A Study of Spatial Attention and Squeeze Excitation Block Fusion Improved ResNet for Identifying Bank Notes

Based on deep learning and digital image processing algorithms, we design and implement an accurate automatic recognition system for bank note text and propose an improved recognition method based on ResNet for the problems of difficult image text extraction and insufficient recognition accuracy. Firstly, a deep hyperparameterized convolution (DO-Conv) is used instead of the traditional convolution in the network to improve the recognition rate while reducing the model parameters. Then, the spatial attention model (SAM) and the squeezed excitation block (SE-Block) are fused and applied to a modified ResNet to extract detailed features of bank note images in the channel and spatial domains. Finally, the label-smoothed cross-entropy (LSCE) loss function is used to train the model to automatically calibrate the network to prevent classification errors. The experimental results demonstrate that the improved model is not easily affected by the image quality, and the model in this paper has good performance in text detection and recognition in specific business ticket scenarios.

Domain Specific Lateralization of the Frontal Processes Informing Inhibition: A TMS Study

<p>Response inhibition is the suppression of actions that are inappropriate given some wider context or goal, a capacity that is vital for everyday functioning. In this thesis the theoretical backdrop of executive functioning is discussed, before exploring current research into response inhibition and its neural underpinnings. A theory by Mostofsky and Simmonds (2008) holds that when the decision to inhibit a behavior is a complex one, task dependent parts of an inhibitory network in the prefrontal cortex are utilized. The current thesis argues on the basis of observed biases in the literature, for the possibility that this task dependent engagement features domain specific lateralization. In order to investigate this, a transcranial magnetic stimulation [TMS] experiment is then presented where four go/no-go tasks, spread across language and spatial domains in complex and simple forms, are performed following TMS. Stimulation sites include the right posterior inferior frontal gyrus, the left posterior inferior frontal gyrus, and sham stimulation. Results are then discussed, however implications are limited, likely due to low statistical power.</p>

Domain Specific Lateralization of the Frontal Processes Informing Inhibition: A TMS Study

<p>Response inhibition is the suppression of actions that are inappropriate given some wider context or goal, a capacity that is vital for everyday functioning. In this thesis the theoretical backdrop of executive functioning is discussed, before exploring current research into response inhibition and its neural underpinnings. A theory by Mostofsky and Simmonds (2008) holds that when the decision to inhibit a behavior is a complex one, task dependent parts of an inhibitory network in the prefrontal cortex are utilized. The current thesis argues on the basis of observed biases in the literature, for the possibility that this task dependent engagement features domain specific lateralization. In order to investigate this, a transcranial magnetic stimulation [TMS] experiment is then presented where four go/no-go tasks, spread across language and spatial domains in complex and simple forms, are performed following TMS. Stimulation sites include the right posterior inferior frontal gyrus, the left posterior inferior frontal gyrus, and sham stimulation. Results are then discussed, however implications are limited, likely due to low statistical power.</p>

Spatial Statistical Models: An Overview under the Bayesian Approach

Spatial documentation is exponentially increasing given the availability of Big Data in the Internet of Things, enabled by device miniaturization and data storage capacity. Bayesian spatial statistics is a useful statistical tool to determine the dependence structure and hidden patterns in space through prior knowledge and data likelihood. However, this class of modeling is not yet well explored when compared to adopting classification and regression in machine-learning models, in which the assumption of the spatiotemporal independence of the data is often made, that is an inexistent or very weak dependence. Thus, this systematic review aims to address the main models presented in the literature over the past 20 years, identifying the gaps and research opportunities. Elements such as random fields, spatial domains, prior specification, the covariance function, and numerical approximations are discussed. This work explores the two subclasses of spatial smoothing: global and local.

3D convolutional neural networks-based multiclass classification of Alzheimer’s and Parkinson’s diseases using PET and SPECT neuroimaging modalities

Background Alzheimer’s disease (AD) is a neurodegenerative brain pathology formed due to piling up of amyloid proteins, development of plaques and disappearance of neurons. Another common subtype of dementia like AD, Parkinson’s disease (PD) is determined by the disappearance of dopaminergic neurons in the region known as substantia nigra pars compacta located in the midbrain. Both AD and PD target aged population worldwide forming a major chunk of healthcare costs. Hence, there is a need for methods that help in the early diagnosis of these diseases. PD subjects especially those who have confirmed postmortem plaque are a strong candidate for a second AD diagnosis. Modalities such as positron emission tomography (PET) and single photon emission computed tomography (SPECT) can be combined with deep learning methods to diagnose these two diseases for the benefit of clinicians. Result In this work, we deployed a 3D Convolutional Neural Network (CNN) to extract features for multiclass classification of both AD and PD in the frequency and spatial domains using PET and SPECT neuroimaging modalities to differentiate between AD, PD and Normal Control (NC) classes. Discrete Cosine Transform has been deployed as a frequency domain learning method along with random weak Gaussian blurring and random zooming in/out augmentation methods in both frequency and spatial domains. To select the hyperparameters of the 3D-CNN model, we deployed both 5- and 10-fold cross-validation (CV) approaches. The best performing model was found to be AD/NC(SPECT)/PD classification with random weak Gaussian blurred augmentation in the spatial domain using fivefold CV approach while the worst performing model happens to be AD/NC(PET)/PD classification without augmentation in the frequency domain using tenfold CV approach. We also found that spatial domain methods tend to perform better than their frequency domain counterparts. Conclusion The proposed model provides a good performance in discriminating AD and PD subjects due to minimal correlation between these two dementia types on the clinicopathological continuum between AD and PD subjects from a neuroimaging perspective.

Medical Image Watermarking for Telemedicine Application Security

In this work, we proposed a robust and blind watermarking approach to adequately secure medical images exchanged in telemedicine. This approach ensures the traceability and integrity of the medical and essential image for data security in the field of telemedicine. In this paper, a blind watermarking method is proposed to adequately secure the electronic patient records. The integration of the watermark will be carefully performed by combining the parity of the successive values. This innovative approach will be typically implemented in the three insertion domains: spatial, frequency and multi-resolution. For the spatial domain, the watermark will be integrated into the colorimetric values of the image. In the frequency domain, the watermark bits will be substituted to the DCT coefficient’s least significant bit. For the multi-resolution domain insertion, after calculating a DWT, the obtained LL sub-band coefficients will be used for the integration process. After comparing our approaches to the various recent works in the three domains, the obtained results demonstrate that our proposed approach offers a good imperceptibility for the frequency and spatial domains insertion.

The thickness of the ventral medial prefrontal cortex (vmPFC) predicts the self-prioritization effect (SPE) on the interaction between spatial reference frames and spatial domains

Neuropsychological studies have demonstrated that the preferential processing of near-space and egocentric representation is associated with the self-prioritization effect (SPE). However, relatively little is known concerning whether the SPE is superior to the representation of egocentric frames or near-space processing in the interaction between spatial reference frames and spatial domains. The present study adopted the variant of the shape-label matching task (i.e., color-label) to establish an SPE, combined with a spatial reference frame judgment task, to examine how the SPE leads to preferential processing of near-space or egocentric representations. Surface-based morphometry analysis was also adopted to extract the cortical thickness of the ventral medial prefrontal cortex (vmPFC) to examine whether it could predict differences in the SPE at the behavioral level. The results showed a significant SPE, manifested as the response of self-associated color being faster than that of stranger-associated color. Additionally, the SPE showed a preference for near-space processing, followed by egocentric representation. More importantly, the thickness of the vmPFC could predict the difference in the SPE on reference frames, particularly in the left frontal pole cortex and bilateral rostral anterior cingulate cortex. These findings indicated that the SPE showed a prior entry effect for information at the spatial level relative to the reference frame level, providing evidence to support the structural significance of the self-processing region. The present study also further clarified the priority in SPE processing and role of the SPE within the real spatial domain.