InRFNet: Involution Receptive Field Network for COVID-19 Diagnosis

COVID-19 is an emerging infectious disease that has been rampant worldwide since its onset causing Lung irregularity and severe respiratory failure due to pneumonia. The Community-Acquired Pneumonia (CAP), Normal, and COVID-19 Computed Tomography (CT) scan images are classified using Involution Receptive Field Network from Large COVID-19 CT scan slice dataset. The proposed lightweight Involution Receptive Field Network (InRFNet) is spatial specific and channel-agnostic with Receptive Field structure to enhance the feature map extraction. The InRFNet model evaluation results show high training (99%) and validation (96%) accuracy. The performance metrics of the InRFNet model are Sensitivity (94.48%), Specificity (97.87%), Recall (96.34%), F1-score (96.33%), kappa score (94.10%), ROC-AUC (99.41%), mean square error (0.04), and the total number of parameters (33100).

V1 receptive field structure contributes to neuronal response latency

The timing of neuronal responses is considered to be important for information transferring and communication across individual neurons. However, the sources of variabilities in the timing of neuronal responses are not well understood and sometimes over-interpreted. A systematic variability in the response latencies of the primary visual cortex has been reported in presence of drifting grating stimulus. Whereas the response latencies are systematically dependent on stimulus orientation. To understand the underlying mechanism of these systematic latencies, we recorded the neuronal response of the cat visual cortex, area 17, and simulated the response latency of V1 neurons, with two geometric models. We showed that outputs of these two models significantly predict the response latencies of the electrophysiology recording during orientation tasks. The periodic patterns created in the raster plots were dependent on the relative position of the stimulus rotation center and the receptive-field sub-regions. We argue the position of stimulus is contributing to systematic response latencies, dependent on drifting orientation. Therefore, we provide a toolbox based on our geometrical model for determining the exact location of RF sub-regions. Our result indicates that a major source of neuronal variability is the lack of fine-tuning in the task parameters. Considering the simplicity of the orientation selectivity task, we argue fine-tuning of stimulus properties is crucial for deduction of neural variability in higher-order cortical areas and understanding their neural dynamics.

Root CT Segmentation Using Incremental Learning Methodology on Improved Multiple Resolution Images

The real-time issue of reliability segmenting root structure while using X-Ray Computed Tomography (CT) images is addressed in this work. A deep learning approach is proposed using a novel framework, involving decoders and encoders. The encoders-decoders framework is useful to improve multiple resolution by means of upsampling and downsampling images. The methodology of the work is enhanced by incorporating network branches with individual tasks using low-resolution context information and high-resolution segmentation. In large volumetric images, it is possible to resolve small root details by implementing a memory efficient system, resulting in the formation of a complete network. The proposed work, recent image analysis tool developed for root CT segmented is compared with several other previously existing methodology and it is found that this methodology is more efficient. Quantitatively and qualitatively, it is found that a multiresolution approach provides high accuracy in a shallower network with a large receptive field or deep network in a small receptive field. An incremental learning approach is also embedded to enhance the performance of the system. Moreover, it is also capable of detecting fine and large root materials in the entire volume. The proposed work is fully automated and doesn’t require user interaction.

Machine remaining life prediction based on multi-layer self-attention and temporal convolution network

Convolution neural network (CNN) has been widely used in the field of remaining useful life (RUL) prediction. However, the CNN-based RUL prediction methods have some limitations. The receptive field of CNN is limited and easy to happen gradient vanishing problem when the network is too deep. The contribution differences of different channels and different time steps to RUL prediction are not considered, and only use deep learning features or handcrafted statistical features for prediction. These limitations can lead to inaccurate prediction results. To solve these problems, this paper proposes an RUL prediction method based on multi-layer self-attention (MLSA) and temporal convolution network (TCN). The TCN is used to extract deep learning features. Dilated convolution and residual connection are adopted in TCN structure. Dilated convolution is an efficient way to widen receptive field, and the residual structure can avoid the gradient vanishing problem. Besides, we propose a feature fusion method to fuse deep learning features and statistical features. And the MLSA is designed to adaptively assign feature weights. Finally, the turbofan engine dataset is used to verify the proposed method. Experimental results indicate the effectiveness of the proposed method.

Sound Event Detection by Pseudo-Labeling in Weakly Labeled Dataset

Weakly labeled sound event detection (WSED) is an important task as it can facilitate the data collection efforts before constructing a strongly labeled sound event dataset. Recent high performance in deep learning-based WSED’s exploited using a segmentation mask for detecting the target feature map. However, achieving accurate detection performance was limited in real streaming audio due to the following reasons. First, the convolutional neural networks (CNN) employed in the segmentation mask extraction process do not appropriately highlight the importance of feature as the feature is extracted without pooling operations, and, concurrently, a small size kernel forces the receptive field small, making it difficult to learn various patterns. Second, as feature maps are obtained in an end-to-end fashion, the WSED model would be weak to unknown contents in the wild. These limitations would lead to generating undesired feature maps, such as noise in the unseen environment. This paper addresses these issues by constructing a more efficient model by employing a gated linear unit (GLU) and dilated convolution to improve the problems of de-emphasizing importance and lack of receptive field. In addition, this paper proposes pseudo-label-based learning for classifying target contents and unknown contents by adding ’noise label’ and ’noise loss’ so that unknown contents can be separated as much as possible through the noise label. The experiment is performed by mixing DCASE 2018 task1 acoustic scene data and task2 sound event data. The experimental results show that the proposed SED model achieves the best F1 performance with 59.7% at 0 SNR, 64.5% at 10 SNR, and 65.9% at 20 SNR. These results represent an improvement of 17.7%, 16.9%, and 16.5%, respectively, over the baseline.

Russian Historiosophy of the ХXth Century in the Context of the Tradition of the Moral and Psychological Novel by F. Dostoevsky

The article is devoted to the study of the specifics of the receptive influence of the moral and psychological novel by F. Dostoevskys on the development of the Russian historiosophical novel of the XXth century. The relevance of the problem is in the identification of an ideological dominant connected with the key problems associated with the moral attitudes of Dostoevsky's novelistics. The novelty of this study lies in considering, taking into account new ideological assessments of the role and status of a historical person, a historical novel about the narodovoltsy of the 50-60s of the ХХth century. The novels about the narodovoltsy of the 50-60s of ХХth century were chosen as an object of research to reflect the ideological concept of F. Dostoevsky in the receptive field of the searches of the XXth century writers and as a determinant of the moral coordinates of modern phenomena of reality. It is proved that the development of the moral and psychological historical novel in the 60-70s takes place under the strongest influence of the tradition of F. Dostoevsky. The receptive correlation of the genre coordinate system, subjective organization, historiosophical ideologism of the XXth century with the traditions of the moral and psychological historiosophy of Dostoevskys contextual field, on the one hand, forms a new Tynyanov-Forsh tradition, and on the other, develops the traditions of the writer's polyphonic ideological novel on a new level and determines the expansion of the moral polyphonism of the historical novel in its value and psychoanalytic orientation, when the principle of internal ethics begins to dominate the ideological and political fields.

Generative Image Inpainting with Dilated Deformable Convolution

The image generation and completion model complement the missing area of the image to be repaired according to the image itself or the information of the image library so that the repaired image looks very natural and difficult to distinguish from the undamaged image. The difficulty of image generation and completion lies in the reasonableness of image semantics and the clear and true texture of the generated image. In this paper, a Wasserstein generative adversarial network with dilated convolution and deformable convolution (DDC-WGAN) is proposed for image completion. A deformable offset is added based on dilated convolution, which enlarges the receptive field and provides a more stable representation of geometric deformation. Experiments show that the DDC-WGAN method proposed in this paper has better performance in image generation and complementation than the traditional generative adversarial complementation network.

Changes in Receptive Field Size in Syngap1 +/- Mouse Model of Autism Spectrum Disorder

Background and Hypothesis: Autism spectrum disorder (ASD) is a form of intellectual disability with impairments in social functioning and cognition. Mutations within the SynGAP1 gene are associated with ASD due to over activation of RAS-GTP causing insertion of AMPA receptors onto the post synaptic membrane, and thus early maturation of dendrites. These mutations lead to an excitatory/inhibitory imbalance within the brain, and patients often present with intellectual disability, seizures, and issues of cognition. Research has shown that Syngap1 +/- mice have decreased cortical gray matter brain volume throughout areas involved in the visual system pathway. However, hierarchal visual processing has not been well characterized in a Syngap1 +/- mouse model of autism. Project Methods: Using 64 and 128 channel microelectrodes, we recorded the neural activity within V1 of four mice. Neural activity was recorded in response to visual stimuli - testing receptive field size between two wild-type and two Syngap1 +/- mice. Data was run through spike sorting algorithms to identify neurons. Receptive field area for each neuron was then calculated and compared between the two genotypes. Results: The receptive field areas of Syngap1 +/- mice were statistically larger (p < 0.01) compared to wild type mice. Syngap1 +/- mice had a mean receptive field area of 450.5 visual degrees (±443.7) and WT mice had a mean receptive field area of 261.1 visual degrees (±187.21). Most of the neurons within Syngap +/- had no distinct receptive field, 67.9%, while only 25.7% of wild type neurons lacked a distinct receptive field. Conclusion and Potential Impact: Overall, Syngap1 +/- mice had larger, and less distinct receptive fields compared to wild type mice. Deficiencies in the Syngap1 protein may impair refinement of visual stimuli. Understanding the mechanism of response of missing SynGAP1 can inform directed therapies and interventions to treat patients with the missing gene and manage their intellectual disability.