Audiovisual Information Research Articles

The influence of visual and auditory environments in parks on visitors’ landscape preference, emotional state, and perceived restorativeness

Various auditory and visual factors influence people’s perception and restoration experiences in the spatial environments. However, few studies have treated these factors as a comprehensive system phenomenon to reveal their integrated effects. Therefore, a specific explanation of the primary pathways and factors that contribute to the main effects of park soundscapes and visual features and the resulting perceived restorativeness remains unclear. The study surveyed 861 visitors in five urban parks in China and collected audiovisual information. Using Partial Least Squares Structural Equation Modeling (PLS-SEM), the research explored the direct, indirect, and moderating effects of common audiovisual environments in parks on perceived restorativeness, emotional states, and preferences. The results indicate that most natural-related visual and auditory factors provide direct benefits for people’s perceived restorativeness, emotional state, and preference. Additionally, certain landscape features and types of sound sources, such as trees and water sounds, have indirect effects on activating restoration through preference and emotion mediation. The study also reveals the moderating effects of landscape features and sound source types on emotional and perceived restorativeness. Another noteworthy finding is the significant relationship between bird songs and the positive impact on perceived restorativeness, emotional state, and preference, which is closely related to acoustic quality indicators. These findings offer new insights for creating urban park spaces through visual and auditory interactions.

Impaired emotional multimodal integration in inhibition of return in children with attention-deficit/hyperactivity disorder.

Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder in children. Previous studies have shown that children with ADHD have impaired processing of emotional stimuli, but it is unclear whether their ability to integrate multimodal emotional stimuli is impaired and at which processing pathway this impairment exists. The present study investigated the ability of children with ADHD to integrate emotional audiovisual stimuli under different emotional conditions, and the effect of audiovisual integration on IOR to reveal the impaired processing pathway of their emotional audiovisual integration. Fifty-eight school-age children (29 with ADHD and 29 matched typically developing (TD) children) performed an emotional valence discrimination task with a cue-target paradigm. The results showed that children with ADHD did not exhibit audiovisual integration of emotional stimuli in all experimental conditions. In addition, the IOR effect was significantly smaller for audiovisual targets than for visual targets under the negative but not the neutral emotion condition in children with ADHD, whereas this effect was present in all emotion conditions in TD children. These results indicate that the ability to integrate emotional audiovisual information is impaired in children with ADHD and this impairment exists in both bottom-up and top-down pathways. Additionally, although presenting emotional auditory stimuli at the same time as emotional faces reduced IOR both in children with ADHD and TD, the manner of reduction differed. These findings provide new evidence of emotional processing deficits and multimodal integration deficits in children with ADHD, and help provide support for children in educational settings.

EXPRESS: Memory for health information: Influences of age, hearing aids, and multisensory presentation.

We investigated how presenting online health information in different modalities can influence memory, as this may be particularly important for older adults who may need to make regular decisions about health, and could also face additional challenges such as memory deficits and sensory impairment (hearing loss). We tested whether, as predicted by some literature, older adults would disproportionately benefit from audio-visual (AV) information compared with visual-only (VO) or auditory-only (AO) information, relative to young adults. Participants were 78 young adults (aged 18-30 years old, mean=25.50 years), 78 older adults with normal hearing (aged 65-80 years old, mean=68.34 years), and 78 older adults who wear hearing aids (aged 65-79 years old, mean=70.89 years). There were no significant differences in the amount of information remembered across modalities (AV, VO, AO), no differences across participant groups, and we did not find the predicted interaction between participant group and modality. The older-adult groups performed worse than young adults on background measures of cognition, with the exception of a vocabulary test, suggesting that they may have been using strategies based on prior knowledge and experience to compensate for cognitive and/or sensory deficits. The findings indicate that cost-effective, text-based websites may be just as useful as those with edited videos for conveying health information to all age groups, and hearing aid users.

Food Consumption Preference Amongst Young Adults Based on Social Media Influence in Malaysia

Food consumption amongst young adults has potentially been influenced by social media. Businesses also utilize social media as a medium of promotion. Thus, cultural food has gone viral on social media, causing the demand for cultural food to rise. Several factors in social media influence could be the reason for young adults discovering international cultural foods. Therefore, the focus of this study is to identify how social media influences young adults' tastes and preferences for international foods. Data was collected from 115 respondents who are young adults. The implications and consequences of the study findings for food consumption are further discussed. Social media influence on cultural food includes audio-visual appearance, information sharing, and delivery, finally, peer pressure on social was investigated in this study.

Multimodal emotion recognition based on a fusion of audiovisual information with temporal dynamics

AbstractIn the Human-Machine Interactions (HMI) landscape, understanding user emotions is pivotal for elevating user experiences. This paper explores Facial Expression Recognition (FER) within HMI, employing a distinctive multimodal approach that integrates visual and auditory information. Recognizing the dynamic nature of HMI, where situations evolve, this study emphasizes continuous emotion analysis. This work assesses various fusion strategies that involve the addition to the main network of different architectures, such as autoencoders (AE) or an Embracement module, to combine the information of multiple biometric cues. In addition to the multimodal approach, this paper introduces a new architecture that prioritizes temporal dynamics by incorporating Long Short-Term Memory (LSTM) networks. The final proposal, which integrates different multimodal approaches with the temporal focus capabilities of the LSTM architecture, was tested across three public datasets: RAVDESS, SAVEE, and CREMA-D. It showcased state-of-the-art accuracy of 88.11%, 86.75%, and 80.27%, respectively, and outperformed other existing approaches.

The development of multisensory facilitation for simple audio-visual information continues through adolescence.

The development of multisensory facilitation for simple audio-visual information continues through adolescence.

The impact of face masks on face-to-face neural tracking of speech: Auditory and visual obstacles

Face masks provide fundamental protection against the transmission of respiratory viruses but hamper communication. We estimated auditory and visual obstacles generated by face masks on communication by measuring the neural tracking of speech. To this end, we recorded the EEG while participants were exposed to naturalistic audio-visual speech, embedded in 5-talker noise, in three contexts: (i) no-mask (audio-visual information was fully available), (ii) virtual mask (occluded lips, but intact audio), and (iii) real mask (occluded lips and degraded audio). Neural tracking of lip movements and of the sound envelope of speech was measured through backward modeling, that is, by reconstructing stimulus properties from neural activity. Behaviorally, face masks increased perceived listening difficulty and phonological errors in speech content retrieval. At the neural level, we observed that the occlusion of the mouth abolished lip tracking and dampened neural tracking of the speech envelope at the earliest processing stages. By contrast, degraded acoustic information related to face mask filtering altered neural tracking of speech envelope at later processing stages. Finally, a consistent link emerged between the increment of perceived listening difficulty and the drop in reconstruction performance of speech envelope when attending to a speaker wearing a face mask. Results clearly dissociated the visual and auditory impact of face masks on the neural tracking of speech. While the visual obstacle related to face masks hampered the ability to predict and integrate audio-visual speech, the auditory filter generated by face masks impacted neural processing stages typically associated with auditory selective attention. The link between perceived difficulty and neural tracking drop also provides evidence of the impact of face masks on the metacognitive levels subtending face-to-face communication.

Relational-branchformer: Novel framework for audio-visual speech recognition

This study embraced the state-of-the-art Branchformer series architecture within the realm of automatic speech recognition, supplanting the widely utilized Conformer architecture. This substitution offers an innovative remedy tailored to audio-visual speech recognition tasks. Building upon the Branchformer architecture, enhancements were made, culminating in the proposal of the Relational-Branchformer (R-Branchformer). The convolutional attention relation module was innovatively incorporated to augment the connectivity between the local and global branches by meticulously considering their interrelations and interplays. Consequently, this module facilitates the mutual embedding of local and global contextual information, ultimately leading to a substantial enhancement in model performance. Our model was grounded in the utilization of the connectionist temporal classification (CTC) loss, wherein intermediate CTC losses were incorporated between blocks. Moreover, through the reference and enhancement of the gated interlayer collaboration module, which superseded the inter CTC module, the conditional independence assumption intrinsic to the CTC model was effectively relaxed. As a consequence, this augmentation markedly bolstered the overall performance of our model. Furthermore, the audio-visual output enhancement module was proposed, which adeptly assimilates information from both audio and visual modalities to enrich the representation of audio-visual information. Consequently, the R-Branchformer model achieved remarkable word error rates of 1.7% and 1.5% on the LRS2 and LRS3 test sets, respectively, exemplifying its state-of-the-art performance in audio-visual speech recognition tasks.

Commentary to “The impact of audiovisual information on parental anxiety levels prior to hypospadias surgery: A prospective single center cohort study”

Commentary to “The impact of audiovisual information on parental anxiety levels prior to hypospadias surgery: A prospective single center cohort study”

Effect of information delivery techniques in reducing pre-procedural anxiety in computed tomography

ObjectivesPatients undergoing medical procedures often experience heightened anxiety, which can affect their experience and overall health. The current study aimed at looking at a quality improvement initiative to compare written and audiovisual information delivery methods to reduce anxiety prior to Computed Tomography (CT). MethodsIn this prospective interventional study, we assessed state and trait anxiety in patients scheduled for their first CT scan. Three PDSA cycles were carried out over six months, with each cycle lasting for two months each. The participants were divided into three groups, the baseline, written, and audiovisual intervention groups. Anxiety levels were assessed using the State-Trait Anxiety Inventory (STAI) questionnaire. State anxiety is a temporary emotional response, while trait anxiety reflects enduring personality characteristics. ResultsThe mean age of participants was 43.26 years (SD 15.07) in the baseline group, 39.9 years (SD 14.72) in the written group, and 48.59 years (SD 13.54) in the audiovisual group. For state anxiety, the baseline mean was 58.4 (SD 6.9), notably reduced to 43.2 (SD 5.5) with written intervention and to 38.6 (SD 7.7) with audiovisual intervention (p < 0.001). Trait anxiety scores remained relatively stable in all groups (p = 0.31). ConclusionBoth written and audiovisual interventions successfully alleviate pre-imaging anxiety in patients undergoing CT scans. The findings underscore the superior efficacy of audiovisual materials in achieving a more substantial reduction in state anxiety compared to written information. These findings are particularly relevant in resource limited settings where simple interventions show significant improvements.

(069) ASSESSING READABILITY, UNDERSTANDABILITY, ACTIONABILITY, AND QUALITY OF ONLINE HEALTH RESOURCES FOR SEXUAL HEALTH DURING MENOPAUSE

Abstract Introduction Recent studies indicate that over half of adults in the United States rely on the internet for accessing health-related information. (1) Patients experiencing menopause may feel a sense of embarrassment about their sexual health and, consequently, turn to online resources to maintain a sense of anonymity. Despite a shift in information-seeking patterns within the last decade, there remains a significant gap in the research assessing the quality of the content that patients encounter online. While prior research has investigated the readability of materials for sexual health promotion and sexual health in men, there are no prior investigations addressing the quality of sexual health materials for individuals experiencing menopause. Objective Our objective was to evaluate online patient- oriented health resources concerning sexual health during menopause for their readability, understandability, actionability, and overall quality. Methods We conducted a Google keyword search for “sexual health during menopause,” reviewed the first three pages of results, and included 22 unique, relevant resources after excluding journal articles and materials not intended for patient education. We assessed readability using multiple established indices, including the Flesch-Kincaid Grade Level. Understandability and actionability were evaluated with the Patient Education Materials Assessment Tool (PEMAT), with a threshold of 70% for actionable or understandable resources. (2) The JAMA benchmark criteria were used to evaluate the quality of each site.(3) Further analysis will consist of qualitative content analysis and assessment of accuracy. Finally, these resources will be compared by the website publisher's industry for any statistically significant differences in any of these outcomes. Results No materials met the American Medical Association's recommended readability standards by any metric.(4) The reading level of the reviewed resources ranged from grades 7 to 18. PEMAT scoring revealed that three resources reached the threshold for understandability though none met the criteria for actionability. On average, understandability was 60.1% and actionability was 51.8%. No resource met all four JAMA benchmark criteria. The average criteria met was 2.0. Correlation analysis demonstrated a strong negative correlation between materials’ readability and understandability (r = −0.459, P &amp;lt; .05). Conclusions These findings underscore the need for improved patient resources for women’s sexual health during menopause. Future efforts in patient education materials development should prioritize patient concerns and enhancing readability, understandability, and actionability. Sources: 1. Wang X, Cohen RA. Health information technology use among adults: United States, July–December 2022. NCHS Data Brief, no 482. Hyattsville, MD: National Center for Health Statistics. 2023. DOI: https://dx.doi.org/10.15620/cdc:133700. 2. Shoemaker SJ, Wolf MS, Brach C. Development of the Patient Education Materials Assessment Tool (PEMAT): a new measure of understandability and actionability for print and audiovisual patient information. Patient Educ Couns. 2014;96(3):395–403. 3. Silberg WM, Lundberg GD, Musacchio RA. Assessing, Controlling, and Assuring the Quality of Medical Information on the Internet: Caveant Lector et Viewor-Let the Reader and Viewer Beware. JAMA. 1997;277(15):1244–1245. doi:10.1001/jama.1997.03540390074039 4. American Medical Association. CHAPTER 9: OPINIONS ON PROFESSIONAL SELF-REGULATION. https://www.ama-assn.org/sites/ama-assn.org/files/corp/media-browser/code-of-medical-ethics-chapter-9.pdf Published 2016 Disclosure No.

The impact of audiovisual information on parental anxiety levels prior to hypospadias surgery: A prospective single center cohort study

Most parents have anxiety before a pediatric surgical procedure. Parental anxiety may impair the parents' ability to cope with new or stressful situations while their children are undergoing surgery. By effectively improving the education of parents regarding the diagnosis, treatment, and potential complications of hypospadias and surgical repair, it might be feasible to reduce their anxiety during this process. To determine whether structured audiovisual information would reduce parents' anxiety levels compared to classic verbal information. The diagnosis was made and, treatment options were explained, and State-Trait Anxiety Inventory Form - State Anxiety (STAI-I) forms were filled out by parents at the first consultation. In the second consultation, parents were divided into structured audio-visual-information (Group-1) and classic verbal information (Group-2) groups. Following these consultations, all parents in both groups filled out STAI-I again. Parents filled out the forms for the last time on the postoperative-14th-day and the results were compared. A total of 124 (51.2%) parents were informed with structured-audiovisual-informational material and 118 parents (48.8%) were informed with classic verbal information. First STAI-I scores were 57.65±5.17 and 56.91±5.28 for Group-1 and Group-2, respectively, and there was no difference between the groups (p=0.709). The STAI-I scores after the second consultation were 44.82±5.65 and 49.42±2.81 for Group-1 and Group-2, respectively. Parental anxiety decreased in both groups following the second consultation. Notably, a statistically significant superiority was found between the groups in favor of Group-1 (p=0.001). Parents whose children will undergo hypospadias surgery experience significant anxiety. We observed that informing patients adequately and in appropriate language using a suitable method was associated with less anxiety. Preoperative parental anxiety is influenced by several variables, including parent age, parent gender, child age, lack of knowledge, and concerns over complications or pain. Although we are unable to alter the factors of child age and parent gender, we can impact parents' concerns regarding postoperative pain and anesthesia by enhancing their comprehension of the procedure via providing them of sufficient and accurate information. Providing parents with structured audio-visual information about the preoperative and postoperative period before hypospadias surgery is associated with lower parental anxiety levels. Supplying structured audiovisual information regarding the preoperative and postoperative periods can help parents have an improved comprehension of the procedure and minimize their anxiety.

Evaluation of online patient education materials for acute myeloid leukemia.

e23135 Background: Acute myeloid leukemia (AML) is the most common adult leukemia, accounting for approximately 80% of all cases. In the modern healthcare landscape, a substantial number of patients turn to online platforms such as Google for information pertaining to their diagnoses and treatment options. This study sought to assess 14 online AML websites for their understandability and actionability using the Patient Education Materials Assessment Tool (PEMAT). Methods: Fourteen patient-facing U.S. online AML websites were searched in Google, selected and analyzed using the PEMAT criteria. The PEMAT rating tool is a freely accessible online resource evaluating print and audiovisual information. The ‘understandability’ section is scored out of 17 possible points and the ‘actionability’ section is scored out of 6 possible points. The websites were rated by two independent reviewers and any discrepancies were discussed. The websites were categorized by Government, Public/Private companies, Patient Advocacy Groups, Professional Societies, and Cancer Centers. Results: The study analyzed 14 websites on AML education material. The mean ‘understandability’ score was 85% ( Range: 79%–92%); Government scored the highest, followed by Professional Societies, Patient Advocacy Groups, Cancer Centers, and Private/Public Companies. PEMAT metric 11 ‘the material provides a summary’ scored poorest across all ‘understandability’ criteria. The mean ‘actionability’ score was 66% ( Range: 56%–90%); Patient Advocacy Groups scored the highest, followed by Professional Societies, Government, Private/Public Companies, and Cancer Centers. PEMAT metric 26 ‘the material uses visual aids whenever they could make it easier to act on the instructions’ scored poorest across all ‘actionability’ criteria. Conclusions: Most of the AML websites analyzed were easy to understand but lacked material that prompts patients to take action. As patients turn to online website sources for information, it is crucial that these education materials provide clear information that patients can appropriately act on. This study highlights an opportunity to enhance online patient education material by adding action-oriented features, such as content summaries, tangible tools, and visual aids. [Table: see text]

Arahan Peningkatan Prioritas Kinerja Operasional Stasiun Sidoarjo dan Stasiun Indro Menggunakan Analisis QFD

The Gerbangkertosusila area is designated as the main driver of the regional economy (primer mover) which has the criteria as an area that grows faster than other regions in a province. Sidoarjo and Gresik Regency are two areas included in the seven administrative areas of Gerbangkertosusila. Sidoarjo and Gresik have transportation systems that can support the mobility of the surrounding community, namely Sidoarjo Station and Indro Station. Sidoarjo Station and Indro Station still have performance that needs to be improved such as the size of the room area and supporting installation devices that do not meet the standards and there is still crossing in the station circulation. The purpose of this study is to determine the priority of directions for improving the operational performance of Sidoarjo Station and Indro Station. This research uses Quality Function Deployment (QFD) analysis. The priority of the direction to improve the operational performance of Sidoarjo Station and Indro Station is determined based on the value of Absolute Importance (AI). The results of the analysis show that the priority direction for improving the operational performance of Sidoarjo Station is the provision of TV as an audio-visual information medium (8,100), while the priority for the direction to improve the operational performance of Indro Station is the addition of information boards for the station area name (9,643).

Audiovisual Resources Metadata: Analysis of Records Originating From Novice Metadata Creators in Kuwait

Audiovisual resources available online gain more importance in satisfying users’ information needs, yet the quality of metadata that ensures discoverability of these resources is not yet emphasized, mainly due to lack of benchmark data. This article addresses the need by presenting results of the comparative evaluation of accuracy and completeness of Dublin Core metadata records created by metadata beginners to represent audio recordings and video recordings. We present our findings in the context of how the metadata learning is organized at the program which currently prepares most of those entering the information profession in Kuwait. Findings reveal some similarities, as well as some pronounced differences in metadata accuracy and completeness patterns for two kinds of online digital resources: audio recordings and video recordings. Video metadata was found to be of substantially higher quality than audio metadata created by the same beginners. Overall, for audiovisual information resources, we found the Type metadata field to be the least prone to completeness errors, and Format to accuracy errors. Our data suggests that the Source metadata field is the most vulnerable for accuracy errors in both audio metadata and video metadata. However, Dublin Core metadata fields with the highest possibility of completeness errors did not exhibit overlap between the two sets of beginner-created metadata records. We discuss examples of the most common metadata errors and compare results with findings of previous research. Empirical data obtained in this study allows assessing preparedness of information professionals to create metadata that is functional in supporting resource discovery.

Macaque claustrum, pulvinar and putative dorsolateral amygdala support the cross-modal association of social audio-visual stimuli based on meaning.

Social communication draws on several cognitive functions such as perception, emotion recognition and attention. The association of audio-visual information is essential to the processing of species-specific communication signals. In this study, we use functional magnetic resonance imaging in order to identify the subcortical areas involved in the cross-modal association of visual and auditory information based on their common social meaning. We identified three subcortical regions involved in audio-visual processing of species-specific communicative signals: the dorsolateral amygdala, the claustrum and the pulvinar. These regions responded to visual, auditory congruent and audio-visual stimulations. However, none of them was significantly activated when the auditory stimuli were semantically incongruent with the visual context, thus showing an influence of visual context on auditory processing. For example, positive vocalization (coos) activated the three subcortical regions when presented in the context of positive facial expression (lipsmacks) but not when presented in the context of negative facial expression (aggressive faces). In addition, the medial pulvinar and the amygdala presented multisensory integration such that audiovisual stimuli resulted in activations that were significantly higher than those observed for the highest unimodal response. Last, the pulvinar responded in a task-dependent manner, along a specific spatial sensory gradient. We propose that the dorsolateral amygdala, the claustrum and the pulvinar belong to a multisensory network that modulates the perception of visual socioemotional information and vocalizations as a function of the relevance of the stimuli in the social context. SIGNIFICANCE STATEMENT: Understanding and correctly associating socioemotional information across sensory modalities, such that happy faces predict laughter and escape scenes predict screams, is essential when living in complex social groups. With the use of functional magnetic imaging in the awake macaque, we identify three subcortical structures-dorsolateral amygdala, claustrum and pulvinar-that only respond to auditory information that matches the ongoing visual socioemotional context, such as hearing positively valenced coo calls and seeing positively valenced mutual grooming monkeys. We additionally describe task-dependent activations in the pulvinar, organizing along a specific spatial sensory gradient, supporting its role as a network regulator.

Decoding Group Emotional Dynamics in a Web-Based Collaborative Environment: A Novel Framework Utilizing Multi-Person Facial Expression Recognition

As a crucial form of non-verbal communication, facial expressions can convey an individual’s emotional state through a combination of facial muscle movements and provide an effective approach to understanding emotional shifts among group members to a certain extent. However, in real-time collaborative environments, the increasing influx of audiovisual information can overwhelm an individual’s limited visual attention, making it challenging to observe and analyze other group members’ facial expressions continually. The failure to promptly recognize and interpret facial expressions can disrupt individual and group-level comprehension and evaluation of emotional dynamics during collaborative interactions, consequently hindering subsequent emotion management and communication. This article delves into the classification of facial expression information and its formation mechanism to thoroughly analyze the relationship between group members’ emotional perceptions and expressions in the collaboration process. Leveraging the YOLO-FaceV2 face detection model, FaceNet face recognition model, and CERN expression recognition model, we present a novel Collaborative Emotion Analysis Framework (CEAF) for multi-person facial expression recognition. By employing Web real-time communication technology, this framework is integrated into an online group meetings system, which can identify the faces and expressions of the participants and provide real-time visual analysis of their expression information. After the conclusion of the meeting, the system can perform an emotional evaluation with pre-defined operators, providing invaluable insights into the emotional dynamics of the group and individual members throughout the collaborative process. Ultimately, validation through an online meeting instance indicates that this system can facilitate groups in interpreting emotional changes among collaborative group members to a considerable extent.

Visual-guided scene-aware audio generation method based on hierarchical feature codec and rendering decision

Visually guided spatial sound generation (VGSSG) is a well-suited multimodal learning method for dealing with recorded videos. However, existing methods are difficult to be directly applied to spatial sound generation for movie clips. This is mainly due to (1) the existence of Cinematic Audiovisual Language (CAL) in movies, which makes it difficult to construct spatial sound mapping models directly through data-driven based methods. (2) The problem of the inadequate model performance, which is caused by the excessive heterogeneous gap between audiovisual modal information. To solve the aforementioned problems, we propose a VGSSG method based on CAL decision-making and hierarchical feature coding and decoding, which effectively accomplishes spatial sound generation based on the CAL of movies. Specifically, to solve the problem of CAL modeling, a multimodal information-guided movie audio rendering decision maker is established, which can decide the rendering strategy based on the CAL of the current clip. To narrow the heterogeneous gap that hinders the fusion between audiovisual modal data, we propose a codec structure based on hierarchical fusion of audiovisual features and full-scale skip-connections, which improves the efficiency of the comprehensive utilization of audiovisual modal data, and demonstrates the effectiveness of adopting shallow features in VGSSG task. We integrate both 2-channel and 6-channel spatial audio generation into a unified framework. In addition, we establish a movie audiovisual bimodal dataset with hand-crafted CAL annotations. Experimentally, we demonstrate that compared with the existing methods, our method has higher performance in terms of reducing generation distortion.

Differential effects of high-definition transcranial direct current stimulation (HD-tDCS) on attentional guidance by working memory in males with substance use disorder according to memory modality

Information stored in working memory can guide perception selection, and this process is modulated by cognitive control. Although previous studies have demonstrated that neurostimulation over the left dorsolateral prefrontal cortex (lDLPFC) contributes to restore cognitive control among individuals with substance use disorder (SUD), there remains an open question about the potential stimulation effects on memory-driven attention. To address this issue, the present study adopted a combined working memory/attention paradigm while employing high-definition transcranial direct current stimulation (HD-tDCS) to stimulate the lDLPFC. Observers were asked to maintain visual or audiovisual information in memory while executing a search task, while the validity of the memory contents for the subsequent search task could be either invalid or neutral. The results showed a faint memory-driven attentional suppression effect in sham stimulation only under the audiovisual condition. Moreover, anodal HD-tDCS facilitated attentional suppression effect in both the strength and temporal dynamics under the visual-only condition, whereas the effect was impaired or unchanged under the audiovisual condition. Surprisingly, cathodal HD-tDCS selectively improved temporal dynamics of the attentional suppression effect under the audiovisual condition. The present study revealed the differential enhancement of HD-tDCS on cognitive control over visual and audiovisual memory-driven attention among individuals with SUD.

A novel vehicle collision detection system: Integrating audio-visual fusion for enhanced performance

In vehicular accidents, the swift and accurate identification of car crashes is paramount, as it serves as the linchpin for prompt responses from emergency services and search-and-rescue operations. This study introduces an innovative multimodal car crash detection system that capitalizes on audio-visual data sourced from dashboard cameras, thus significantly enhancing the precision of automobile collision detection. In contrast to car crash detection systems relying on single-modal inputs, this research employs advanced multimodal methodologies with a neural network architecture that integrates Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) for car crash detection. This system concurrently leverages audio spectrogram and audio feature data, video RGB, video optical flow, and video differential information, enabling collision recognition through a neural network system, resulting in markedly improved collision detection accuracy. A comprehensive comparative analysis is conducted, benchmarking our system against the most cutting-edge existing car crash detection systems. The system employs a unique fusion approach, allowing it to apply its inference to audio-visual information of varying durations compared to the training set. The empirical findings unequivocally affirm our proposed solution’s substantial enhancement in car crash detection.