Dataset Information

Combining feature selection and integration--a neural model for MT motion selectivity.

ABSTRACT:

Background

The computation of pattern motion in visual area MT based on motion input from area V1 has been investigated in many experiments and models attempting to replicate the main mechanisms. Two different core conceptual approaches were developed to explain the findings. In integrationist models the key mechanism to achieve pattern selectivity is the nonlinear integration of V1 motion activity. In contrast, selectionist models focus on the motion computation at positions with 2D features.

Methodology/principal findings

Recent experiments revealed that neither of the two concepts alone is sufficient to explain all experimental data and that most of the existing models cannot account for the complex behaviour found. MT pattern selectivity changes over time for stimuli like type II plaids from vector average to the direction computed with an intersection of constraint rule or by feature tracking. Also, the spatial arrangement of the stimulus within the receptive field of a MT cell plays a crucial role. We propose a recurrent neural model showing how feature integration and selection can be combined into one common architecture to explain these findings. The key features of the model are the computation of 1D and 2D motion in model area V1 subpopulations that are integrated in model MT cells using feedforward and feedback processing. Our results are also in line with findings concerning the solution of the aperture problem.

Conclusions/significance

We propose a new neural model for MT pattern computation and motion disambiguation that is based on a combination of feature selection and integration. The model can explain a range of recent neurophysiological findings including temporally dynamic behaviour.

SUBMITTER: Beck C

PROVIDER: S-EPMC3140976 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Segmenting objects from each other and their background is critical for vision. The speed at which objects move provides a salient cue for segmentation. However, how the visual system represents and differentiates multiple speeds is largely unknown. Here we investigated the neural encoding of multiple speeds of overlapping stimuli in the primate visual cortex. We first characterized the perceptual capacity of human and monkey subjects to segment spatially overlapping stimuli moving at different speeds. We then determined how neurons in the motion-sensitive, middle-temporal (MT) cortex of macaque monkeys encode multiple speeds. We made a novel finding that the responses of MT neurons to two speeds of overlapping stimuli showed a robust bias toward the faster speed component when both speeds were slow (≤ 20°/s). The faster-speed bias occurred even when a neuron had a slow preferred speed and responded more strongly to the slower component than the faster component when presented alone. The faster-speed bias emerged very early in neuronal response and was robust over time and to manipulations of motion direction and attention. As the stimulus speed increased, the faster-speed bias changed to response averaging. Our finding can be explained by a modified divisive normalization model, in which the weights for the speed components are proportional to the responses of a population of neurons elicited by the individual speeds. Our results suggest that the neuron population, referred to as the weighting pool, includes neurons that have a broad range of speed preferences. As a result, the response weights for the speed components are determined by the stimulus speeds and invariant to the speed preferences of individual neurons. Our findings help to define the neural encoding rule of multiple stimuli and provide new insight into the underlying neural mechanisms. The faster-speed bias would benefit behavioral tasks such as figure-ground segregation if figural objects tend to move faster than the background in the natural environment.

Project description:BackgroundFor rehabilitation training systems, it is essential to automatically record and recognize exercises, especially when more than one type of exercise is performed without a predefined sequence. Most motion recognition methods are based on feature engineering and machine learning algorithms. Time-domain and frequency-domain features are extracted from original time series data collected by sensor nodes. For high-dimensional data, feature selection plays an important role in improving the performance of motion recognition. Existing feature selection methods can be categorized into filter and wrapper methods. Wrapper methods usually achieve better performance than filter methods; however, in most cases, they are computationally intensive, and the feature subset obtained is usually optimized only for the specific learning algorithm.ObjectiveThis study aimed to provide a feature selection method for motion recognition of upper-limb exercises and improve the recognition performance.MethodsMotion data from 5 types of upper-limb exercises performed by 21 participants were collected by a customized inertial measurement unit (IMU) node. A total of 60 time-domain and frequency-domain features were extracted from the original sensor data. A hybrid feature selection method by combining filter and wrapper methods (FESCOM) was proposed to eliminate irrelevant features for motion recognition of upper-limb exercises. In the filter stage, candidate features were first selected from the original feature set according to the significance for motion recognition. In the wrapper stage, k-nearest neighbors (kNN), Naïve Bayes (NB), and random forest (RF) were evaluated as the wrapping components to further refine the features from the candidate feature set. The performance of the proposed FESCOM method was verified using experiments on motion recognition of upper-limb exercises and compared with the traditional wrapper method.ResultsUsing kNN, NB, and RF as the wrapping components, the classification error rates of the proposed FESCOM method were 1.7%, 8.9%, and 7.4%, respectively, and the feature selection time in each iteration was 13 seconds, 71 seconds, and 541 seconds, respectively.ConclusionsThe experimental results demonstrated that, in the case of 5 motion types performed by 21 healthy participants, the proposed FESCOM method using kNN and NB as the wrapping components achieved better recognition performance than the traditional wrapper method. The FESCOM method dramatically reduces the search time in the feature selection process. The results also demonstrated that the optimal number of features depends on the classifier. This approach serves to improve feature selection and classification algorithm selection for upper-limb motion recognition based on wearable sensor data, which can be extended to motion recognition of more motion types and participants.