Features selection by genetic algorithm optimization with k-nearest neighbour and learning ensemble to predict Parkinson disease

<span lang="EN-US">Among the several ways followed for detecting Parkinson's disease, there is the one based on the speech signal, which is a symptom of this disease. In this paper focusing on the signal analysis, a data of voice records has been used. In these records, the patients were asked to utter vowels “a”, “o”, and “u”. Discrete wavelet transforms (DWT) applied to the speech signal to fetch the variable resolution that could hide the most important information about the patients. From the approximation a3 obtained by Daubechies wavelet at the scale 2 level 3, 21 features have been extracted: a <a name="_Hlk88480766"></a>linear predictive coding (LPC), energy, zero-crossing rate (ZCR), mel frequency cepstral coefficient (MFCC), and wavelet Shannon entropy. Then for the classification, the K-nearest neighbour (KNN) has been used. The KNN is a type of instance-based learning that can make a decision based on approximated local functions, besides the ensemble learning. However, through the learning process, the choice of the training features can have a significant impact on overall the process. So, here it stands out the role of the genetic algorithm (GA) to select the best training features that give the best accurate classification.</span>

EXPRESS: “Run to the hills”: Specific contributions of anticipated energy expenditure during active spatial learning

Grounded views of cognition consider that space perception is shaped by the body and its potential for action. These views are substantiated by observations such as the distance-on-hill effect, described as the overestimation of visually perceived uphill distances. An interpretation of this phenomenon is that slanted distances are overestimated because of the integration of energy expenditure cues. The visual perceptual processes involved are however usually tackled through explicit estimation tasks in passive situations. The goal of this study was to consider instead more ecological active spatial processing. Using immersive virtual reality and an omnidirectional treadmill, we investigated the effect of anticipated implicit physical locomotion cost by comparing spatial learning for uphill and downhill routes, while maintaining actual physical cost and walking speed constant. In the first experiment, participants learnt city layouts by exploring uphill or downhill routes. They were then tested using a landmark positioning task on a map. In the second experiment, the same protocol was used with participants who wore loaded ankle weights. Results from the first experiment showed that walking uphill routes led to a global underestimation of distances compared to downhill routes. This inverted distance-of-hill effect was not observed in the second experiment, where an additional effort was applied. These results suggest that the underestimation of distances observed in experiment one emerged from recalibration processes whose function was to solve the transgression of proprioceptive predictions linked with uphill energy expenditure. Results are discussed in relation to constructivist approaches on spatial representations and predictive coding theories.

Instability and Uncertainty Are Critical for Psychotherapy: How the Therapeutic Alliance Opens Us Up

Tschacher and Haken have recently applied a systems-based approach to modeling psychotherapy process in terms of potentially beneficial tendencies toward deterministic as well as chaotic forms of change in the client’s behavioral, cognitive and affective experience during the course of therapy. A chaotic change process refers to a greater exploration of the states that a client can be in, and it may have a potential positive role to play in their development. A distinction is made between on the one hand, specific instances of instability which are due to techniques employed by the therapist, and on the other, a more general instability which is due to the therapeutic relationship, and a key, necessary result of a successful therapeutic alliance. Drawing on Friston’s systems-based model of free energy minimization and predictive coding, it is proposed here that the increase in the instability of a client’s functioning due to therapy can be conceptualized as a reduction in the precisions (certainty) with which the client’s prior beliefs about themselves and their world, are held. It is shown how a good therapeutic alliance (characterized by successful interpersonal synchrony of the sort described by Friston and Frith) results in the emergence of a new hierarchical level in the client’s generative model of themselves and their relationship with the world. The emergence of this new level of functioning permits the reduction of the precisions of the client’s priors, which allows the client to ‘open up’: to experience thoughts, emotions and experiences they did not have before. It is proposed that this process is a necessary precursor to change due to psychotherapy. A good consilience can be found between this approach to understanding the role of the therapeutic alliance, and the role of epistemic trust in psychotherapy as described by Fonagy and Allison. It is suggested that beneficial forms of instability in clients are an underappreciated influence on psychotherapy process, and thoughts about the implications, as well as situations in which instability may not be beneficial (or potentially harmful) for therapy, are considered.

The structured flow on the brain's resting state manifold

Spontaneously fluctuating brain activity patterns emerge at rest and relate to brain functional networks involved in task conditions. Despite detailed descriptions of the spatio-temporal brain patterns, our understanding of their generative mechanism is still incomplete. Using a combination of computational modeling and dynamical systems analysis we provide a complete mechanistic description in terms of the constituent entities and the productive relation of their causal activities leading to the formation of a resting state manifold via the network connectivity. We demonstrate that the symmetry breaking by the connectivity creates a characteristic flow on the manifold, which produces the major empirical data features including spontaneous high amplitude co-activations, neuronal cascades, spectral cortical gradients, multistability and characteristic functional connectivity dynamics. The understanding of the brain's resting state manifold is fundamental for the construction of task-specific flows and manifolds used in theories of brain function such as predictive coding.

Expectation violations produce error signals in mouse V1

Repeated exposure to visual sequences changes the form of evoked activity in the primary visual cortex (V1). Predictive coding theory provides a potential explanation for this, namely that plasticity shapes cortical circuits to encode spatiotemporal predictions and that subsequent responses are modulated by the degree to which actual inputs match these expectations. Here we use a recently developed statistical modeling technique called Model-Based Targeted Dimensionality Reduction (MbTDR) to study visually-evoked dynamics in mouse V1 in context of a previously described experimental paradigm called "sequence learning". We report that evoked spiking activity changed significantly with training, in a manner generally consistent with the predictive coding framework. Neural responses to expected stimuli were suppressed in a late window (100-150ms) after stimulus onset following training, while responses to novel stimuli were not. Omitting predictable stimuli led to increased firing at the expected time of stimulus onset, but only in trained mice. Substituting a novel stimulus for a familiar one led to changes in firing that persisted for at least 300ms. In addition, we show that spiking data can be used to accurately decode time within the sequence. Our findings are consistent with the idea that plasticity in early visual circuits is involved in coding spatiotemporal information.

Comparisons of Speech Parameterisation Techniques for Classification of Intellectual Disability Using Machine Learning

Classification of intellectually disabled children through manual assessment of speech at an early age is inconsistent, subjective, time-consuming and prone to error. This study attempts to classify the children with intellectual disabilities using two speech feature extraction techniques: Linear Predictive Coding (LPC) based cepstral parameters, and Mel-frequency cepstral coefficients (MFCC). Four different classification models: k-nearest neighbour (k-NN), support vector machine (SVM), linear discriminant analysis (LDA) and radial basis function neural network (RBFNN) are employed for classification purposes. 48 speech samples of each group are taken for analysis, from subjects with a similar age and socio-economic background. The effect of the different frame length with the number of filterbanks in the MFCC and different frame length with the order in the LPC is also examined for better accuracy. The experimental outcomes show that the projected technique can be used to help speech pathologists in estimating intellectual disability at early ages.

Prediction Error-Based Action Policy Learning for Quadcopter Flight Control

Quadcopters are finding their place in everything from transportation, delivery, hospitals, and to homes in almost every part of daily life. In places where human intervention for quadcopter flight control is impossible, it becomes necessary to equip drones with intelligent autopilot systems so that they can make decisions on their own. All previous reinforcement learning (RL)-based efforts for quadcopter flight control in complex, dynamic, and unstructured environments remained unsuccessful during the training phase in avoiding the trend of catastrophic failures by naturally unstable quadcopters. In this work, we propose a complementary approach for quadcopter flight control using prediction error as an effective control policy reward in the sensory space instead of rewards from unstable action spaces alike in conventional RL approaches. The proposed predictive coding biased competition using divisive input modulation (PC/BC-DIM) neural network learns prediction error-based flight control policy without physically actuating quadcopter propellers, which ensures its safety during training. The proposed network learned flight control policy without any physical flights, which reduced the training time to almost zero. The simulation results showed that the trained agent reached the destination accurately. For 20 quadcopter flight trails, the average path deviation from the ground truth was 1.495 and the root mean square (RMS) of the goal reached 1.708.