Frame Information Research Articles

Identification of core therapeutic targets for Monkeypox virus and repurposing potential of drugs: A WEB prediction approach.

A new round of monkeypox virus has emerged in the United Kingdom since July 2022 and rapidly swept the world. Currently, despite numerous research groups are studying this virus and seeking effective treatments, the information on the open reading frame, inhibitors, and potential targets of monkeypox has not been updated in time, and the comprehension of monkeypox target ligand interactions remains a key challenge. Here, we first summarized and improved the open reading frame information of monkeypox, constructed the monkeypox inhibitor library and potential targets library by database research as well as literature search, combined with advanced protein modeling technologies (Sequence-based and AI algorithms-based homology modeling). In addition, we build monkeypox virus Docking Server, a web server to predict the binding mode between targets and substrate. The open reading frame information, monkeypox inhibitor library, and monkeypox potential targets library are used as the initial files for server docking, providing free interactive tools for predicting ligand interactions of monkeypox targets, potential drug screening, and potential targets search. In addition, the update of the three databases can also effectively promote the study of monkeypox drug inhibition mechanism and provide theoretical guidance for the development of drugs for monkeypox.

R-ATCN: continuous human activity recognition using FMCW radar with temporal convolutional networks

Abstract The utilization of millimeter-wave radar sensors for continuous human activity recognition technology has garnered significant interest. Prior research predominantly concentrated on recursive neural networks, which often incorporate numerous extraneous information features, hindering the ability to make precise and effective predictions for ongoing activities. In response to this challenge, this paper introduces a dual-dilated one-dimensional temporal convolutional network model with an attention mechanism (R-ATCN). By stacking temporal convolutions to enhance the receptive field without compromising temporal resolution, the R-ATCN effectively captures features. Additionally, the attention mechanism is employed to capture crucial frame information related to activity transitions and overall features. The study gathered 60 data sets from 5 participants utilizing frequency modulated continuous wave radar. It encompassed 8 various activities lasting a total of 52.5 min, with randomized durations and transition times for each activity. To evaluate the performance of the model, this paper also introduces evaluation metrics such as short-time tolerance (STT) score. Experimental results show that the R-ATCN model outperforms other contrastive models in terms of segmental F1-score and STT scores. The effectiveness of the proposed model lies in its ability to accurately identify ongoing human activities within indoor environments.

Information Framing Effects on Diet Choices Among Chinese Urban Residents

Information Framing Effects on Diet Choices Among Chinese Urban Residents

Multimodal Information Fusion Dynamic Target Recognition for Autonomous Driving

With the continuous development of autonomous driving technology, realizing high-precision road obstacle detection is crucial to ensure traffic safety and driving experience. However, traditional obstacle detection methods often perform poorly in complex driving scenarios, such as obstacle movement and occlusion. To cope with this problem, this study proposes a road obstacle detection method based on a two-stream convolutional neural network model, aiming to overcome the limitations of traditional methods in capturing spatiotemporal features and handling complex situations. Our research approach is based on the following innovations: First, we introduce a dual-stream convolutional neural network structure, where one stream is used to extract spatial features from the contour information of the obstacle frames, and the other stream extracts temporal features from the temporal stream information. This dual-stream structure can fully capture the appearance and dynamic information of the obstacles, thus improving detection accuracy. Second, we design a feature fusion module to fuse the two features to obtain richer obstacle features. In addition, we propose a new loss function, i.e. clustering loss, for better optimizing the model training process, reducing intra-class variation, and increasing inter-class differences, thus improving the generalization performance of the model. In the experimental section, we conducted extensive experimental analysis using Citycapes and BDD100K datasets. The experimental results show that our model achieves significant performance improvement compared to both the traditional convolutional neural network method and the YOLOv5 method in a variety of scenarios such as obstacle stationary, obstacle moving, and obstacle with occlusion. Specifically, our method improves the recognition rate up to 4.8% to 14.5% on the Citycapes dataset and 6.5% to 12.8% on the BDD100K dataset, respectively, under different scenarios. In addition, our model also exhibits more advantages on small datasets, showing higher generalization ability and robustness.

Vaccine equity implementation: exploring factors influencing COVID-19 vaccine delivery in the Philippines from an equity lens

BackgroundDuring the early phase of the COVID-19 vaccine rollout, low and middle-income countries (LMICs) were facing challenges in achieving equitable vaccine delivery. Few studies have contextualized global vaccine distributive injustice into national-specific contexts to understand its impact on vaccine delivery from an equity perspective. We aimed to investigate factors influencing equitable COVID-19 vaccine delivery in the Philippines and to provide recommendations to enhance equitable vaccine delivery in LMICs to prepare for future health emergencies.MethodsThe Health Equity Implementation Framework was employed to guide this qualitative study. We recruited participants using purposeful and snowballing sampling strategies. Semi-structured interviews were conducted with participants in person, online, or over the phone. A reflective thematic analysis approach was employed to analyze data.ResultsWe recruited 38 participants including seven high-level stakeholders from the public and private sectors, 14 health workers, and 17 community members in the province of Negros Occidental, Philippines. Equitable delivery of COVID-19 vaccines was influenced by an interplay of multiple factors operating in different domains. Contextually, the rapidly evolving nature of the COVID-19 virus, ongoing scientific advancements, and international negotiations directed national-level vaccine policies. Political commitment and support were recognized as crucial drivers for successful vaccine delivery, with a strong emphasis on health information framing and communication and adherence to human rights principles. The vulnerability of the health system significantly impacted the timely and effective distribution of vaccines. Furthermore, the geographical characteristics of the Philippines presented unique logistical challenges to vaccine delivery. At the recipient domain, individual perceptions of vaccines, shaped by their socioeconomic status, exposure to (mis)information, social influence, and entrenched religious beliefs, played a major role in their vaccine decisions and thus vaccine coverage regionally. Additionally, vaccine characteristics and operational challenges related to its distribution also impacted fair allocation.ConclusionsThe findings highlight the urgent need for LMICs to strengthen their health system resilience and sustainability and use multilevel strategies to build public trust to improve vaccine uptake and coverage. Moreover, each LMIC must be attentive to its unique contextual factors to develop tailored implementation strategies to promote equitable vaccine distribution.

An effective Key Frame Extraction technique based on Feature Fusion and Fuzzy-C means clustering with Artificial Hummingbird

Key frame extraction is very important in video summarization and content-based video analysis to address the problem of data redundancy in a video. Key frame extraction enables quick navigation and expert video arrangement in many applications. The visually impaired can benefit from the use of key frame extraction for rapid object recognition and tracking. Most key frame extraction techniques consider only a single visual feature instead of multiple features or full pictorial information of the video. This study proposes a key frame extraction method from a video that (i) first removes insignificant frames by pre-processing, (ii) second, four visual and structural feature differences among the consecutive frames are extracted and aggregated to identify informative frames, (iii) third, to cluster the obtained frames, a hybrid FCM-AHA method is proposed by combining Fuzzy C-means(FCM) with artificial hummingbird optimization algorithm (AHA) to circumvent the local minima trapping problem of FCM, and finally, from each cluster, the two frames having greatest Euclidean distance from all the other frames within a cluster is selected as key frames to remove redundant frames. Experimental results on the Open video and YouTube datasets show that the suggested method outperforms state-of-the-art methods both in terms of subjective qualitative analysis and objective quantitative evaluation, e.g., Precision, Recall, and F-score. Further, results are also taken on real video to demonstrate its applicability in real-life applications.

Does health anxiety and vaccine concern predict self-reported adverse events following COVID-19 vaccination?–A Danish national cohort study

ObjectivesThe nocebo effect refers to an expectation of sickness that leads to sickness in the expectant. Studies have found COVID-19 vaccines to be associated with the nocebo effect. However, the literature in this field is sparse yet important with the continuation of booster vaccines. Study designNational cohort study. MethodsThis study used data from the Danish national cohort “BiCoVac”, which contains self-reported information on both health anxiety and specific COVID-19 vaccine concern, as well as 19 systemic AEs following COVID-19 vaccination. Simple and multiple logistic regression was used to estimate the association between health anxiety and specific COVID-19 vaccine concern with having one or more systemic AEs following COVID-19 vaccination. Inverse probability weights were used to compensate for the initial dropout and loss to follow-up. ResultsOf the 85,080 participants in the study, 4 % reported health anxiety, 30 % reported specific COVID-19 vaccine concern, and 26 % one or more systemic AEs following vaccination. After adjusting for covariates, participants with health anxiety had higher odds of reporting one or more systemic AEs following vaccination compared to those without (OR, 1·21 CI 95 % [1·10; 1·33]). For specific COVID-19 vaccine concern, the OR was 1·51 CI 95 % [1·45; 1·58]. ConclusionsParticipants with specific COVID-19 vaccine concern had higher odds of reporting one or more systemic AEs following vaccination compared with those who had no specific COVID-19 vaccine concern. There might be a potential to reduce AEs, with positive framing of AEs and information about nocebo. Reporting of AEs was also associated with health anxiety, but to a lesser degree.

Promoting Upcycled Food: An analysis of social media communication strategies of Upcycled Food Association

Global food loss and waste are significant challenges in the food system, critical to addressing food insecurity and national security in the U.S. Upcycled food, which reduces waste at the source, is a promising solution. Social media offers both opportunities and challenges for communicating food benefits. This study examines publicly available data from Instagram, Facebook, and Twitter of a non-profit organization Upcycled Food Association (UFA) using content analysis and machine learning techniques. The analysis revealed that social media posts focused on promoting food waste awareness and benefits related to sustainability, health, and the economy, with environmental information being prioritized. UFA employs diverse impact information frames and uses positive emotion framing to increase food waste awareness and empower consumers by highlighting the impact of their purchasing power. Communication strategies are tailored to the unique characteristics of each social media platform and its users. We recommend social media initiatives continue emphasizing food waste awareness and upcycling, alongside increasing health information to encourage upcycled food consumption. Diverse strategies with diverse benefits and tailored to each platform's characteristics and sociodemographic groups are recommended. Future research can explore efficient topic modeling methods in larger datasets in social media analysis.

Blockchain for video watermarking: An enhanced copyright protection approach for video forensics based on perceptual hash function.

As a direct result of advancements in digital technology and the Internet, the copyright protection and information integrity of multimedia that are being published across the Internet have emerged as a major and urgent issue that needs to be addressed. The technique of digital watermarking may be used to protect intellectual property. In terms of authentication, resilience, storage, and capacity of digital watermarking information, there is still room for development. Blockchain's potential in video copyright protection and management applications has motivated researchers. Copyright owners and consumers may now communicate directly via copyright protection apps built on the blockchain, eliminating the need for distributers and the associated fees. Nonetheless, the current blockchain-based video watermarking solutions require storing a significant number of coordinates depending on the watermark size and are susceptible to video frame attacks on the video frame texture region. This study proposes an enhanced video copyright management approach that incorporates digital watermarking, the blockchain, and a perceptual hash function. Watermark information is stored on a blockchain structure, which also acts as a timestamp for verification purposes. To verify watermark data without the source video, a perceptual hash function is employed to compute a hash value based on the structural information of video frames. The contribution is in learning how to extract a hash function from a small number of video frames that still adequately represent a large amount of video content while also reducing the number of unnecessary video frames and the amount of computation required to summarize and index that content in a blockchain. This expedites the dissemination of copyrighted works and increases their security and readability, hence facilitating their circulation on the Internet. Our experimental results demonstrate that this approach is memory efficient, as it only needs to store one key for each key frame, regardless of the size of the watermark. Additionally, the overall robustness is greatly improved by using the blockchain's random hash function. Therefore, new and important advancements in video watermarking have been realized because of this effort.

Search region updating with hierarchical feature fusion for accurate thermal infrared tracking

Due to their resilience against lighting variations, thermal infrared (TIR) images demonstrate robust adaptability in diverse environments, enabling effective object tracking even in intricate scenarios. Nevertheless, TIR target tracking encounters challenges such as fast target motion and interference from visually similar objects, substantially compromising the tracking precision of TIR trackers. To surmount these challenges, we propose a method grounded in the strategy of search region updating and hierarchical feature fusion, tailored for the precise TIR target-tracking task. Specifically, to address the issue of fast motion causing the target to depart from the search region, we propose to update the current search region by leveraging historical frame information. Additionally, we employ a hierarchical feature fusion strategy to contend with interference from visually similar objects in the tracking scenario. This strategy enhances the ability to model and represent the target more accurately, thereby elevating the tracker’s capacity to discriminate between the target and similar objects. Furthermore, to tackle the challenge of inaccurate estimation of target bounding boxes, we introduce an enhanced Intersection over Union (IoU) loss function, which improvement facilitates a more precise prediction of target bounding boxes, resulting in superior target localization. Extensive experiments substantiate that our tracker exhibits a commendable level of competitiveness when compared to other trackers.

Railway foreign object tracking and detection with spatial positioning and feature generalization enhancement

The existing deep learning foreign object tracking and detection algorithm is easily affected by complex environments and target occlusion, resulting in problems such as missed detection and low detection accuracy. A railway foreign object tracking and detection algorithm with spatial positioning and feature generalization enhancement is proposed. First, a multi-scale cascade improved GhostNet feature network is proposed to improve the feature extraction capability of infrared targets. Secondly, the spatial positioning and feature generalization enhancement module is designed by using the spatial position positioning and generalized morphological information of foreign objects to enhance the detection accuracy of targets with position movement and tracking trajectory changesin complex scenes. Then, a pyramid prediction network is constructed to obtain the detection anchor frame, type and confidence information of infrared railway foreign objects. Finally, by improving the DeepSORT tracking algorithm with improved category and confidence display, combined with Kalman filtering and Hungarian algorithm, railway foreign object tracking and detection in infrared weak light environment is realized. Experimental results show that the proposed method has a tracking and detection accuracy of railway foreign objects 83.3%, with an average detection rate of 11.3 frames per second. Compared with the comparison method, the proposed method has higher detection accuracy and has better performance in railway foreign object tracking and detection in infrared weak light scenes.

The influence of message frame and product type on green consumer purchase decisions : an ERPs study

Green consumption is a crucial pathway towards achieving global sustainability goals. Product-oriented green advertisements can effectively stimulate consumers’ latent needs and convert them into eventual purchasing intentions and behaviors, thereby promoting green consumption. Given that neuromarketing methods facilitate the understanding of consumers’ decision-making processes, this study combines prospect theory and need fulfillment theory, employing event-related potentials (ERPs) as measures to explore changes in consumers’ cognitive resources and emotional arousal levels when confronted with green products and advertising information. This enables inference regarding consumers’ acceptance of purchasing and their psychological processes. Behavioral results indicated that message framing influences consumers’ purchases, with consumers consuming more green in response to negatively framed advertisements. EEG results indicated that matching positive framing with utilitarian green products was effective in increasing consumers’ cognitive attention in the early cognitive stage. In the late stage of cognition negative frames stimulated consumers’ mood swings more, and the influence of product type depended on the role of message frames, and the consumption motivation induced by the product, whose influence was overridden by external evaluations such as message frames. These research findings provide an explanation for the impact of frame information on consumers’ purchasing decisions at different stages, assisting marketers in devising diverse promotional strategies based on product characteristics to foster the development and practice of green consumption. This will further embed the concept of green consumption advocated by organizations such as the United Nations Environment Programme (UNEP), World Wildlife Fund (WWF), and Greenpeace into the public consciousness.

Parallel Implementation of the CCSDS Turbo Decoder on GPU

This paper presents a software turbo decoder on graphics processing units (GPU). Unlike previous works, the proposed decoding architecture for turbo codes mainly focuses on the Consultative Committee for Space Data Systems (CCSDS) standard. However, the information frame lengths of the CCSDS turbo codes are not suitable for flexible sub-frame parallelism design. To mitigate this issue, we propose a padding method that inserts several bits before the information frame header. To obtain low-latency performance and high resource utilization, two-level intra-frame parallelisms and an efficient data structure are considered. The presented Max-Log-Map decoder can be adopted to decode the Long Term Evolution (LTE) turbo codes with only small modifications. The proposed CCSDS turbo decoder at 10 iterations on NVIDIA RTX3070 achieves about 150 Mbps and 50 Mbps throughputs for the code rates 1/6 and 1/2, respectively.

Dark patterns, dark nudges, sludge and misinformation: alcohol industry apps and digital tools.

Many alcohol-industry-funded (AIF) organizations disseminate eHealth/mHealth tools that claim to assist users in making health decisions by monitoring alcohol consumption, e.g. blood alcohol calculators, AUDIT scores, consumption trackers. Previously, AIF materials were found to contain health misinformation that could increase consumption (dark nudges) or make healthy behaviour change more difficult (sludge). The accuracy and functionality of AIF tools have never been analysed, and given the history of AIF materials it is possible they contain misinformation and function as covert marketing channels to promote alcohol-industry-friendly narratives on the causes and possible solutions of alcohol-related harms. We evaluated the information accuracy and framing, behaviour change techniques (BCTs), and functions of AIF digital tools (n = 15, from the UK, Ireland, the USA, Canada, New Zealand, Australia; including Drinkaware, Drinkwise, Educ'alcool and others), compared to a non-industry-funded independent sample (n = 10). We identified misinformation and 'dark patterns' (interface design strategies for influencing users against their interest) throughout AIF tools; significantly fewer provided accurate feedback (33% vs 100%), and significantly more omitted information on cancer (67% vs 10%) and cardiovascular disease (80% vs 30%) and promoted industry-friendly narratives (47% vs 0%). AIF tools encouraged consumption through priming nudges (53%) and social norming (40%). AIF tools utilized fewer BCTs, provided users with more limited pre-set options (54%), and fewer drink choices (mean 24 vs 275). Their input structure often impeded their ability to provide guideline advice. We conclude that AIF tools contain pro-industry misinformation strategies and dark patterns that misinform users about their consumption and could 'nudge' them towards continuing to drink alcohol-characteristics of 'Dark Apps' designs.

Enhancing street-level bureaucrats ’compliance with policies challenging traditional customs through information frameworks: an experimental study in China

ABSTRACT Street-level bureaucrats face serious policy compliance challenges when implementing ‘policies that run counter to traditional custom’. How can the compliance of street-level bureaucrats with such policies be enhanced? To answer this question, based on the policy context of a fireworks display ban, this paper examines the policy compliance behavioural tendencies of street-level bureaucrats under informational frames using a 2(emotional vs. logical) * 2 (gain vs. loss) experimental approach. It was found that different information frames differentially affect the policy compliance. Emotion-based information frames are more effective in strengthening street-level bureaucrats’ policy compliance than logic-based narrative frames. Emphasizing losses is more effective in enhancing street-level bureaucrats’ policy compliance than emphasizing gains. The attitude of street bureaucrats to policy plays a partly mediating role. This study provides insight into the street-level bureaucrats’ policy compliance tendencies in implementing policies that are contrary to traditional custom, emphasizing the important role of information presentation mode in policy propaganda and mobilization in intervening in the policy compliance behaviour of street-level bureaucrats.

Combining optical flow and Swin Transformer for Space-Time video super-resolution

Space–time video super-resolution is a task that aims to interpolate low frame rate, low resolution videos to high frame rate, high resolution ones. While existing Transformer-based methods have achieved results comparable to convolutional neural networks-based methods, the computational cost of Transformer limits its performance with constrained computational resources. Moreover, Swin Transformer may fail to fully exploit the spatio-temporal information of video frames due to the limitation of window size, impeding its effectiveness in handling large motions. To address these limitations, we propose an end-to-end space–time video super-resolution architecture based on optical flow alignment and Swin Transformer. The alignment module is introduced to extract spatio-temporal information from adjacent frames without significantly increasing the computational burden. Additionally, we design a residual convolution layer to enhance the translational invariance of the features extracted by Swin Transformer and introduces additional nonlinear transformations. Experimental results demonstrate that our proposed method achieves superior performance on various benchmark datasets compared to state-of-the-art methods. In terms of Peak Signal-to-Noise Ratio, our method outperforms the state-of-the-art methods by at least 0.15 dB on Vimeo-Medium dataset.

Deep learning based fine-grained recognition technology for basketball movements

The technical essentials of basketball are very complex, in order to accomplish the identification of fine-grained basketball movements and improve the quality of basketball training, the study innovatively proposes a region screening strategy to obtain the local region information of image frames, and draws on the SlowFast network structure to design the static and dynamic detail models, and finally utilizes the 3D attention feature fusion module to complete the multi-feature relationship processing and recognition. Performance testing experiments have confirmed that the dual stream model based on region filtering has achieved a maximum improvement in average accuracy of 16.35 % and 60.36 % in the recognition of RGB images, preserving relatively complete local effective region information of RGB images. The model based on channel domain attention mechanism improves its average accuracy to over 60 %. The model recognition accuracy calculation time after dual stream fusion is reduced by about 50 %. The model based on 3D attention feature fusion module exhibits stronger robustness when the feature dimension changes. And the loss value of this model rapidly decreases and converges to the minimum loss value, with its accuracy and recall reaching 90.03 % and 88.47 % respectively, and its AUC value reaching a maximum of 0.761. The design of the study contributes to the digital development of teaching and training in basketball and enriches the theoretical body of knowledge on deep learning and action recognition.

Recurrent feature supplementation network for video super-resolution

ABSTRACT Efficient aggregation of temporal information is the basis for achieving video super-resolution. Most researchers have employed alignment or propagation to exploit the temporal information of consecutive frames. However, they frequently overlook the centrality of the reference frame in the model reconstruction when using temporal features. Thus, in this paper, we design a novel recurrent feature supplementation network. We divide the temporal information into three parts: surrounding, back propagation and forward propagation, and extract and fuse them separately. A new grouping approach is proposed for extracting features from the reference frame and its surroundings. The backward temporal fusion module and the forward temporal fusion module are designed to aggregate the backward and forward temporal information at a distance. The temporal fusion module is designed to aggregate temporal information from different parts. Moreover, we propose a feature supplementation mechanism to improve the stability of the model. The feature supplement module is devised to improve the utilization of input features and the stability of the model. Experiments demonstrate that our model achieves the state-of-the-art performance.

FQTrack:Object Tracking Method Based on a Feature-Enhanced Memory Network and Memory Quality Selection Mechanism

Visual object tracking technology is widely used in intelligent security, automatic driving and other fields, and also plays an important role in frontier fields such as human–computer interactions and virtual reality. The memory network improves the stability and accuracy of tracking by using historical frame information to assist in the positioning of the current frame in object tracking. However, the memory network is still insufficient in feature mining and the accuracy and robustness of the model may be reduced when using noisy observation samples to update it. In view of the above problems, we propose a new tracking framework, which uses the attention mechanism to establish a feature-enhanced memory network and combines cross-attention to aggregate the spatial and temporal context information of the target. The former introduces spatio-temporal adaptive attention and cross-spatial attention, embeds spatial location information into channels, realizes multi-scale feature fusion, dynamically emphasizes target location information, and obtains richer feature maps. The latter guides the tracker to focus on the area with the largest amount of information in the current frame to better distinguish the foreground and background. In addition, through the memory quality selection mechanism, the accuracy and richness of the feature samples are improved, thereby enhancing the adaptability and discrimination ability of the tracking model. Experiments on benchmark test sets such as OTB2015, TrackingNet, GOT-10k, LaSOT and UAV 123 show that this method achieves comparable performance with advanced trackers.

Fourier Raman light field microscopy based on surface-enhanced Raman scattering.

Raman scattering, as a vibrational spectrum that carries material information, has no photobleaching that enables long-duration imaging. Raman spectra have very narrow emission peaks, and multiplex Raman imaging can be achieved by using different Raman scattering peak signals. These advantages make Raman imaging widely used in biology, cytology, and medicine, which has a wider range of application scenarios. However, obtaining a three-dimensional (3D) Raman image requires scanning for tens of minutes to several hours at present. Therefore, a fast non-scanning 3D Raman imaging method is greatly needed. In this article, we propose a Fourier Raman light field microscopy based on surface-enhanced Raman scattering (sers-FRLFM). Using flower-like gap-enhanced Raman nanoparticles (F-GERNs) to enhance Raman scattering signals, a Fourier-configured light field microscope (LFM) is capable of recording complete four-dimensional Raman field information in a single frame, facilitating the 3D reconstruction of the Raman image without generating reconstruction artifacts at the native object plan. Moreover, F-GERNs can mark specific locations and have the potential to become a new tracing method to achieve specific imaging. This imaging method has great potential in the 3D real-time Raman imaging of cells, microorganisms, and tissues with the lateral resolution of 2.40 µm and an axial resolution of 4.02 µm.