No abstract

In a multisensory task, human adults integrate information from different sensory modalities -behaviorally in an optimal Bayesian fashion- while children mostly rely on a single sensor modality for decision making. The reason behind this change of behavior over age and the process behind learning the required statistics for optimal integration are still unclear and have not been justified by the conventional Bayesian modeling. We propose an interactive multisensory learning framework without making any prior assumptions about the sensory models. In this framework, learning in every modality and in their joint space is done in parallel using a single-step reinforcement learning method. A simple statistical test on confidence intervals on the mean of reward distributions is used to select the most informative source of information among the individual modalities and the joint space. Analyses of the method and the simulation results on a multimodal localization task show that the learning system autonomously starts with sensory selection and gradually switches to sensory integration. This is because, relying more on modalities -i.e. selection- at early learning steps (childhood) is more rewarding than favoring decisions learned in the joint space since, smaller state-space in modalities results in faster learning in every individual modality. In contrast, after gaining sufficient experiences (adulthood), the quality of learning in the joint space matures while learning in modalities suffers from insufficient accuracy due to perceptual aliasing. It results in tighter confidence interval for the joint space and consequently causes a smooth shift from selection to integration. It suggests that sensory selection and integration are emergent behavior and both are outputs of a single reward maximization process; i.e. the transition is not a preprogrammed phenomenon.

No abstract

No abstract

Sleep disturbances are common in Alzheimer’s disease and other neurodegenerative disorders, and together represent a potential therapeutic target for disease modification. A major barrier for studying sleep in patients with dementia is the requirement for overnight polysomnography (PSG) to achieve formal sleep staging. This is not only costly, but also spending a night in a hospital setting is not always advisable in this patient group. As an alternative to PSG, portable electroencephalography (EEG) headbands (HB) have been developed, which reduce cost, increase patient comfort, and allow sleep recordings in a person’s home environment. However, naïve applications of current automated sleep staging systems tend to perform inadequately with HB data, due to their relatively lower quality. Here we present a deep learning (DL) model for automated sleep staging of HB EEG data to overcome these critical limitations. The solution includes a simple band-pass filtering, a data augmentation step, and a model using convolutional (CNN) and long short-term memory (LSTM) layers. With this model, we have achieved 74% (±10%) validation accuracy on low-quality two-channel EEG headband data and 77% (±10%) on gold-standard PSG. Our results suggest that DL approaches achieve robust sleep staging of both portable and in-hospital EEG recordings, and may allow for more widespread use of ambulatory sleep assessments across clinical conditions, including neurodegenerative disorders.

No abstract

No abstract

In this letter, we propose a learning system, active decision fusion learning (ADFL), for active fusion of decisions. Each decision maker, referred to as a local decision maker, provides its suggestion in the form of a probability distribution over all possible decisions. The goal of the system is to learn the active sequential selection of the local decision makers in order to consult with and thus learn the final decision based on the consultations. These two learning tasks are formulated as learning a single sequential decision-making problem in the form of a Markov decision process (MDP), and a continuous reinforcement learning method is employed to solve it. The states of this MDP are decisions of the attended local decision makers, and the actions are either attending to a local decision maker or declaring final decisions. The learning system is punished for each consultation and wrong final decision and rewarded for correct final decisions. This results in minimizing the consultation and decision-making costs through learning a sequential consultation policy where the most informative local decision makers are consulted and the least informative, misleading, and redundant ones are left unattended. An important property of this policy is that it acts locally. This means that the system handles any nonuniformity in the local decision maker's expertise over the state space. This property has been exploited in the design of local experts. ADFL is tested on a set of classification tasks, where it outperforms two well-known classification methods, Adaboost and bagging, as well as three benchmark fusion algorithms: OWA, Borda count, and majority voting. In addition, the effect of local experts design strategy on the performance of ADFL is studied, and some guidelines for the design of local experts are provided. Moreover, evaluating ADFL in some special cases proves that it is able to derive the maximum benefit from the informative local decision makers and to minimize attending to redundant ones.