Explore the vast range of titles available.

We report the use of streaming data interfaces to perform fully online data processing for serial crystallography experiments, without storing intermediate data on disk. The system produces Bragg reflection intensity measurements suitable for scaling and merging, with a latency of less than 1 s per frame. Our system uses the CrystFEL software in combination with the ASAP::O data framework. In a series of user experiments at PETRA III, frames from a 16 megapixel Dectris EIGER2 X detector were searched for peaks, indexed and integrated at the maximum full-frame readout speed of 133 frames per second. The computational resources required depend on various factors, most significantly the fraction of non-blank frames (`hits'). The average single-thread processing time per frame was 242 ms for blank frames and 455 ms for hits, meaning that a single 96-core computing node was sufficient to keep up with the data, with ample headroom for unexpected throughput reductions. Further significant improvements are expected, for example by binning pixel intensities together to reduce the pixel count. We discuss the implications of real-time data processing on the `data deluge' problem from recent and future photon-science experiments, in particular on calibration requirements, computing access patterns and the need for the preservation of raw data.

This study presents a novel method for the automatic detection of debris flow motion and velocity measurement using deep learning and image processing techniques. An advanced convolutional neural network (CNN) model based on the You Only Look Once algorithm was employed to identify debris flow motion from videos recorded by a camera system. An image processing technique was also proposed to calculate the front velocity of the detected debris flow along a channel. The CNN model was trained and tested on an image dataset (named Debrisflow21) derived from 12 debris flow videos (5950 frames) that were obtained from small flume tests, large flume tests, and several debris flow events. The results showed that the debris flow detection model using CNN achieved an average precision (AP) of 96.37% and an average intersection over union of 84.80% on the test datasets. The application results of the proposed CNN model to five additional videos reached approximately 39 frames per second with an AP over 99.72%. In addition, the accuracy of the velocity calculation results tested on small flume and large flume experiment videos ranged between 87.1 and 97.3%. The proposed method exhibited high accuracy and fast processing speed; thus, it can be applied for early detection and warning systems.

Graphic Processing Units (GPUs) are becoming very important in the present day. Their high computational capabilities with high speed and accuracy are making them a very strong force in communication engineering. In recent times, their need has increased tremendously due to the increasing range of applications. Video surveillance is an important field where very heavy computations are needed to be done on videos to perfectly detect the motion of an object in suspicious situations. The various analyses on video can be used to extract information and process data to generate actionable intelligent conclusions. However, CPUs fail to deliver real time results when it comes to high-resolution videos from a large number of cameras simultaneously. Thankfully, there is a lot of graphic hardware available nowadays, which comprises powerful hardware processors often intended to process data in parallel and so greatly accelerates the processes being done on them. An accelerated algorithm is required for processing petabytes of data from security cameras and video surveillance satellites and that in real time. In this paper, we propose a method of using GPUs in detecting the motion of an object at different junctions in video surveillance. The results show a great gain in performance when the proposed method runs on GPUs and CPUs in terms of speed as well as accuracy. The new parallel processing approaches are developed on each phase of the algorithm to enhance the efficiency of the system. Proposed algorithm achieved an average speed up of 50.094x for lower resolution video frames (320 × 240,720 × 480,1024 × 768) and 38.012x for higher resolution video frames (1360 × 768,1920 × 1080) on GPU, which is superior to CPU processing.

The detection of video anomalies is a well-known issue in the realm of visual research. The volume of normal and abnormal sample data in this field is unbalanced, hence unsupervised training is generally used in research. Since the development of deep learning, the field of video anomaly has developed from reconstruction-based detection methods to prediction-based detection methods, and then to hybrid detection methods. To identify the presence of anomalies, these methods take advantage of the differences between ground-truth frames and reconstruction or prediction frames. Thus, the evaluation of the results is directly impacted by the quality of the generated frames. Built around the Dual Contrast Discriminator for Video Sequences (DCDVS) and the corresponding loss function, we present a novel hybrid detection method for further explanation. With less false positives and more accuracy, this method improves the discriminator’s guidance on the reconstruction-prediction network’s generation performance. we integrate optical flow processing and attention processes into the Auto-encoder (AE) reconstruction network. The network’s sensitivity to motion information and its ability to concentrate on important areas are improved by this integration. Additionally, DCDVS’s capacity to successfully recognize significant features gets improved by introducing the attention module implemented through parameter sharing. Aiming to reduce the risk of network overfitting, we also invented reverse augmentation, a data augmentation technique designed specifically for temporal data. Our approach achieved outstanding performance with AUC scores of 99.4, 92.9, and 77.3 % on the UCSD Ped2, CUHK Avenue, and ShanghaiTech datasets, respectively, demonstrates competitiveness with advanced methods and validates its effectiveness.

Dance style recognition through video analysis during university training can significantly benefit both instructors and novice dancers. Employing video analysis in training offers substantial advantages, including the potential to train future dancers using innovative technologies. Over time, intricate dance gestures can be honed, reducing the burden on instructors who would, otherwise, need to provide repetitive demonstrations. Recognizing dancers’ movements, evaluating and adjusting their gestures, and extracting cognitive functions for efficient evaluation and classification are pivotal aspects of our model. Deep learning currently stands as one of the most effective approaches for achieving these objectives, particularly with short video clips. However, limited research has focused on automated analysis of dance videos for training purposes and assisting instructors. In addition, assessing the quality and accuracy of performance video recordings presents a complex challenge, especially when judges cannot fully focus on the on‐stage performance. This paper proposes an alternative to manual evaluation through a video‐based approach for dance assessment. By utilizing short video clips, we conduct dance analysis employing techniques such as fine‐grained dance style classification in video frames, convolutional neural networks (CNNs) with channel attention mechanisms (CAMs), and autoencoders (AEs). These methods enable accurate evaluation and data gathering, leading to precise conclusions. Furthermore, utilizing cloud space for real‐time processing of video frames is essential for timely analysis of dance styles, enhancing the efficiency of information processing. Experimental results demonstrate the effectiveness of our evaluation method in terms of accuracy and F1‐score calculation, with accuracy exceeding 97.24% and the F1‐score reaching 97.30%. These findings corroborate the efficacy and precision of our approach in dance evaluation analysis.

Video Synthetic Aperture Radar (ViSAR) operating in spotlight mode has received widespread attention in recent years because of its ability to form a sequence of SAR images for a region of interest (ROI). However, due to the heavy computational burden of data processing, the application of ViSAR is limited in practice. Although back projection (BP) can avoid unnecessary repetitive processing of overlapping parts between consecutive video frames, it is still time-consuming for high-resolution video-SAR data processing. In this article, in order to achieve the same or a similar effect to BP and reduce the computational burden as much as possible, a novel time-frequency sub-aperture technology (TFST) is proposed. Firstly, based on azimuth resampling and full aperture azimuth scaling, a time domain sub-aperture (TDS) processing algorithm is proposed to process ViSAR data with large coherent integration angles to ensure the continuity of ViSAR monitoring. Furthermore, through frequency domain sub-aperture (FDS) processing, multiple high-resolution video frames can be generated efficiently without sub-aperture reconstruction. In addition, TFST is based on the range migration algorithm (RMA), which can take into account the accuracy while ensuring efficiency. The results of simulation and X-band airborne SAR experimental data verify the effectiveness of the proposed method.

Building damage due to earthquake shocks causes affected victims to potentially lose their homes so that temporary housing is needed. Therefore, strengthening of buildings using bracing is needed to support building resistance to lateral loads in earthquake areas. Bracing can be divided into two types, namely concentric and eccentric. Eccentric braces have links that will form inelastic rotation when yielding occurs due to deformation that occurs in the structure so that they are considered effective in absorbing lateral loads. EBF (eccentric braced frames) have better stiffness when compared to MRF (moment resisting frames) but are able to provide better ductility behavior compared to CBF (concentric braced frames). The purpose of this experimental study was to determine the performance of variations in EBF split-k cold-formed steel wall panel links against lateral loads. The aspects reviewed are maximum load, maximum deviation, and stiffness. The flow of this research is the manufacture, testing of test objects, and data processing. In this study, the following results were obtained: the short link variation obtained the largest maximum load result with 134.62 kg, the smallest maximum deviation of 30.472 mm, and the largest stiffness with 18.363 kg/mm.

PurposeDespite the growing interest in AI, the scientific literature lacks multinational studies that examine how mainstream media depict AI applications. This paper is one of the first empirical studies to explore how French and English-speaking mainstream media portray AI during a pandemic. The purpose of this study is to examine how media define AI and how they frame this technology.Design/methodology/approachThe authors selected five media outlets and extracted all news articles that mentioned AI over a period of 30 days. The authors constituted the sample to ensure a mix of global, national and local media newspapers. The authors included Le Temps (Switzerland), Le Monde (France), The Guardian (United Kingdom), Politico Europe (Europe) and the New York Times (USA). The authors used the NexisUni database to collect the news articles. This resulted in a sample of 54 articles, which the authors then refined to 35 articles mentioning at the same AI and COVID-19. They then manually coded to identify media frames about AI.FindingsAlthough no news article provides a definition of AI, most articles highlight two main characteristics: information processing and adaptability. This paper also shows that the coverage of AI in US newspaper is more optimistic than pessimistic. European newspapers offer a more balanced perspective of the risks and benefits associated with the technology, and highlight its use mainly in the context of the COVID-19. Media framing changes according to the evolution of the pandemic. While the USA were not yet heavily affected by the virus, Europe experienced the peak of the crisis. The authors argue that the framing of AI follows that of the pandemic.Research limitations/implicationsThis study is limited in terms of timeframe (30 days) and media outlets (5). It would be useful to extend this sample to verify the results, and also conduct interviews among journalists to understand their motivations and understanding of AI.Originality/valueDespite the growing interest in AI, the scientific literature lacks multinational studies that examine how mainstream media depict AI applications in society. This paper is one of the first empirical studies to explore how French and English-speaking mainstream media portray AI during a pandemic.Peer reviewThe peer review history for this article is available at: https://publons.com/publon/10.1108/OIR-09-2020-0393

Background Generalized Joint Hyper-mobility (GJH) can aid in the diagnosis of Ehlers-Danlos Syndrome (EDS), a complex genetic connective tissue disorder with clinical features that can mimic other disease processes. Our study focuses on developing a unique image-based goniometry system, the HybridPoseNet, which utilizes a hybrid deep learning model. Objective The proposed model is designed to provide the most accurate joint angle measurements in EDS appraisals. Using a hybrid of CNNs and HyperLSTMs in the pose estimation module of HybridPoseNet offers superior generalization and time consistency properties, setting it apart from existing complex libraries. Methodology HybridPoseNet integrates the spatial pattern recognition prowess of MobileNet-V2 with the sequential data processing capability of HyperLSTM units. The system captures the dynamic nature of joint motion by creating a model that learns from individual frames and the sequence of movements. The CNN module of HybridPoseNet was trained on a large and diverse data set before the fine-tuning of video data involving 50 individuals visiting the EDS clinic, focusing on joints that can hyperextend. HyperLSTMs have been incorporated in video frames to avoid any time breakage in joint angle estimation in consecutive frames. The model performance was evaluated using Spearman’s coefficient correlation versus manual goniometry measurements, as well as by the human labeling of joint position, the second validation step. Outcome Preliminary findings demonstrate HybridPoseNet achieving a remarkable correlation with manual Goniometric measurements: thumb (rho = 0.847), elbows (rho = 0.822), knees (rho = 0.839), and fifth fingers (rho = 0.896), indicating that the newest model is considerably better. The model manifested a consistent performance in all joint assessments, hence not requiring selecting a variety of pose-measuring libraries for every joint. The presentation of HybridPoseNet contributes to achieving a combined and normalized approach to reviewing the mobility of joints, which has an overall enhancement of approximately 20% in accuracy compared to the regular pose estimation libraries. This innovation is very valuable to the field of medical diagnostics of connective tissue diseases and a vast improvement to its understanding.

Sign languages (SL) are the natural languages used by Deaf communities to communicate with each other. Signers use visible parts of their bodies, like their hands, to convey messages without sound. Because of this modality change, SLs have to be represented differently in natural language processing (NLP) tasks: Inputs are regularly presented as video data rather than text or sound, which makes even simple tasks computationally intensive. Moreover, the applicability of NLP techniques to SL processing is limited by their linguistic characteristics. For instance, current research in SL recognition has centered around lexical sign identification. However, SLs tend to exhibit lower vocabulary sizes than vocal languages, as signers codify part of their message through highly iconic signs that are not lexicalized. Thus, a lot of potentially relevant information is lost to most NLP algorithms. Furthermore, most documented SL corpora contain less than a hundred video hours; far from enough to train most non-symbolic NLP approaches. This article proposes a method to achieve unsupervised identification of phonetic units in SL videos, based on Image Thresholding using The Liddell and Johnson Movement-Hold Model [13]. The procedure strives to identify the smallest possible linguistic units that may carry relevant information. This is an effort to avoid losing sub-lexical data that would be otherwise missed to most NLP algorithms. Furthermore, the process enables the elimination of noisy or redundant video frames from the input, decreasing the overall computation costs. The algorithm was tested in a collection of Mexican Sign Language videos. The relevance of the extracted segments was assessed by way of human judges. Further comparisons were carried against French Sign Language resources (LSF), so as to explore how well the algorithm performs across different SLs. The results show that the frames selected by the algorithm contained enough information to remain comprehensible to human signers. In some cases, as much as 80% of the available frames could be discarded without loss of comprehensibility, which may have direct repercussions on how SLs are represented, transmitted and processed electronically in the future.