Wild Animal Information Collection Based on Depthwise Separable Convolution in Software Defined IoT Networks

The wild animal information collection based on the wireless sensor network (WSN) has an enormous number of applications, as demonstrated in the literature. Yet, it has many problems, such as low information density and high energy consumption ratio. The traditional Internet of Things (IoT) system has characteristics of limited resources and task specificity. Therefore, we introduce an improved deep neural network (DNN) structure to solve task specificity. In addition, we determine a programmability idea of software-defined network (SDN) to solve the problems of high energy consumption ratio and low information density brought about by low autonomy of equipment. By introducing some advanced network structures, such as attention mechanism, residuals, depthwise (DW) convolution, pointwise (PW) convolution, spatial pyramid pooling (SPP), and feature pyramid networks (FPN), a lightweight object detection network with a fast response is designed. Meanwhile, the concept of control plane and data plane in SDN is introduced, and nodes are divided into different types to facilitate intelligent wake-up, thereby realizing high-precision detection and high information density of the detection system. The results show that the proposed scheme can improve the detection response speed and reduce the model parameters while ensuring detection accuracy in the software-defined IoT networks.

Retrospective Exploratory Analysis of Task-Specific Effects on Brain Activity after Stroke

Background: Evidence supports cortical reorganization in sensorimotor areas induced by constraint-induced movement therapy (CIMT). However, only a few studies examined the neural plastic changes as a function of task specificity. This provoked us to retrospectively analyze a previously unpublished imaging dataset from chronic stroke survivors before and after participation in the signature CIMT protocol. This exploratory analysis aims to evaluate the functional brain activation changes during a precision and a power grasp task in chronic stroke survivors who received two-weeks of CIMT compared to a control group. Materials and methods: Fourteen chronic stroke survivors, randomized to CIMT (n=8) or non-CIMT (n=6), underwent functional MRI (fMRI) before and after a two-week period. During scan runs, participants performed two different grasp tasks (precision, power). Pre to post changes in laterality index (LI) were compared by group and task for two predetermined motor regions of interest: dorsal premotor cortex (PMd) and primary motor cortex (MI). Results: Two weeks of CIMT resulted in a relative increase in activity in a key region of the motor network, the PMd of the lesioned hemisphere, under precision grasp task conditions compared to a non-treatment control group. However, no changes in LI were observed in MI for either task or group. Conclusion: These findings provide evidence for the task specificity effects of CIMT in the promotion of recovery-supportive cortical reorganization in chronic stroke survivors.

Highly task-specific and distributed neural connectivity in working memory revealed by single-trial decoding in mice and humans

Working memory (WM), the capacity to briefly and intentionally maintain mental items, is key to successful goal-directed behaviour and impaired in a range of psychiatric disorders. To date, several brain regions, connections, and types of neural activity have been correlatively associated with WM performance. However, no unifying framework to integrate these findings exits, as the degree of their species- and task-specificity remains unclear. Here, we investigate WM correlates in three task paradigms each in mice and humans, with simultaneous multi-site electrophysiological recordings. We developed a machine learning-based approach to decode WM-mediated choices in individual trials across subjects from hundreds of electrophysiological measures of neural connectivity with up to 90% prediction accuracy. Relying on predictive power as indicator of correlates of psychological functions, we unveiled a large number of task phase-specific WM-related connectivity from analysis of predictor weights in an unbiased manner. Only a few common connectivity patterns emerged across tasks. In rodents, these were thalamus-prefrontal cortex delta- and beta-frequency connectivity during memory encoding and maintenance, respectively, and hippocampal-prefrontal delta- and theta-range coupling during retrieval, in rodents. In humans, task-independent WM correlates were exclusively in the gamma-band. Mostly, however, the predictive activity patterns were unexpectedly specific to each task and always widely distributed across brain regions. Our results suggest that individual tasks cannot be used to uncover generic physiological correlates of the psychological construct termed WM and call for a new conceptualization of this cognitive domain in translational psychiatry.

Occipital cortex is modulated by transsaccadic changes in spatial frequency: an fMRI study

Previous neuroimaging studies have shown that inferior parietal and ventral occipital cortex are involved in the transsaccadic processing of visual object orientation. Here, we investigated whether the same areas are also involved in transsaccadic processing of a different feature, namely, spatial frequency. We employed a functional magnetic resonance imaging paradigm where participants briefly viewed a grating stimulus with a specific spatial frequency that later reappeared with the same or different frequency, after a saccade or continuous fixation. First, using a whole-brain Saccade > Fixation contrast, we localized two frontal (left precentral sulcus and right medial superior frontal gyrus), four parietal (bilateral superior parietal lobule and precuneus), and four occipital (bilateral cuneus and lingual gyri) regions. Whereas the frontoparietal sites showed task specificity, the occipital sites were also modulated in a saccade control task. Only occipital cortex showed transsaccadic feature modulations, with significant repetition enhancement in right cuneus. These observations (parietal task specificity, occipital enhancement, right lateralization) are consistent with previous transsaccadic studies. However, the specific regions differed (ventrolateral for orientation, dorsomedial for spatial frequency). Overall, this study supports a general role for occipital and parietal cortex in transsaccadic vision, with a specific role for cuneus in spatial frequency processing.

Maximum Relevance Minimum Redundancy Dropout with Informative Kernel Determinantal Point Process

In recent years, deep neural networks have shown significant progress in computer vision due to their large generalization capacity; however, the overfitting problem ubiquitously threatens the learning process of these highly nonlinear architectures. Dropout is a recent solution to mitigate overfitting that has witnessed significant success in various classification applications. Recently, many efforts have been made to improve the Standard dropout using an unsupervised merit-based semantic selection of neurons in the latent space. However, these studies do not consider the task-relevant information quality and quantity and the diversity of the latent kernels. To solve the challenge of dropping less informative neurons in deep learning, we propose an efficient end-to-end dropout algorithm that selects the most informative neurons with the highest correlation with the target output considering the sparsity in its selection procedure. First, to promote activation diversity, we devise an approach to select the most diverse set of neurons by making use of determinantal point process (DPP) sampling. Furthermore, to incorporate task specificity into deep latent features, a mutual information (MI)-based merit function is developed. Leveraging the proposed MI with DPP sampling, we introduce the novel DPPMI dropout that adaptively adjusts the retention rate of neurons based on their contribution to the neural network task. Empirical studies on real-world classification benchmarks including, MNIST, SVHN, CIFAR10, CIFAR100, demonstrate the superiority of our proposed method over recent state-of-the-art dropout algorithms in the literature.

Functional specialization within the inferior parietal lobes across cognitive domains

The inferior parietal lobe (IPL) is a key neural substrate underlying diverse mental processes, from basic attention to language and social cognition, that define human interactions. Its putative domain-global role appears to tie into poorly understood differences between cognitive domains in both hemispheres. Across attentional, semantic, and social cognitive tasks, our study explored functional specialization within the IPL. The task specificity of IPL subregion activity was substantiated by distinct predictive signatures identified by multivariate pattern-learning algorithms. Moreover, the left and right IPL exerted domain-specific modulation of effective connectivity among their subregions. Task-evoked functional interactions of the anterior and posterior IPL subregions involved recruitment of distributed cortical partners. While anterior IPL subregions were engaged in strongly lateralized coupling links, both posterior subregions showed more symmetric coupling patterns across hemispheres. Our collective results shed light on how under-appreciated functional specialization in the IPL supports some of the most distinctive human mental capacities.

Does Exercise-Based Conventional Training Improve Reactive Balance Control among People with Chronic Stroke?

Background: Exercise-based conventional training has predominantly benefited fall-associated volitional balance control domain; however, the effect on reactive balance control is under-examined. Therefore, the purpose of this study was to examine the effect of exercise-based conventional training on reactive balance control. Methods: Eleven people with chronic stroke (PwCS) underwent multi-component training for six weeks (20 sessions) in a tapering manner. Training focused on four constructs-stretching, functional strengthening, balance, and endurance. Volitional balance was measured via movement velocity on the Limits of Stability (LOS) test and reactive balance via center of mass (COM) state stability on the Stance Perturbation Test (SPT). Additionally, behavioral outcomes (fall incidence and/or number of steps taken) were recorded. Results: Movement velocity significantly increased on the LOS test (p < 0.05) post-intervention with a significant decrease in fall incidence (p < 0.05). However, no significant changes were observed in the COM state stability, fall incidence and number of recovery steps on the SPT post-intervention. Conclusion: Although volitional and reactive balance control may share some neurophysiological and biomechanical components, training based on volitional movements might not significantly improve reactive balance control for recovery from large-magnitude perturbations due to its task-specificity.