ACA-Net: adaptive context-aware network for basketball action recognition.

The advancements in intelligent action recognition can be instrumental in developing autonomous robotic systems capable of analyzing complex human activities in real-time, contributing to the growing field of robotics that operates in dynamic environments. The precise recognition of basketball players' actions using artificial intelligence technology can provide valuable assistance and guidance to athletes, coaches, and analysts, and can help referees make fairer decisions during games. However, unlike action recognition in simpler scenarios, the background in basketball is similar and complex, the differences between various actions are subtle, and lighting conditions are inconsistent, making action recognition in basketball a challenging task. To address this problem, an Adaptive Context-Aware Network (ACA-Net) for basketball player action recognition is proposed in this paper. It contains a Long Short-term Adaptive (LSTA) module and a Triplet Spatial-Channel Interaction (TSCI) module to extract effective features at the temporal, spatial, and channel levels. The LSTA module adaptively learns global and local temporal features of the video. The TSCI module enhances the feature representation by learning the interaction features between space and channels. We conducted extensive experiments on the popular basketball action recognition datasets SpaceJam and Basketball-51. The results show that ACA-Net outperforms the current mainstream methods, achieving 89.26% and 92.05% in terms of classification accuracy on the two datasets, respectively. ACA-Net's adaptable architecture also holds potential for real-world applications in autonomous robotics, where accurate recognition of complex human actions in unstructured environments is crucial for tasks such as automated game analysis, player performance evaluation, and enhanced interactive broadcasting experiences.

I2U-Net: A dual-path U-Net with rich information interaction for medical image segmentation.

Although the U-shape networks have achieved remarkable performances in many medical image segmentation tasks, they rarely model the sequential relationship of hierarchical layers. This weakness makes it difficult for the current layer to effectively utilize the historical information of the previous layer, leading to unsatisfactory segmentation results for lesions with blurred boundaries and irregular shapes. To solve this problem, we propose a novel dual-path U-Net, dubbed I2U-Net. The newly proposed network encourages historical information re-usage and re-exploration through rich information interaction among the dual paths, allowing deep layers to learn more comprehensive features that contain both low-level detail description and high-level semantic abstraction. Specifically, we introduce a multi-functional information interaction module (MFII), which can model cross-path, cross-layer, and cross-path-and-layer information interactions via a unified design, making the proposed I2U-Net behave similarly to an unfolded RNN and enjoying its advantage of modeling time sequence information. Besides, to further selectively and sensitively integrate the information extracted by the encoder of the dual paths, we propose a holistic information fusion and augmentation module (HIFA), which can efficiently bridge the encoder and the decoder. Extensive experiments on four challenging tasks, including skin lesion, polyp, brain tumor, and abdominal multi-organ segmentation, consistently show that the proposed I2U-Net has superior performance and generalization ability over other state-of-the-art methods. The code is available at https://github.com/duweidai/I2U-Net.

Women's use of online health and social media resources to make sense of their polycystic ovary syndrome (PCOS) diagnosis: a qualitative study.

BACKGROUND: With the growing availability of online health resources and the widespread use of social media to better understand health conditions, people are increasingly making sense of and managing their health conditions using resources beyond their health professionals and personal networks. However, where the condition is complex and poorly understood, this can involve extensive "patient work" to locate, interpret and test the information available. The overall purpose of this study was to investigate how women with polycystic ovary syndrome (PCOS) across two healthcare systems engage with online health resources and social media to better understand this complex and poorly understood lifelong endocrine disorder. METHODS: A semi-structured interview study was conducted with women from the US ( N = 8 ) and UK ( N = 7 ) who had been diagnosed with PCOS within the previous five years. Transcribed data was analysed using a reflexive thematic analysis method. RESULTS: We highlight the information needs and information-seeking strategies women use to make sense of how PCOS affects them, to gain emotional support, and to help them find an effective treatment. We also show how women with PCOS use online health and social media resources to compare themselves to women they view as "normal" and other women with PCOS, to find their sense of "normal for me" along a spectrum of this disorder. CONCLUSION: We draw on previous models of sense-making and finding normal for other complex and sensitive health conditions to capture the nuances of making sense of PCOS. We also discuss implications for the design and use of social media to support people managing PCOS.

Research on the mechanism of short video information interaction behavior of college students with psychological disorders based on grounded theory.

BACKGROUND: The utilization of short videos by individuals often leads to the emergence of information exchange behavior. Previous studies have shown that certain students with psychological disorders exhibit addictive tendencies towards short video-related software. Therefore, it is essential to address the psychology and behavior of college students with psychological disorders while engaging with short videos. This study aims to explore the mechanism of short video information interaction behavior among college students with psychological disorders. METHODS: We conducted semi-structured interviews with 30 college students afflicted by psychological disorders in a prefecture-level city in Henan Province, China from September to December 2022. Based on the Grounded theory, we encoded 30 text materials across three levels to explore the mechanism of short video information interaction behavior among college students with psychological disorders, and subsequently build a model framework. RESULTS: The findings of this study suggest that college students with psychological disorders exhibit negative cognition tendencies that can lead to strongly negative emotions, excacerbated by a lack of social support. These adverse factors collectively drive the consumption of short video content in this demographic, providing a virtual environment where they can fulfill their unmet social needs. Therefore, the mechanism governing short video messages interaction among college students with psychological disorders encompasses negative cognitive tendencies, negative emotions, lack of social support, post-video-watching behaviors, and the gratification of social needs within the confines of a virtual environment. CONCLUSIONS: This study comprehensively analyzes the motivation and complexity of college students with psychological disorders in short video interaction. Although short videos provide this group with some ways of self-expression and emotional support, they still have a negative impact on their physical and mental health. The short video interaction of college students with psychological disorders is affected by many factors, including their negative cognitive tendencies, negative emotions, lack of social support, post-video-watching behaviors, and the gratification of social needs within the confines of a virtual environment. These findings deepened our understanding to the mechanism of short video information interaction behavior among college students with psychological disorders, also provided us with guidance on facilitating the proper use of short video and maintaining the mental health. In future researches, researchers can discuss more about intervention measures to help this demographic cope with the challenges from short video interaction.

Multiscale information interaction at local frequency band in functional corticomuscular coupling.

The multiscale information interaction between the cortex and the corresponding muscles is of great significance for understanding the functional corticomuscular coupling (FCMC) in the sensory-motor systems. Though the multiscale transfer entropy (MSTE) method can effectively detect the multiscale characteristics between two signals, it lacks in describing the local frequency-band characteristics. Therefore, to quantify the multiscale interaction at local-frequency bands between the cortex and the muscles, we proposed a novel method, named bivariate empirical mode decomposition-MSTE (BMSTE), by combining the bivariate empirical mode decomposition (BEMD) with MSTE. To verify this, we introduced two simulation models and then applied it to explore the FCMC by analyzing the EEG over brain scalp and surface EMG signals from the effector muscles during steady-state force output. The simulation results showed that the BMSTE method could describe the multiscale time-frequency characteristics compared with the MSTE method, and was sensitive to the coupling strength but not to the data length. The experiment results showed that the coupling at beta1 (15-25 Hz), beta2 (25-35 Hz) and gamma (35-60 Hz) bands in the descending direction was higher than that in the opposition, and at beta2 band was higher than that at beta1 band. Furthermore, there were significant differences at the low scales in beta1 band, almost all scales in beta2 band, and high scales in gamma band. These results suggest the effectiveness of the BMSTE method in describing the interaction between two signals at different time-frequency scales, and further provide a novel approach to understand the motor control. Supplementary Information: The online version contains supplementary material available at 10.1007/s11571-022-09895-y.

Abnormal and Changing Information Interaction in Adults with Attention-Deficit/Hyperactivity Disorder Based on Network Motifs.

Network motif analysis approaches provide insights into the complexity of the brain's functional network. In recent years, attention-deficit/hyperactivity disorder (ADHD) has been reported to result in abnormal information interactions in macro- and micro-scale functional networks. However, most existing studies remain limited due to potentially ignoring meso-scale topology information. To address this gap, we aimed to investigate functional motif patterns in ADHD to unravel the underlying information flow and analyze motif-based node roles to characterize the different information interaction methods for identifying the abnormal and changing lesion sites of ADHD. The results showed that the interaction functions of the right hippocampus and the right amygdala were significantly increased, which could lead patients to develop mood disorders. The information interaction of the bilateral thalamus changed, influencing and modifying behavioral results. Notably, the capability of receiving information in the left inferior temporal and the right lingual gyrus decreased, which may cause difficulties for patients in processing visual information in a timely manner, resulting in inattention. This study revealed abnormal and changing information interactions based on network motifs, providing important evidence for understanding information interactions at the meso-scale level in ADHD patients.

Metaformer: A Transformer That Tends to Mine Metaphorical-Level Information.

Since introducing the Transformer model, it has dramatically influenced various fields of machine learning. The field of time series prediction has also been significantly impacted, where Transformer family models have flourished, and many variants have been differentiated. These Transformer models mainly use attention mechanisms to implement feature extraction and multi-head attention mechanisms to enhance the strength of feature extraction. However, multi-head attention is essentially a simple superposition of the same attention, so they do not guarantee that the model can capture different features. Conversely, multi-head attention mechanisms may lead to much information redundancy and computational resource waste. In order to ensure that the Transformer can capture information from multiple perspectives and increase the diversity of its captured features, this paper proposes a hierarchical attention mechanism, for the first time, to improve the shortcomings of insufficient information diversity captured by the traditional multi-head attention mechanisms and the lack of information interaction among the heads. Additionally, global feature aggregation using graph networks is used to mitigate inductive bias. Finally, we conducted experiments on four benchmark datasets, and the experimental results show that the proposed model can outperform the baseline model in several metrics.

Information interaction and social support: exploring help-seeking in online communities during public health emergencies.

BACKGROUND: During public health emergencies, online community users can obtain social support and assistance through information interaction in the online community. This study takes the COVID-19 pandemic as the context and aims to analyze the influence of user information interaction in online communities on the acquisition of social support during this public health emergency. METHODS: Data collected from help-seeking posts in the "COVID-19 Patients Help-Seeking Dialog" subforum on China's Sina Weibo were used as the research sample. The influence of the frequency of interaction and responsiveness on help seekers' receipt of online social support was analyzed, and the moderating effect of help seekers' identity type and intensity of online community use was explored. RESULTS: The results reveal that the frequency of interaction positively impacts informational support (ß = 0.367, p < 0.001) and negatively impacts emotional support (ß=-0.240, p < 0.001), and the responsiveness of other users toward help-seeking posts positively impacts emotional support (ß = 0.145, p < 0.01). Moreover, help seeker's identity type and intensity of online community use significantly moderate the relationship between the frequency of interaction and the emotional support obtained by the help seeker. CONCLUSIONS: The study highlights the impact of user information interaction on obtaining help-seeking information from online communities for social support. The initiative would facilitate the resolution of issues related to users' information help-seeking during public health emergencies.

Multi-Scale Feature Interactive Fusion Network for RGBT Tracking.

The fusion tracking of RGB and thermal infrared image (RGBT) is paid wide attention to due to their complementary advantages. Currently, most algorithms obtain modality weights through attention mechanisms to integrate multi-modalities information. They do not fully exploit the multi-scale information and ignore the rich contextual information among features, which limits the tracking performance to some extent. To solve this problem, this work proposes a new multi-scale feature interactive fusion network (MSIFNet) for RGBT tracking. Specifically, we use different convolution branches for multi-scale feature extraction and aggregate them through the feature selection module adaptively. At the same time, a Transformer interactive fusion module is proposed to build long-distance dependencies and enhance semantic representation further. Finally, a global feature fusion module is designed to adjust the global information adaptively. Numerous experiments on publicly available GTOT, RGBT234, and LasHeR datasets show that our algorithm outperforms the current mainstream tracking algorithms.

Web-Based COVID-19 Dashboards and Trackers in the United States: Survey Study.

BACKGROUND: The SARS-CoV-2 pandemic provided an opportunity to use public-facing web data visualization tools to help citizens understand the evolving status of the outbreak. Given the heterogeneity of data sources, developers, tools, and designs used in this effort, it raised questions about how visualizations were constructed during a time when daily batches of data were available, but issues of data quality and standardization were unresolved. OBJECTIVE: This paper surveyed web-based COVID-19 dashboards and trackers that are likely to be used by the residents of the United States to monitor the spread of infection on a local, national, and global scale. This study is intended to provide insights that will help application developers increase the usefulness, transparency, and trustworthiness of dashboards and trackers for public health data in the future. METHODS: Websites of coronavirus dashboards and trackers were identified in August 2020 using the Google search engine. They were examined to determine the data sources used, types of data presented, types of data visualizations, characteristics of the visualizations, and issues with messy data. The websites were surveyed 3 more times for changes in design and data sources with the final survey conducted in June 2022. Themes were developed to highlight the issues concerning challenges in presenting COVID-19 data and techniques of effective visualization. RESULTS: In total, 111 websites were identified and examined (84 state focused, 11 nationwide, and 16 with global data), and this study found an additional 17 websites providing access to the state vaccination data. This study documents how data aggregators have played a central role in making data accessible to visualization developers. The designs of dashboards and tracker visualizations vary in type and quality, with some well-designed displays supporting the interpretation of the data and others obscuring the meaning of the data and potentially misleading the viewers. Five themes were identified to describe challenges in presenting COVID-19 data and techniques of effective visualization. CONCLUSIONS: This analysis reveals the extent to which dashboards and trackers informing the American public about the COVID-19 pandemic relied on an ad hoc pipeline of data sources and data aggregators. The dashboards and trackers identified in this survey offer an opportunity to compare different approaches for the display of similar data.

Abnormal information interaction in multilayer directed network based on cross-frequency integration of mild cognitive impairment and Alzheimer's disease.

Mild cognitive impairment (MCI) and Alzheimer's disease (AD) have been reported to result in abnormal cross-frequency integration. However, previous studies have failed to consider specific abnormalities in receiving and outputting information among frequency bands during integration. Here, we investigated heterogeneity in receiving and outputting information during cross-frequency integration in patients. The results showed that during cross-frequency integration, information interaction first increased and then decreased, manifesting in the heterogeneous distribution of inter-frequency nodes for receiving information. A possible explanation was that due to damage to some inter-frequency hub nodes, intra-frequency nodes gradually became new inter-frequency nodes, whereas original inter-frequency nodes gradually became new inter-frequency hub nodes. Notably, damage to the brain regions that receive information between layers was often accompanied by a strengthened ability to output information and the emergence of hub nodes for outputting information. Moreover, an important compensatory mechanism assisted in the reception of information in the cingulo-opercular and auditory networks and in the outputting of information in the visual network. This study revealed specific abnormalities in information interaction and compensatory mechanism during cross-frequency integration, providing important evidence for understanding cross-frequency integration in patients with MCI and AD.

Improved Gravitational Search Algorithm Based on Adaptive Strategies.

The gravitational search algorithm is a global optimization algorithm that has the advantages of a swarm intelligence algorithm. Compared with traditional algorithms, the performance in terms of global search and convergence is relatively good, but the solution is not always accurate, and the algorithm has difficulty jumping out of locally optimal solutions. In view of these shortcomings, an improved gravitational search algorithm based on an adaptive strategy is proposed. The algorithm uses the adaptive strategy to improve the updating methods for the distance between particles, gravitational constant, and position in the gravitational search model. This strengthens the information interaction between particles in the group and improves the exploration and exploitation capacity of the algorithm. In this paper, 13 classical single-peak and multi-peak test functions were selected for simulation performance tests, and the CEC2017 benchmark function was used for a comparison test. The test results show that the improved gravitational search algorithm can address the tendency of the original algorithm to fall into local extrema and significantly improve both the solution accuracy and the ability to find the globally optimal solution.

Application Research of Public Art in the Design of Old People's Rehabilitation Space Based on Virtual Information Interaction Platform From the Perspective of Developing Economies.

To solve the problem of the design of the old people's recuperation space, the virtual information interaction platform is used to study the public art application in the design of the old people's recuperation space. Firstly, the principles of interactive design are expounded, and secondly, the existing institutions for the old people are investigated. Under the premise of optimizing the functions of the facilities, the concepts of humanistic care, emotional care and humanization in public art are integrated into the design of the old people's rehabilitation space, to solve the long-term negative impression of the old people's repression and indifference to the old people's care institutions. The construction of the scene allows the old people to experience some operations with the help of the virtual information interaction platform. In the modern elderly rehabilitation space, the attention and application of public art design will inevitably bring spiritual and material help to the old people in their later years, and create a happy, peaceful, and comfortable elderly life for them. The survey results manifest that 65.3% of urban old people and 71.8% of rural old people feel that they cannot keep up with the pace of development. Through the analysis and discussion of the physiological and psychological characteristics of the old people, the whole survey denotes that the physiological functions of the old people are declining, which seriously affects their normal life. Therefore, the design of the rehabilitation space for the old people should not only meet the basic needs of life, but also analyze the space design from the perspective of humanization and emotion. An ecological, natural, and human settlement environment has been established. The recuperation space is designed for the needs of different old people, which helps the old people to eliminate loneliness, enhance their value of the old people, and make life full of joy and meaning for the old people.

From warning messages to preparedness behavior: The role of risk perception and information interaction in the Covid-19 pandemic.

During infectious disease outbreaks, early warning is crucial to prevent and control the further spread of the disease. While the different waves of the Covid-19 pandemic have demonstrated the need for continued compliance, little is known about the impact of warning messages and risk perception on individual behavior in public health emergencies. To address this gap, this paper uses data from the second wave of Covid-19 in China to analyse how warning information influences preventive behavior through four categories risk perception and information interaction. Drawing on the protective action decision model (PADM) and the social amplification of risk framework (SARF), risk warning information (content, channel, and type), risk perception (threat perception, hazard- and resource-related preparedness behavior perception and stakeholder perception), information interaction, and preparedness behavior intention are integrated into a comprehensive model. To test our model, we run a survey with 724 residents in Northern China. The results show that hazard-related preparedness behavior perception and stakeholder perception act as mediators between warning and preventive action. Stakeholder perception had much stronger mediating effects than the hazard-related attributes. In addition, information interaction is effective in increasing all categories risk perception, stimulating public response, while functioning as a mediator for warning. The risk warning information content, channel, and type are identified as key drivers of risk perception. The research found that information channel was more related to different risk perception than other characteristics. Overall, these associations in our model explain core mechanisms behind compliance and allow policy-makers to gain new insights into preventive risk communication in public health emergencies.

[Internal control of the quality and safety of medical activities in the field of information interaction between patient and medical organization]. / Vnutrennii kontrol' kachestva i bezopasnosti meditsinskoi deyatel'nosti v sfere informatsionnogo vzaimodeistviya patsienta i meditsinskoi organizatsii.

The scope of information interaction between patients, medical organizations and regulatory authorities is regulated by a large number of legislative and regulatory documents, a number of which are discussed in this article. The quality of information interaction in the Russian Federation is assessed within the framework of internal quality control and safety of medical activities. At the same time, the analysis of court cases related to poor-quality dental care over 6 years allowed the authors to identify a large proportion of patient complaints about the quality of information interaction between patients and medical organizations. Questions of incorrect information of patients, incorrect storage and disclosure of information related to medical confidentiality were contained in 84% of court cases, their share was 12.15% of all claims of patients to the courts. The article analyzes the areas of internal quality control and safety of medical activities and discusses the need to develop special criteria for assessing the quality of the information environment of a medical organization.

Flexible thermochromic fabrics enabling dynamic colored display.

Color-changeable fibers can provide diverse functions for intelligent wearable devices such as novel information displays and human-machine interfaces when woven into fabric. This work develops a low-cost, effective, and scalable strategy to produce thermochromic fibers by wet spinning. Through a combination of different thermochromic microcapsules, flexible fibers with abundant and reversible color changes are obtained. These color changes can be clearly observed by the naked eye. It is also found that the fibers exhibit excellent color-changing stability even after 8000 thermal cycles. Moreover, the thermochromic fibers can be fabricated on a large scale and easily woven or implanted into various fabrics with good mechanical performance. Driven by their good mechanical and physical characteristics, applications of thermochromic fibers in dynamic colored display are demonstrated. Dynamic quick response (QR) code display and recognition are successfully realized with thermochromic fabrics. This work well confirms the potential applications of thermochromic fibers in smart textiles, wearable devices, flexible displays, and human-machine interfaces.

IMIIN: An inter-modality information interaction network for 3D multi-modal breast tumor segmentation.

Breast tumor segmentation is critical to the diagnosis and treatment of breast cancer. In clinical breast cancer analysis, experts often examine multi-modal images since such images provide abundant complementary information on tumor morphology. Known multi-modal breast tumor segmentation methods extracted 2D tumor features and used information from one modal to assist another. However, these methods were not conducive to fusing multi-modal information efficiently, or may even fuse interference information, due to the lack of effective information interaction management between different modalities. Besides, these methods did not consider the effect of small tumor characteristics on the segmentation results. In this paper, We propose a new inter-modality information interaction network to segment breast tumors in 3D multi-modal MRI. Our network employs a hierarchical structure to extract local information of small tumors, which facilitates precise segmentation of tumor boundaries. Under this structure, we present a 3D tiny object segmentation network based on DenseVoxNet to preserve the boundary details of the segmented tumors (especially for small tumors). Further, we introduce a bi-directional request-supply information interaction module between different modalities so that each modal can request helpful auxiliary information according to its own needs. Experiments on a clinical 3D multi-modal MRI breast tumor dataset show that our new 3D IMIIN is superior to state-of-the-art methods and attains better segmentation results, suggesting that our new method has a good clinical application prospect.

Twelve Agendas on Interacting with Information: A Human-Engaged Computing Perspective.

During the coronavirus global pandemic crisis, we have received information from authentic and inauthentic sources. Fake news, continuous rumors, and prejudiced opinions from digital platforms and social media have the capacity to disrupt social harmony, to stall personal development, and to undermine trust on all levels of human interaction. Despite the wide plurality of perspectives, the diversity of contents, the variety of voices, and the many often-conflicting reasons for publishing, our interactions with information on digital devices are progressively shaping such situations and affecting decisions on all levels. We look at the limitations of existing designs and guidelines in the current paradigm, and we ask to what extent researchers and developers can focus and contribute, through their innovations, to the reduction of uncertainty and cases of misdirection, how they can mitigate tensions between information and humans, and how they can contribute to the maintenance and enhancement of worthy human values. Human-engaged computing (HEC) calls for innate user capacities to be enhanced rather than displaced by digital technologies so that the human factor in interactions is fully exploited and truly efficient symbiotic relationships between humans and devices can be achieved. Under the framework of HEC, we propose 12 research agendas from the theoretical, principled, and practical aspects, in order to develop future synergized interactions between humans and information. The present crisis presents us with a good opportunity to reflect on the need to empower humans in relation to the tools they use and to consider the next paradigm shift for designing information interaction.

Study on Multi-agent Information Interaction Mechanism of Drug Supply Emergency Management Based on Multi-agent Sy s- tem / 中国药房

OBJECTIVE： To provide reference for improving the efficiency of drug supply emergency management in China. METHODS： Referring to the general principle of multi-agent system， the multi-agent information interaction mechanism of drug supply emergency management was constructed by using drug production and distribution enterprises， medical institutions， government， patients and media as the main bodies. RESULTS & CONCLUSIONS： In this study， a multi-agent information interaction mechanism of drug supply emergency management was preliminarily established， which was composed of risk information transfer coordination mechanism， information sharing mechanism and emergency task decomposition mechanism. The process can be divided into four stages as risk prevention， risk early warning， risk response and risk mitigation. The multi-agent information interaction mechanism of drug supply emergency management had certain applicability to improve the transmission efficiency of key information in the process of drug supply emergency management， which can provide new ideas for relevant departments to improve the ability of drug supply risk identification and response， and then improve China’s drug information monitoring system and supply guarantee system.

The Modeling and Simulation of the Galvanic Coupling Intra-Body Communication via Handshake Channel.

Intra-body communication (IBC) is a technology using the conductive properties of the body to transmit signal, and information interaction by handshake is regarded as one of the important applications of IBC. In this paper, a method for modeling the galvanic coupling intra-body communication via handshake channel is proposed, while the corresponding parameters are discussed. Meanwhile, the mathematical model of this kind of IBC is developed. Finally, the validity of the developed model has been verified by measurements. Moreover, its characteristics are discussed and compared with that of the IBC via single body channel. Our results indicate that the proposed method will lay a foundation for the theoretical analysis and application of the IBC via handshake channel.