Early Diagnosis of Alzheimer’s Disease Using Cerebral Catheter Angiogram Neuroimaging: A Novel Model Based on Deep Learning Approaches

Neuroimaging refers to the techniques that provide efficient information about the neural structure of the human brain, which is utilized for diagnosis, treatment, and scientific research. The problem of classifying neuroimages is one of the most important steps that are needed by medical staff to diagnose their patients early by investigating the indicators of different neuroimaging types. Early diagnosis of Alzheimer’s disease is of great importance in preventing the deterioration of the patient’s situation. In this research, a novel approach was devised based on a digital subtracted angiogram scan that provides sufficient features of a new biomarker cerebral blood flow. The used dataset was acquired from the database of K.A.U.H hospital and contains digital subtracted angiograms of participants who were diagnosed with Alzheimer’s disease, besides samples of normal controls. Since each scan included multiple frames for the left and right ICA’s, pre-processing steps were applied to make the dataset prepared for the next stages of feature extraction and classification. The multiple frames of scans transformed from real space into DCT space and averaged to remove noises. Then, the averaged image was transformed back to the real space, and both sides filtered with Meijering and concatenated in a single image. The proposed model extracts the features using different pre-trained models: InceptionV3 and DenseNet201. Then, the PCA method was utilized to select the features with 0.99 explained variance ratio, where the combination of selected features from both pre-trained models is fed into machine learning classifiers. Overall, the obtained experimental results are at least as good as other state-of-the-art approaches in the literature and more efficient according to the recent medical standards with a 99.14% level of accuracy, considering the difference in dataset samples and the used cerebral blood flow biomarker.

Towards Language Sensitivity and Diversity in the Digital Humanities

English Recent years have seen a growing focus on diversity in the digital humanities, and yet there has been rather less work on geolinguistic diversity, and the research which has been carried out often focuses on the structures of geographic representation in the field or has viewed ‘language’ as a technical or linguistic problem to solve. This article takes a different view, namely that we need to consider this diversity through multiple ‘frames’ of digitally-mediated language and culture, and that this is not just a question of epistemic justice or community manners, but that the digital humanities also need to address more actively challenges around global dynamics of digital multilingualism, transcultural exchange and geodiversity in its research agenda. This paper explores these questions through the prism of ‘language indifference’ in digital studies and, responding to Galina’s call for better data on the state of geolinguistic diversity in DH (2014), it articulates possible frameworks for addressing this diversity in a strategic, programmatic and research-led manner. We conclude by exploring the role of a greater multilingual focus in what Liu calls ‘the techne of diversity’ in digital humanities (2020), and contend that the digital humanities has much to gain, and much to offer, in engaging more fully with the languages-related cultural challenges of our era. RésuméCes dernières années l’accent a été mis de plus en plus sur la diversité dans les sciences humaines numériques, et pourtant il y a plutôt eu moins de travaux sur la diversité geo linguistique, et les recherches qui ont été menées portent souvent sur les structures de la représentation géographique sur le terrain, ou estiment le ‘langage’ comme un problème technique ou linguistique à résoudre. Cet article adopte un point différent, à savoir que nous devons considérer cette diversité à travers plusieurs ‘cadres’ de culture et de language à médiation numérique, cela n’étant pas uniquement une question de justice ou de savoir-faire communautaire, mais que, dans son programme de recherches, les sciences humaines numériques doivent également relever plus activement les défis à la dynamique mondiale du multilinguisme numérique, aux échanges transculturels et à la geo diversité. Ce document explore ces questions à travers le prisme de ‘l’indifférence linguistique’ dans les études numériques et, en réponse à l’appel de Galina pour de meilleures données sur l’état de la diversité geo linguistique dans DH (2014), il définit des systèmes possibles pour faire face à cette diversité de manière stratégique, programmatique et axée sur la recherche. Nous en concluons qu’en explorant le rôle d’une meilleure focalisation sur le multilinguisme dans les humanités numériques de ce que Liu appelle ‘la tech de la diversité’ (2020) et nous soutenons que les sciences humaines numériques ont beaucoup à gagner en s’engageant pleinement dans les défis culturels liés aux langues de notre époque.Mots-clés: Humanités numériques multilingues, Diversité linguistique et culturelle, Langues modernes numériques, Indifférence linguistique, Perturber le monolinguisme numérique

Real-Time Analysis of Athletes’ Physical Condition in Training Based on Video Monitoring Technology of Optical Flow Equation

This article is dedicated to the research of video motion segmentation algorithms based on optical flow equations. First, some mainstream segmentation algorithms are studied, and on this basis, a segmentation algorithm for spectral clustering analysis of athletes’ physical condition in training is proposed. After that, through the analysis of the existing methods, compared with some algorithms that only process a single frame in the video, this article analyzes the continuous multiple frames in the video and extracts the continuous multiple frames of the sampling points through the Lucas-Kanade optical flow method. We densely sampled feature points contain as much motion information as possible in the video and then express this motion information through trajectory description and finally achieve segmentation of moving targets through clustering of motion trajectories. At the same time, the basic concepts of image segmentation and video motion target segmentation are described, and the division standards of different video motion segmentation algorithms and their respective advantages and disadvantages are analyzed. The experiment determines the initial template by comparing the gray-scale variance of the image, uses the characteristic optical flow to estimate the search area of the initial template in the next frame, reduces the matching time, judges the template similarity according to the Hausdorff distance, and uses the adaptive weighted template update method for the templates with large deviations. The simulation results show that the algorithm can achieve long-term stable tracking of moving targets in the mine, and it can also achieve continuous tracking of partially occluded moving targets.

Weakly Supervised Faster-RCNN+FPN to classify small animals in camera trap images

<div>Camera traps have revolutionized animal research of many species that were previously nearly impossible to observe due to their habitat or behavior.</div><div>Deep learning has the potential to overcome the workload to the class automatically those images according to taxon or empty images. However, a standard deep neural network classifier fails because animals often represent a small portion of the high-definition images. Therefore, we propose a workflow named Weakly Object Detection Faster-RCNN+FPN which suits this challenge. The model is weakly supervised because it requires only the animal taxon label per image but doesn't require any manual bounding box annotations. First, it automatically performs the weakly supervised bounding box annotation using the motion from multiple frames. Then, it trains a Faster-RCNN+FPN model using this weak supervision.<br></div><div>Experimental results have been obtained on two datasets and an easily reproducible testbed.</div>

Weakly Supervised Faster-RCNN+FPN to classify small animals in camera trap images

<div>Camera traps have revolutionized animal research of many species that were previously nearly impossible to observe due to their habitat or behavior.</div><div>Deep learning has the potential to overcome the workload to the class automatically those images according to taxon or empty images. However, a standard deep neural network classifier fails because animals often represent a small portion of the high-definition images. Therefore, we propose a workflow named Weakly Object Detection Faster-RCNN+FPN which suits this challenge. The model is weakly supervised because it requires only the animal taxon label per image but doesn't require any manual bounding box annotations. First, it automatically performs the weakly supervised bounding box annotation using the motion from multiple frames. Then, it trains a Faster-RCNN+FPN model using this weak supervision.<br></div><div>Experimental results have been obtained on two datasets and an easily reproducible testbed.</div>

Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes

For the success of video deblurring, it is essential to utilize information from neighboring frames. Most state-of-the-art video deblurring methods adopt motion compensation between video frames to aggregate information from multiple frames that can help deblur a target frame. However, the motion compensation methods adopted by previous deblurring methods are not blur-invariant, and consequently, their accuracy is limited for blurry frames with different blur amounts. To alleviate this problem, we propose two novel approaches to deblur videos by effectively aggregating information from multiple video frames. First, we present blur-invariant motion estimation learning to improve motion estimation accuracy between blurry frames. Second, for motion compensation, instead of aligning frames by warping with estimated motions, we use a pixel volume that contains candidate sharp pixels to resolve motion estimation errors. We combine these two processes to propose an effective recurrent video deblurring network that fully exploits deblurred previous frames. Experiments show that our method achieves the state-of-the-art performance both quantitatively and qualitatively compared to recent methods that use deep learning.

S2A: Scale-Attention-Aware Networks for Video Super-Resolution

Convolutional Neural Networks (CNNs) have been widely used in video super-resolution (VSR). Most existing VSR methods focus on how to utilize the information of multiple frames, while neglecting the feature correlations of the intermediate features, thus limiting the feature expression of the models. To address this problem, we propose a novel SAA network, that is, Scale-and-Attention-Aware Networks, to apply different attention to different temporal-length streams, while further exploring both spatial and channel attention on separate streams with a newly proposed Criss-Cross Channel Attention Module (C3AM). Experiments on public VSR datasets demonstrate the superiority of our method over other state-of-the-art methods in terms of both quantitative and qualitative metrics.

Merging familiar and new senses to perceive and act in space

Our experience of the world seems to unfold seamlessly in a unitary 3D space. For this to be possible, the brain has to merge many disparate cognitive representations and sensory inputs. How does it do so? I discuss work on two key combination problems: coordinating multiple frames of reference (e.g. egocentric and allocentric), and coordinating multiple sensory signals (e.g. visual and proprioceptive). I focus on two populations whose spatial processing we can observe at a crucial stage of being configured and optimised: children, whose spatial abilities are still developing significantly, and naïve adults learning new spatial skills, such as sensing distance using auditory cues. The work uses a model-based approach to compare participants’ behaviour with the predictions of alternative information processing models. This lets us see when and how—during development, and with experience—the perceptual-cognitive computations underpinning our experiences in space change. I discuss progress on understanding the limits of effective spatial computation for perception and action, and how lessons from the developing spatial cognitive system can inform approaches to augmenting human abilities with new sensory signals provided by technology.

Tracklet Proposal Network for Multi-Object Tracking on Point Clouds

This paper proposes the first tracklet proposal network, named PC-TCNN, for Multi-Object Tracking (MOT) on point clouds. Our pipeline first generates tracklet proposals, then refines these tracklets and associates them to generate long trajectories. Specifically, object proposal generation and motion regression are first performed on a point cloud sequence to generate tracklet candidates. Then, spatial-temporal features of each tracklet are exploited and their consistency is used to refine the tracklet proposal. Finally, the refined tracklets across multiple frames are associated to perform MOT on the point cloud sequence. The PC-TCNN significantly improves the MOT performance by introducing the tracklet proposal design. On the KITTI tracking benchmark, it attains an MOTA of 91.75%, outperforming all submitted results on the online leaderboard.