is feasible and effective. (shrink)

With the improvement of citizens’ risk perception ability and environmental protection awareness, social conflicts caused by environmental problems in large-scale construction projects are becoming more and more frequent. Traditional social risk prevention management has some defects in obtaining risk data, such as limited coverage, poor availability, and insufficient timeliness, which makes it impossible to realize effective early warning of social risks in the era of big data. This paper focuses on the three environments of diversification of stakeholders, risk media, and (...) big data era. The evolution characteristics of the social risk of environmental damage of large-scale construction projects are analyzed from the four stages of incubation, outbreak, mitigation, and regression in essence. On this basis, a social risk early warning model is constructed， and the multicenter network governance mode of social risk of environmental damage in large-scale construction projects and practical social risk prevention strategies in different stages are put forward. Experiments show that the long short-term memory neural network model is effective and feasible for predicting the social risk trend of environmental damage of large-scale construction projects. Compared with other classical models, the long short-term memory model has the advantages of strong processing capability and high early warning accuracy for time-sensitive data and will have broad application prospects in the field of risk control research. By using the network governance framework and long short-term memory model, this paper studies the environmental mass events of large-scale construction projects on the risk early warning method, providing reference for the government to effectively prevent and control social risk of environmental damage of large-scale construction project in China. (shrink)

This study aims to predict the shear strength of reinforced concrete deep beams based on artificial neural network using four training algorithms, namely, Levenberg–Marquardt, quasi-Newton method, conjugate gradient, and gradient descent. A database containing 106 results of RC deep beam shear strength tests is collected and used to investigate the performance of the four proposed algorithms. The ANN training phase uses 70% of data, randomly taken from the collected dataset, whereas the remaining 30% of data are used for the algorithms’ (...) evaluation process. The ANN structure consists of an input layer with 9 neurons corresponding to 9 input parameters, a hidden layer of 10 neurons, and an output layer with 1 neuron representing the shear strength of RC deep beams. The performance evaluation of the models is performed using statistical criteria, including the correlation coefficient, root mean square error, mean absolute error, and mean absolute percentage error. The results show that the ANN-CG model has the best prediction performance with R = 0.992, RMSE = 14.02, MAE = 14.24, and MAPE = 6.84. The results of this study show that the ANN-CG model can accurately predict the shear strength of RC deep beams, representing a promising and useful alternative design solution for structural engineers. (shrink)

Foundational research focuses on the theory, but theories are to be related also to other theories, experiments, facts in their domains, data, and to their uses in applications, whether of prediction, control, or explanation. A theory is to be identified through its class of models, but not so narrowly as to disallow these roles. The language of science is to be studied separately, with special reference to the relations listed above, and to the consequent need for resources other than (...) for theoretical description. Peculiar to the foundational level are questions of completeness (specifically in the representation of measurement), and of interpretation (a topic beset with confusions of truth and evidence, and with inappropriate metalinguistic abstraction). (shrink)

Controlled natural languages (CNL) with a direct mapping to formal logic have been proposed to improve the usability of knowledge representation systems, query interfaces, and formal specifications. Predictive editors are a popular approach to solve the problem that CNLs are easy to read but hard to write. Such predictive editors need to be able to “look ahead” in order to show all possible continuations of a given unfinished sentence. Such lookahead features, however, are difficult to implement in a (...) satisfying way with existing grammar frameworks, especially if the CNL supports complex nonlocal structures such as anaphoric references. Here, methods and algorithms are presented for a new grammar notation called Codeco, which is specifically designed for controlled natural languages and predictive editors. A parsing approach for Codeco based on an extended chart parsing algorithm is presented. A large subset of Attempto Controlled English has been represented in Codeco. Evaluation of this grammar and the parser implementation shows that the approach is practical, adequate and efficient. (shrink)

The human masticatory system is a complex functional unit characterized by a multitude of skeletal components, muscles, soft tissues, and teeth. Muscle activation dynamics cannot be directly measured on live human subjects due to ethical, safety, and accessibility limitations. Therefore, estimation of muscle activations and their resultant forces is a longstanding and active area of research. Reinforcement learning (RL) is an adaptive learning strategy which is inspired by the behavioral psychology and enables an agent to learn the dynamics of an (...) unknown system via policy-driven explorations. The RL framework is a well-formulated closed-loop system where high capacity neural networks are trained with the feedback mechanism of rewards to learn relatively complex actuation patterns. In this work, we are building on a deep RL algorithm, known as the Soft Actor-Critic, to learn the inverse dynamics of a simulated masticatory system, i.e., learn the activation patterns that drive the jaw to its desired location. The outcome of the proposed training procedure is a parametric neural model which acts as the brain of the biomechanical system. We demonstrate the model’s ability to navigate the feasible three-dimensional (3D) envelope of motion with sub-millimeter accuracies. We also introduce a performance analysis platform consisting of a set of quantitative metrics to assess the functionalities of a given simulated masticatory system. This platform assesses the range of motion, metabolic efficiency, the agility of motion, the symmetry of activations, and the accuracy of reaching the desired target positions. We demonstrate how the model learns more metabolically efficient policies by integrating a force regularization term in the RL reward. We also demonstrate the inverse correlation between the metabolic efficiency of the models and their agility and range of motion. The presented masticatory model and the proposed RL training mechanism are valuable tools for the analysis of mastication and other biomechanical systems. We see this framework’s potential in facilitating the functional analyses aspects of surgical treatment planning and predicting the rehabilitation performance in post-operative subjects. (shrink)

Experimental studies of speech production involving compensations for auditory and somatosensory perturbations and adaptation after training suggest that both types of sensory information are considered to plan and monitor speech production. Interestingly, individual sensory preferences have been observed in this context: subjects who compensate less for somatosensory perturbations compensate more for auditory perturbations, and \textit{vice versa}. We propose to integrate this sensory preference phenomenon in a model of speech motor planning using a probabilistic model in which speech units (...) are characterized both in auditory and somatosensory terms. Sensory preference is implemented in the model according to two approaches. In the first approach, which is often used in motor control models accounting for sensory integration, sensory preference is attributed to the relative precision (i.e., inverse of the variance) of the sensory characterization of the speech motor goals associated with phonological units (which are phonemes in the context of this paper). In the second, ``more original’’ variant, sensory preference is implemented by modulating the sensitivity of the comparison between the predicted sensory consequences of motor commands and the sensory characterizations of the phonemes. We present simulation results using these two variants, in the context of the adaptation to an auditory perturbation, implemented in a 2-dimensional biomechanical model of the tongue. Simulation results show that both variants lead to qualitatively similar results. Distinguishing them experimentally would require precise analyses of partial compensation patterns. However, the second proposed variant implements sensory preference without changing the sensory characterizations of the phonemes. This dissociates sensory preference and sensory characterizations of the phonemes, and makes the account of sensory preference more flexible. Indeed, in the second variant the sensory characterizations of the phonemes can remain stable, when sensory preference varies as a response to cognitive or attentional control. This opens new perspectives for capturing speech production variability associated with aging, disorders and speaking conditions. (shrink)

The rapid development of computers and technology affects modern daily life. Individuals in the digital age need to develop computational thinking skills. Existing studies have shown that programming teaching is conducive to cultivating students’ CT, and various learning models have different effects on the cultivation of CT. This study proposed a problem-oriented learning model that is closely related to programming and computational thinking. In all, 60 eighth-grade students from a middle school in China were divided into an experimental group (...) which adopted the POL model, and a control group which adopted the lecture-and-practice learning model. The results showed that the students who were instructed using the POL model performed better than those who were instructed using the LAP model on CT concepts, CT practices, and CT perspectives. Significant differences were found for CT concepts and CT perspectives, but not for CT practices. Findings have implications for teachers who wish to apply new learning models to facilitate students’ CT skills, and the study provides a reference case for CT training and Python programming teaching. (shrink)

The Theory of Planned Behavior predicts that a combination of attitudes, perceived norms, and perceived behavioral control predict intentions, and that intentions ultimately predict behavior. Previous studies have found that the TPB can predict students’ engagement in plagiarism. Furthermore, the General Theory of Crime suggests that self-control is particularly important in predicting engagement in unethical behavior such as plagiarism. In Study 1, we incorporated self-control in a TPB model and tested whether norms, attitudes, and self-control predicted intention to plagiarize (...) and plagiarism behavior. The best statistical fit for the path-analytic model was achieved when a direct path from self-control to plagiarism engagement was specified. In Study 2, we added a measure of perceived behavioral control and split the measurement of norms into descriptive and injunctive components. This study found that both self-control and perceived-behavioral control additively contributed to the prediction of plagiarism and the path-analytic model achieved its best fit when direct paths from perceived norms to plagiarism behavior were specified. These studies suggest that setting strong anti-plagiarism norms, such as by the use of honor codes, and seeking to enhance students’ self-control may reduce engagement in plagiarism. (shrink)

Concern about air-quality in urban areas has led to the implementation of Low Emission Zones as one of many other initiatives to control it. Recently in Spain, the enactment of a law made this mandatory for cities with a population larger than 50k inhabitants. The delimitation of these areas is not without controversy because of possible negative economic and social impacts. Therefore, clear assessments of how these initiatives decrease pollutant concentrations are to be provided. Madrid Central is a major initiative (...) of Madrid city council for reducing motor traffic and the associated air pollution in the city centre. This Low Emission Zone starts at the end of 2018, but the first fully-operational period corresponds to the second quarter of 2019. In this work, a methodology based on the Gaussian Process to analyse the evolution of Nitrogen Dioxide inside Madrid Central is undertaken. A Gaussian Process is a stochastic process suitable for interpretable model selection and predictions. Due to its probabilistic nature it provides error estimation at predictions. After the activation of Madrid Central, a relevant reduction of Nitrogen Dioxide has been observed. However, the role of the meteorology during this period must be ascertained to correctly evaluate the role of the activation of the Low Emission Zone against a prone weather. In this work, a model based on the Gaussian Process is trained with meteorological information to predict the concentration of Nitrogen Dioxide at Madrid Central, $[NO_{2}]$. This probabilistic description allows extracting statistical information on the reduction affected by the meteorological scenario and separately by the Madrid Central activation. (shrink)