In this work, we introduce the TriFusion Network, an innovative deep learning framework designed for the simultaneous analysis of auditory, visual, and textual data to accurately assess emotional states. The architecture of the TriFusion Network is uniquely structured, featuring both independent processing pathways for each modality and integrated layers that harness the combined strengths of these modalities to enhance emotion recognition capabilities. Our approach addresses the complexities inherent in multimodal data integration, with a focus on optimizing the interplay between modality-specific features and their joint representation. Extensive experimental evaluations on the challenging AVEC Sentiment Analysis in the Wild dataset highlight the TriFusion Network's robust performance. It significantly outperforms traditional models that rely on simple feature-level concatenation or complex score-level fusion techniques. Notably, the TriFusion Network achieves Concordance Correlation Coefficients (CCC) of 0.606, 0.534, and 0.170 for the arousal, valence, and liking dimensions respectively, demonstrating substantial improvements over existing methods. These results not only confirm the effectiveness of the TriFusion Network in capturing and interpreting complex emotional cues but also underscore its potential as a versatile tool in real-world applications where accurate emotion recognition is critical.

In this paper, we propose a novel approach of video skimming by exploiting the fusion of video temporal information and keyword information representation extracted from multi-model video information including audio, text and visual indices. In addition, we introduce the brand-safe filtering and sentiment analysis in order to only reserve the user-friendly content in the video skim. In the experiment by using the videos from YouTube-8M dataset, we have proved that the semantic conservation in the video skim from the proposed approach highly outperforms the approaches by only partial information of the video in conserving the semantic content of the video.

Elaborate sound design, including background music, ambient sounds (sounds describing the game world), and character sounds (sounds generated by the character’s actions), plays a pivotal role in modern videogames. However, the influence of these different types of sound on the player experience has not been extensively researched. This study examines the influence of these sound types on immersion, avatar identification, fun and perceived competence. In two experiments, participants played League of Legends in four different sound conditions. The first experiment revealed a non-significant trend in the effect of character sound on avatar identification. Ambient sounds, however, were limited in this experiment because the task restricted participants’ movement across the game map. Consequently, we adapted the task to allow for a wider variety of ambient sounds in the second experiment. Here, a significant impact of character sounds on immersion, avatar identification, and fun, was observed, as well as an interaction effect of character sounds and ambient sounds on fun. Furthermore, we observed a trend, though not statistically significant, suggesting that ambient sounds may influence the player’s sense of flow. These findings underline the distinct effects of different sound types and we discuss implications for the design of sound in video games.

Audio classification using deep learning models, essential for applications like voice assistants and music analysis, faces challenges when deployed on edge devices due to their limited computational resources and memory. Achieving a balance between performance, efficiency, and accuracy is a significant obstacle in optimizing these models for such constrained environments. In this investigation, we evaluate diverse deep learning architectures, including Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), for audio classification tasks on the ESC 50, UrbanSound8k, and Audio Set datasets. Our empirical findings indicate that Mel Spectrograms outperform raw audio data, attributing this enhancement to their synergistic alignment with advanced image classification algorithms and their congruence with human auditory perception. To address the constraints of model size, we apply model compression techniques, notably magnitude pruning, Taylor Pruning, and 8-bit quantization. The research demonstrates that a hybrid pruned model achieves a commendable accuracy rate of 89 percent, which, although marginally lower than the 92 percent accuracy of the uncompressed CNN, strikingly illustrates an equilibrium between efficiency and performance. Subsequently, we deploy the optimized model on Raspberry Pi 4 and NVIDIA Jetson Nano platforms for audio classification tasks. These findings highlight the significant potential of model compression strategies in enabling effective deep learning applications on resource-limited devices, with minimal compromise on accuracy.

Although wireless capsule endoscopy (WCE) detects small bowel diseases effectively, it has some limitations. For example, the reading process can be time-consuming due to the numerous images generated per case, and lesion detection accuracy may rely on the operators' skills and experiences. Hence, many researchers have recently developed deep learning-based methods to address these limitations. However, they tend to select only a portion of the images from a given WCE video and analyze each image individually. In this study, we note that more information can be extracted from the unused frames and temporal relations of sequential frames. Specifically, to increase the accuracy of lesion detection without depending on experts' frame selection skills, we suggest using whole video frames as the input to the deep-learning system. Thus, we propose a new Transformer-based neural encoder that takes the entire video as the input, exploiting the power of the Transformer to extract long-term global correlation within and between the input frames. Subsequently, we can capture the temporal context of the input frames and the attentional features within a frame. Tests on benchmark datasets of four WCE videos showed 95.1% sensitivity and 83.4% sensitivity. These results may significantly advance automated lesion detection techniques for WCE images. Our code is available at https://github.com/syupoh/VWCE-Net.git.

Background: Swimming and, specifically, front crawl, can be included among the "overhead" sports. Overhead sports are a risk factor for some problems of the musculoskeletal system, especially the shoulder. The aim of the study was assessing the incidence of shoulder and neck pain in a Masters Swimming Team and its correlation with the crawl stroke. Methods: It is an observational study through video-analysis of the stroke and a questionnaire. The participants are 61 athletes of a Master team, whose prevailing training stroke was the front crawl were selected for the present study. Their stroke was analyzed during training by a go-pro camera mounted on a sliding trolley on a track, evaluating with their trainer their technical defects. A questionnaire about frequency of shoulder and neck pain during the last five years was administered to all the participants at the study. Results: From the questionnaire, 45 and 55 out of 61 athletes had suffered from shoulder pain and cervical pain, respectively. Both types of pain were correlated with the weekly swimming volume. The swimmers with hyperflexion of the wrist and prolonged internal rotation in the pulling phase had shoulder problems. Those who suffered from current shoulder pain reduced the underwater time. The four swimmers with an excessive body roll during breathing and those who kept their heads extended, reported cervical pain. Conclusions: Shoulder and neck pain could be prevented with the correction of specific technical errors in crawl stroke.

In recent years, the scientific and technological developments led to an explosion of available videos on the web, increasing the necessity of fast and effective video analysis and summarization. Video summarization methods aim to generate a synopsis by selecting the most informative parts of the video content. The user’s personal preferences, often involved in the expected results, should be taken into account in the video summaries. In this paper, we provide the first comprehensive survey on personalized video summarization relevant to the techniques and datasets used. In this context, we classify and review personalized video summary techniques based on the type of personalized summary, on criteria, on the video domain, on the source of information, on the time of summarization, and on the machine learning technique. Depending on the type of methodology used by the personalized video summarization techniques for the summary production process, we classify the techniques into five major categories, which are feature-based video summarization, key frame selection, shot selection-based approach, video summarization using trajectory analysis, and personalized video summarization using clustering. We also compare personalized video summarization methods and present 37 datasets used to evaluate personalized video summarization methods. Finally, we analyze opportunities and challenges in the field and suggest innovative research lines.

Cerebral palsy (CP) presents challenges in movement and posture due to central nervous system damage, necessitating lifelong management. The COVID-19 pandemic has limited access to traditional treatments, increasing demand for home-based therapies and digital resources. This study analyzed the qualitative and quantitative aspects of YouTube videos focusing on CP therapy for children. In total, 95 videos were evaluated for content quality, therapeutic program efficacy, and popularity. Most videos were uploaded by health professionals. Neuromotor therapy types varied, with Bobath therapy being prominent. The quality assessments revealed moderate to high reliability in video content; nonetheless, shortcomings in addressing uncertainties were observed. Therapeutic programs often lack crucial details such as intensity and outcome assessment methods. No significant differences were found between professional and non-professional uploads. Classifiable videos based on exercise type, in contrast to the types of neuromotor therapy, exhibited better therapeutic quality than unclassified ones. Notably, video popularity did not correlate with quality. This study underscores the need for improved educational content on YouTube, particularly in providing comprehensive therapeutic information for CP management. Further refinement of evaluation tools is essential for assessing the rationale behind neuromotor therapeutic modalities for children with CP.

The classifier system proposed in this work combines the dissimilarity spaces produced by a set of Siamese neural networks (SNNs) designed using 4 different backbones, with different clustering techniques for training SVMs for automated animal audio classification. The system is evaluated on two animal audio datasets: one for cat and another for bird vocalizations. Different clustering methods reduce the spectrograms in the dataset to a set of centroids that generate (in both a supervised and unsupervised fashion) the dissimilarity space through the Siamese networks. In addition to feeding the SNNs with spectrograms, additional experiments process the spectrograms using the Heterogeneous Auto-Similarities of Characteristics. Once the similarity spaces are computed, a vector space representation of each pattern is generated that is then trained on a Support Vector Machine (SVM) to classify a spectrogram by its dissimilarity vector. Results demonstrate that the proposed approach performs competitively (without ad-hoc optimization of the clustering methods) on both animal vocalization datasets. To further demonstrate the power of the proposed system, the best stand-alone approach is also evaluated on the challenging Dataset for Environmental Sound Classification (ESC50) dataset. The MATLAB code used in this study is available at https://github.com/LorisNanni.

This study provides an evaluation of a web-based platform for game management and sales, developed using PHP, MySQL, and SASS. The development process utilized the SCRUM methodology, concentrating on essential modules such as user management, game catalog, payment processing, and technical support. The platform's performance was assessed using Google's Lighthouse tool, which evaluates four critical areas: performance, accessibility, best practices, and SEO. The results demonstrated exceptional performance with a score of 99/100 and perfect adherence to best practices with a score of 100/100, reflecting high efficiency and compliance with web development standards. Accessibility received a score of 83/100, indicating potential areas for improvement, while SEO achieved a score of 91/100, suggesting effective search engine optimization. The findings reveal that the platform exhibits high levels of optimization and operational efficiency. However, there remains an opportunity to enhance accessibility features. This study highlights the significance of rigorous web development practices and optimization efforts in achieving superior performance and user experience in web-based systems.

In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose factorising the final task of audio transcription into multiple intermediate tasks in order to improve the training performance when dealing with this kind of low-resource datasets. We evaluate three data-efficient approaches of training a stacked convolutional and recurrent neural network for the intermediate tasks. Our results show that different methods of training have different advantages and disadvantages.

Dictionary Learning (DL) and Sparse Representation (SR) based Classifier have impacted greatly on the classification performance and has had good recognition rate on image data. In Video Semantic Analysis (VSA), the local structure of video data contains more vital discriminative information needed for classification. However, this has not been fully exploited by the current DL based approaches. Besides, similar coding findings are not being realized from video features with the same video category. Based on the issues stated afore, a novel learning algorithm, called Sparsity based Locality-Sensitive Discriminative Dictionary Learning(SLSDDL) for VSA is proposed in this paper. In the proposed algorithm, a discriminant loss function for the category based on sparse coding of the sparse coefficients is introduced into structure of Locality-Sensitive Dictionary Learning (LSDL) algorithm. Finally, the sparse coefficients for the testing video feature sample are solved by the optimized method of SLSDDL and the classification result for video semantic is obtained by minimizing the error between the original and reconstructed samples. The experiment results show that, the proposed SLSDDL significantly improves the performance of video semantic detection compared with the comparative state-of-the-art approaches. Moreover, the robustness to various diverse environments in video is also demonstrated, which proves the universality of the novel approach.

Well-being is one of the pillars of positive psychology, which is known to have positive effects not only on the personal and professional lives of individuals, but also on teams and organizations. Understanding and promoting individual well-being is essential for staff health and long-term success, but current tools for assessing subjective well-being rely on time-consuming surveys and questionnaires, which limit the possibility of providing the real-time feedback needed to raise awareness and change individual behavior. This paper proposes a framework for understanding the process of non-verbal communication in teamwork, using video data to identify significant predictors of individual well-being in teamwork. It relies on video acquisition technologies and state-of-the-art artificial intelligence tools to extract individual, relative, and environmental characteristics from panoramic video. Statistical analysis is applied to each time series, leading to the generation of a dataset of 125 features, which are then linked to PERMA (Positive Emotion, Engagement, Relationships, Meaning, and Accomplishments) surveys developed in the context of positive psychology. Each pillar of the PERMA model is evaluated as a regression or classification problem using machine learning algorithms. Our approach was applied to a case study, where 80 students collaborated in 20 teams for a week on a team task in a face-to-face setting. This enabled us to formulate several hypotheses identifying factors influencing individual well-being in teamwork. These promising results point to interesting avenues for research, for instance fusing different media for the analysis of individual well-being in teamwork.

This study introduces an original comprehensive system centered on identifying specific terms that indicate a user's position, particularly the discrete values representing latitude and longitude. This system not only detects these terms but also retrieves the corresponding numerical data for accurate and efficient determination of locations. The importance of this study can be applied various fields, notably aiding offline operations of military personnel, who often lack internet access. In such scenarios, precise awareness of location is vital for strategic manoeuvres, rescue operations, and navigating unfamiliar landscapes. The system allows these personnel by allowing them to extract exact location coordinates from spoken terms, thereby enhancing their awareness even in challenging surroundings. Apart from its military utility, the project holds broader significance. Teams responding to emergencies, personnel involved in disaster management, and exploratory missions can all gain from this technology during disruptions in communication infrastructure. Furthermore, travelers, adventurers, and outdoor enthusiasts can utilize this system to accurately determine their positions in remote areas without relying on online maps. We used offline speech recognition techniques to precisely transcribe spoken terms, achieving an accuracy of over 91.3% and a word error rate of 4.2%. For sound recognition, the OpenAI Whisper model was used, and a conversion process from SpeechRecognition to AudioSegmentation was implemented, followed by transforming the audio into .wav format, we have also developed the interface of the app to use it efficiently using Streamlit. This was done to ensure seamless compatibility with the Whisper model and uninterrupted audio input. By training the system to identify specific linguistic linked to location, it achieves robust detection and extraction of relevant terms. This approach eliminates the necessity for constant internet connectivity, rendering it exceptionally useful in remote, offline, and resource-limited situations.

Detecting and understanding emotions is critical for our daily activities. As emotion recognition (ER) systems develop, we start looking at more difficult cases than just acted adult audio-visual speech. In this work, we investigate automatic classification of audio-visual emotional speech of children. Our interest is, specifically, in the improvement of the utilization of the cross-modal relationships between the selected modalities: video and audio. To underscore the importance of developing ER systems for the real-world environment, we present a corpus of children’s emotional audio-visual speech that we collected. We select a state-of-the-art model as a baseline for the purposes of comparison and present several modifications focused on a deeper learning of the cross-modal relationships. By conducting experiments with our proposed approach and the selected baseline model, we observe a relative improvement in performance by 2%. Finally, we conclude that focusing more on the cross-modal relationships may be beneficial for building ER systems for child-machine communications and the environments where qualified professionals work with children.

This paper proposes a method for recognizing audio events in urban environments that combines handcrafted audio features with a deep learning architectural scheme (Convolutional Neural Networks, CNNs), which has been trained to distinguish between different audio context classes. The core idea is to use the CNNs as a method to extract context-aware deep audio features that can offer supplementary feature representations to any soundscape analysis classification task. Towards this end, the CNN is trained on a database of audio samples which are annotated in terms of their respective "scene" (e.g. train, street, park), and then it is combined with handcrafted audio features in an early fusion approach, in order to recognize the audio event of an unknown audio recording. Detailed experimentation proves that the proposed context-aware deep learning scheme, when combined with the typical handcrafted features, leads to a significant performance boosting in terms of classification accuracy. The main contribution of this work is the demonstration that transferring audio contextual knowledge using CNNs as feature extractors can significantly improve the performance of the audio classifier, without need for CNN training (a rather demanding process that requires huge datasets and complex data augmentation procedures).

In recent years, with the development of social media, people are more and more inclined to upload text, pictures and videos on the platform to express their personal emotions, thus the number of short videos is increasing and becoming the first choice for people to socialize. Unlike the traditional way, people can convey their personal emotions and opinions through media other than words, such as video images, etc. for external information. Therefore, the expression and analysis of emotions is not only through text, but also through the analysis of emotional needs in images and videos, and the research scholars have customized products for individual users. Compared with pure text content, video information can more intuitively express users' happiness, anger and sorrow, thus short video-related applications have gained more and more popularity among Internet users in recent years. However, not all short videos on social networking sites can accurately express users' emotions, and related text information can more accurately assist sentiment analysis and thus improve accuracy. However, short video sentiment analysis based on video frame images is inaccurate in some scenarios, such as when expressing tears of joy, the sentiment expressed by the user's facial expression and voice are different, which will cause errors in the analysis of sentiment. As a result, researchers began to consider multimodal sentiment analysis to reduce the impact of the above scenarios on short video sentiment analysis. This paper focuses on proposing a sentiment analysis method for short videos. We first propose a residual attention model to make full use of the information in audio to classify the emotions contained in them. Then the text information in the dataset is classified by feature extraction. The key to extract features from text information is not only to retain the semantic information of the text, but also to explore the potential emotional information in the text, so as to ensure the integrity of the text information features. The experiments show that the sentiment analysis model proposed in this paper is more superior than the baselines.

Tropical storm Nate, which was a powerful hurricane prior to landfall along the Alabama coast, traversed north towards our instrumented site in Hunstville, AL. The rain bands lasted 18 h and the 2D-video disdrometer (2DVD) captured the event which was shallow and indicative of pure warm rain processes. Measurements of raindrop size, shape and velocity distributions are quite rare in pure warm rain and are expected to differ from cold rain processes. In particular, asymmetric shapes due to drop oscillations and their impact on polarimetric radar signatures in warm rain have not been studied so far. Recently, the 2DVD data has been used for 3D reconstruction of asymmetric raindrop shapes but their fraction (relative to the more common oblate shapes) in warm rain has yet to be ascertained. Here we compute the scattering matrix drop-by-drop using Computer Simulation Technology integral equation solver for drop sizes>2.5 mm. From the scattering matrix elements, the polarimetric radar observables are simulated by integrating over 1 minute consecutive segments of the event. These simulated values are compared with dual-polarized C-band radar data located at 15 km range from the 2DVD site to evaluate the contribution of the asymmetric drop shapes.

Characters are one of the most important elements in composing digital animation. The appear-ance and voice of a character should be designed to express the personality and values of the character. However, it is not easy for animation producers to harmoniously match the appear-ance and voice of a character. Advances in deep learning technology have made it possible to overcome this limitation. To achieve this, firstly, an audio-visual dataset of characters is required. In this study, we construct and verify a Korean audio-visual dataset consisting of frontal face im-ages of various characters and short voice clips. We developed an application that can automati-cally extract the frontal face image and a short voice clip of a character by collecting videos up-loaded to YouTube. Through this, a dataset consisting of a total of 1,522 face images and a total of 7,999 seconds of voice clips was built based on 490 characters. Furthermore, we automatically la-bel characters by gender and age to validate the dataset. The dataset built in this study is expected to be used in various deep learning fields, such as classification, generative adversarial networks, and speech synthesis.

The focus of this research is to analyze the results of encrypting audio using various authenticated encryption algorithms implemented in the Python cryptography library for ensuring authenticity and confidentiality of the original contents. The Advanced Encryption Standard (AES) is used as the underlying cryptographic primitive in conjunction with various modes including Galois Counter Mode (GCM), Counter with Cipher Block Chaining Message Authentication Code (CCM), and Cipher Block Chaining (CBC) with Keyed-Hashing for encrypting a relatively small audio file. The resulting encrypted audio shows similarity in the variance when encrypting using AES-GCM and AES-CCM. There is a noticeable reduction in variance of the performed encodings and an increase in the amount of time it takes to encrypt and decrypt the same audio file using AES-CBC with Keyed-Hashing. In addition, the corresponding encrypted using this mode audio spans a longer duration. As a result, AES should either have GCM or CCM for an efficient and reliable authenticated encryption integration within a workflow.

Abstract: Passive acoustic monitoring (PAM) is a non-invasive technique to supervise the wildlife. Acoustic surveillance is preferable in some situation such as in the case of marine mammals, when the animals spend most of their time underwater, making it hard to obtain their images. Machine learning is very useful for PAM, for example, to identify species based on audio recordings. But some care should be taken to evaluate the capability of a system. We define PAM-filters as the creation of the experimental protocols according to the dates and locations of the recordings, aiming to avoid the use of the same individuals, noise and recording devices in both training and test sets. A random division of a database present accuracies much higher than accuracies obtained with protocols generated with PAM-filter. Although we use the animal vocalizations, in our method we convert the audio into spectrogram images, after that, we describe the images using the texture. Those are well-known techniques for audio classification, and they have already been used for species classification. Also, we perform statistical tests to demonstrate the significant difference between accuracies generated with and without PAM-filters with several well-known classifiers. The configuration of our experimental protocols and the database were made available online.

This paper presents an approach to teacher identity heritage as result of the implementation of a research device created through Arts-based Research (ABR) methods, specifically with video elicitation and video essay used as research tools. Two main objectives were raised. The first one, to establish the real relevance of focusing performance on teacher identity. The second one, testing a new methodological proposal specifically designed for this purpose, but still useful in other contexts where heritage identity is as present as in teaching. The device, Body-camera, involves a process that allows new ways to understand the creation of identities using video to encourage the production of new meanings by visual and oral data. The participants were teachers in training during their internship period. Some notions about teachers' identity heritage were revealed, and also preserved, firstly, through personal perspectives by video elicitations and secondly, through collective perspectives by video essays. Both are video structures used in ABR which mix creative experience, memories, life experiences, relationships and links that shape the teachers’ professional identity.

Primary Ciliary Dyskinesia (PCD) is a rare genetic disorder characterized by alterations in motile cilia func-tion. The diagnosis of PCD is challenging due to the lack of standardized methods in clinical practice. High-speed video microscopy analysis (HSVA) directly evaluates ciliary beat frequency (CBF) in PCD. Recently, open-source ciliary analysis software applications have shown promise in measuring CBF accurately. How-ever, there is limited knowledge about the performance of different software applications, creating a gap in understanding their comparative effectiveness in measuring CBF in PCD. We compared two open-source software applications, CiliarMove and Cilialyzer, against the manual count method. We used videos rec-orded at high-speed of nasal ciliary brush samples from PCD patients and healthy controls. All three meth-ods showed lower median CBF values in PCD patients than healthy controls. CiliarMove and Cilialyzer identified lower CBF in PCD patients, similar to the manual count. Cilialyzer, CiliarMove and manual count demonstrated statistical significance (p-value < 0.0001) in the difference of median CBF values be-tween PCD and healthy controls. These findings support the utility of open-source software-based analysis tools. Further studies are needed to validate these findings with other genetic variants and identify the op-timal software for accurate CBF measurement in PCD.

One of the most important problems, which public health is called to face, is obesity. The World Health Organization (WHO) underlines that worldwide more than 380 million of overweight or obese children and adolescents exist. Although obesity is a multifactorial disease, excessive use of the screen seems to act in a way that affects obesity. The purpose of this systematic literature review is to study of the major problem, obesity in teenagers and its association with the hours of entertainment(referring to excessive hours of television use and viewing, video games and social media).In the present systematic literature review was carried out search for sources, through the scientific databases PubMed, ScienceDirect, and Scopus for the period from 2010 to 2022.This systematic review provides public health evidence regarding the positive association of excessive screen time and of obesity and overweight in adolescents.

Social communication skills, especially eye contact and joint attention, are highly impaired in autism spectrum disorder (ASD) and predict functional outcomes. Applied Behavior Analysis is one of the best evidence-based treatments for ASD, but it is not accessible to most families in low- and middle-income countries (LMICs) as it is a costly and intensive and needs to be delivered by highly specialized professionals. Parental training has emerged as an effective alternative. The aim of this study was to test the efficacy of a parental intervention group via video modeling to acquire eye contact and joint attention. Four graded measures of eye contact and joint attention (full physical prompt, partial physical prompt, gestural prompt, and independent) were assessed in 34 children with ASD and intellectual disability (ID). There was a progressive reduction in the level of prompt required over time to acquire eye contact and joint attention, and a positive correlation between the time of exposure to the intervention and acquisition of the abilities. This parent training using video modelling to teach eye contact and joint attention skills to children with ASD and ID is a low-cost intervention that can be applied in low- resource settings.

In this paper, we propose a robust video understanding model for activity recognition by learning the actor’s pair-wise correlations and relational reasoning, exploiting spatial and temporal information. In order to measure the similarity between the pair appearances and construct an actor relations map, the Zero Mean Normalized Cross-Correlation (ZNCC) and the Zero Mean Sum of Absolute Differences(ZSAD) is proposed to allow the Graph Convolution Network (GCN) to learn how to distinguish group actions. We recommend that MNASNet be used as the backbone to retrieve features. Experiments show a 38.50% and 23.7% reduction in training time in the 2-stage training process along with a 1.52% improvement in accuracy against traditional methods.

The operations of digitization, transmission and storage of medical data, particularly images require increasingly effective encoding methods not only in terms of compression ratio and flow of information but also in terms of visual quality. At first, there was DCT (discrete cosine transform) then DWT (discrete wavelet transform) and their associated standards in terms of coding and image compression. After that, the 2nd generation wavelets seeks to be positioned and confronted to the image and video coding methods currently used. It is in this context that we suggested a method combining bandelets and SPIHT (set partitioning in hierarchical trees) algorithm. There are two main reasons for our approach: the first lies in the nature of the bandelet transform to take advantage by capturing the geometrical complexity of the image structure. The second reason stems in the suitability of encoding the bandelet coefficients by the SPIHT encoder. Quality measurements shows that in some cases (for low bit rates) the performances of the proposed coding compete with the well-established ones and opens up new application prospects in the field of medical imaging.

Primary ciliary dyskinesia (PCD) is an inherited disorder that impairs motile cilia, essential for respiratory health, with a reported prevalence of 1 in 16,309 within Hispanic populations. Despite having the RSPH4A [c.921+3_921+6del (intronic)] founder mutation in 70% of Puerto Rican patients, the characterization of the ciliary dysfunction remains unidentified due to the unavailability of advanced diagnostic modalities like High-Speed Video Microscopy Analysis (HSVA). Our study implemented HSVA for the first time on the island as a tool to better diagnose and characterize the RSPH4A [c.921+3_921+6del (intronic)] founder mutation in Puerto Rican patients. By applying HSVA, we analyzed the ciliary beat frequency (CBF) and pattern (CBP) in native Puerto Rican patients with PCD. Our results showed decreased CBF and a rotational CBP linked to the RSPH4A founder mutation in Puerto Ricans, presenting a novel diagnostic marker that could be implemented as an axillary test into the PCD diagnosis algorithm in Puerto Rico. The integration of HSVA technology in Puerto Rico substantially enhances the framework for PCD evaluation and diagnosis, facilitating prompt detection and early intervention for improved disease management. This initiative, demonstrating the potential of HSVA as an adjunctive test within the PCD diagnostic algorithm, could serve as a blueprint for analogous developments throughout Latin America.

We describe a multi-resolution approach for audio classification and illustrate its application to the open data set for environmental sound classification. The proposed approach utilizes a multi-resolution based ensemble consisting of targeted feature extraction of approximation (coarse scale) and detail (fine scale) portions of the signal under the action of multiple transforms. This is paired with an automatic machine learning engine for algorithm and parameter selection and the LSTM algorithm, capable of mapping several sequences of features to a predicted class membership probability distribution. Initial results show an improvement in multi-class classification accuracy.

The falling cost of cameras, the advancement of AI based computer vision algorithms, and powerful hardware accelerators for deep learning have enabled wide-spread deployment of surveillance cameras with the ability to automatically analyze streaming video feeds to detect events of interest. While streaming video analytics is currently largely done in the cloud, edge computing has emerged as a pivotal component due to its advantages of low latency, reduced bandwidth, and enhanced privacy. However, a distinct gap persists between the state-of-the-art computer vision algorithms, and successful practical implementation of edge-based streaming video analytics systems. This paper presents a comprehensive review of more than 30 research papers published over the last 6 years on edge video analytics systems. The papers are analyzed across 17 distinct dimensions. Unlike prior reviews, we examine each system holistically, identifying their strengths and weaknesses in diverse implementations. Our findings suggest that certain critical topics necessary for the practical realization of edge video analytics systems are not sufficiently addressed in current research. Based on these observations, we propose research trajectories across short, medium, and long term horizons. Additionally, we explore trending topics in other computing areas that can significantly impact the field of edge video analytics.

Accurate traffic simulation models play a crucial role in developing intelligent transport systems that offer timely traffic information to users and efficient traffic management. However, calibrating these models to represent real-world traffic conditions accurately poses a significant challenge due to the dynamic nature of traffic flow and the limitations of traditional calibration methods. This article introduces a machine learning-based approach to calibrate macroscopic traffic simulation models using real-time traffic video stream data. By leveraging computer vision technologies to extract key traffic parameters from video streams, the approach demonstrated a notable improvement in aligning the generated data from the calibrated simulation model with car sensor data, achieving an average improvement of over 50% compared to the uncalibrated macroscopic model. Moreover, there was a substantial reduction in data drift for the machine learning model integrated into the virtual transport space using vehicle-to-everything technology, resulting in a more than fourfold decrease in the average absolute error of the model.

Spherical harmonic (SH) interpolation is a commonly used method to spatially up-sample sparse Head Related Transfer Function (HRTF) datasets to denser HRTF datasets. However, depending on the number of sparse HRTF measurements and SH order, this process can introduce distortions in high frequency representation of the HRTFs. This paper investigates whether it is possible to restore some of the distorted high frequency HRTF components using machine learning algorithms. A combination of Convolutional Auto-Encoder (CAE) and Denoising Auto-Encoder (DAE) models is proposed to restore the high frequency distortion in SH interpolated HRTFs. Results are evaluated using both Perceptual Spectral Difference (PSD) and localisation prediction models, both of which demonstrate significant improvement after the restoration process.

In response to the growing challenges in drone security and airspace management, this study introduces an advanced drone classifier, capable of detecting and categorizing Unmanned Aerial Vehicles (UAVs) based on acoustic signatures. Utilizing a comprehensive database of drone sounds across EU-defined classes (C0 to C3), this research leverages machine learning (ML) techniques for effective UAV identification. The study primarily focuses on the impact of data augmentation methods—pitch shifting, time delays, harmonic distortion, and ambient noise integration—on classifier performance. These techniques aim to mimic real-world acoustic variations, thus enhancing the classifier's robustness and practical applicability. Results indicate that moderate levels of augmentation significantly improve classification accuracy. However, excessive application of these methods can negatively affect performance. The study concludes that sophisticated acoustic data augmentation can substantially enhance ML-driven drone detection, providing a versatile and efficient tool for managing drone-related security risks. This research contributes to UAV detection technology, presenting a model that not only identifies but also categorizes drones, underscoring its potential for diverse operational environments.

Purpose: This study aims to provide a foundational understanding of patient-centric perceptions of telemedicine implementation in rural Minnesota. Methods: This retrospective cohort study utilized a mail questionnaire to assess patient attitudes and behaviors regarding telemedicine during the emergency response to COVID-19. The target population was patients of a Primary Care clinic in eastern Minnesota. Descriptive statistics were used to assess respondents’ level of agreement with survey items scored on a 0-10 scale. Results: A majority of the respondents indicated that they were satisfied with using telemedicine (73.96%); that they gained an additional sense of control over their health condition due to the availability of telemedicine (52.08%); that they would support the use of telemedicine in the future (61.05%); that telemedicine increased access to care (65.63%); telemedicine was preferred over the clinic (61.46%), and that they would purchase new equipment to increase the utility of telemedicine services (54.17%). 51.04% of the respondents indicated a 10/10 level of satisfaction with telemedicine services. 48.96% indicated the strongest level of disagreement related to difficulty using telemedicine or a preference for in-person clinical appointments. Conclusions: Patients were found to have favorable perceptions of telemedicine overall. Though providers continue to recognize the benefit of face-to-face visits, their patients show an increased predilection for virtual care and telemedicine will likely remain an essential tool for providers to reach patients who would otherwise choose not to seek care.

The problem of event detection in general noisy signals arises in many applications; usually, either a functional form for the event is available, or a previous annotated sample with instances of the event that can be used to train a classification algorithm. There are situations, however, where neither functional forms nor annotated samples are available; then it is necessary to apply other strategies to separate and characterize events. In this work, we analyze 15 minute-long samples of an acoustic signal, and are interested in separating sections, or segments, of the signal which are likely to contain significative events. For that, we apply a sequential algorithm with the only assumption that an event alters the energy of the signal. The algorithm is entirely based on Bayesian methods.

Background: The use of wearable devices has burgeoned over the past decade, including wearables for infants and young children. Typically, such devices assess a single modality, and few have undergone scientific validation. To address this gap, we developed an infant wearable platform, LittleBeats™, that integrates electrocardiogram (ECG), motion, and audio sensors on a single printed circuit board to permit daylong remote assessments of infants and caregivers in home environments. Objective: Complementing our prior reports focused on LittleBeats™ data collected among infants and children in the home context, our main objective here is to present a technical validation of each sensor modality against established laboratory protocols and gold-standard equipment. Materials and Methods: We conducted five studies, including assessments of (a) interbeat interval (IBI) data obtained from the LittleBeats™ ECG sensor versus the gold-standard BIOPAC among adults (Study 1, N=16) and infants (Study 2, N=5), (b) performance of automated activity recognition (upright vs. walk vs. glide vs. squat ) among adults using accelerometer data obtained from LittleBeats™ versus Google Pixel 1 smartphone (Study 3, N=12), and (c) performance of speech emotion recognition (SER; Study 4, N=8) and automatic speech recognition (ASR; Study 5, N =12) algorithms among adult samples using audio data from LittleBeats™ versus smartphone. Results: Results for IBI data obtained from the LittleBeats™ ECG sensor indicate acceptable mean absolute percent error (MAPE) rates for both the adults (MAPE = 5.29% to 5.97%; Study 1) and infants (MAPE =0.96% to 1.66%; Study 2) across low- and high-challenge sessions, as well as expected patterns of change in respiratory sinus arrythmia (RSA) across sessions. For activity recognition (Study 3), LittleBeats™ data showed good to excellent performance (Accuracy = 89%, F1-score=88%; Cohen’s kappa =.79), although the smartphone outperformed LittleBeats™ by less than 4%. Finally, performance on the SER applied to LittleBeats™ versus smartphone audio data (Study 4) indicated comparable performance, with a matched-pairs test indicating no significant difference in error rates (p=.26). On the ASR task (Study 5), the best performing algorithm yielded relatively low word error rates, although LittleBeats™ (4.16%) versus smartphone (2.73%) error rates are somewhat higher. Discussion: Taken together, results from these controlled laboratory studies conducted predominantly with adults indicate that the LittleBeats™ sensors yield data quality that is largely comparable to those obtained from gold-standard devices and protocols that have been used extensively in prior research. The advantages of the LittleBeats™ platform is the (a) integration of multiple sensors into one platform that was (b) designed specifically for use with infants and young children. Leveraging data from the multiple modalities and fine-tuning postprocessing steps to further increase data quality, combined with assessing data quality among infants and young children in their natural environments, will be key next steps in this research program.

The recent public release of the generative AI language model ChatGPT has captured the public imagination and has resulted a rapid uptake and widespread experimentation by the general public and academia alike. The number of academic publications focusing on the capabilities as well as practical and ethical implications of generative AI has been growing exponentially. One of the concerns with this unprecedented growth in scholarship related to generative AI, in particular ChatGPT, is that in most cases the raw data, that is the text of the original ‘conversations,’ have not been made available to the audience of the papers and thus cannot be drawn on to assess the veracity of the arguments made and the conclusions drawn therefrom. This paper provides a protocol for the documentation and archiving of these raw data.

Superpixels are a representation of still images as pixel grids because of their more meaningful information compared with atomic pixels. However, their usefulness for video classification has been given little attention. In this paper, rather than using spatial RGB values as low-level features, we use optical flows mapped into hue-saturation-value (HSV) space to capture rich motion features over time. We introduce motion superpixels, which are superpixels generated from flow fields. After mapping flow fields into HSV space, independent superpixels are formed by iteration of seeded regions. Every grid of a motion superpixel is tracked over time using nearest neighbors in the histogram of flow (HOF) for consecutive flow fields. To define the temporal representation, the evolution of three features within the superpixel region, namely the HOF, HOG, and the center of superpixel mass are used as descriptors. The bag of features algorithm is used to quantify final features, and generalized histogram-kernel support vector machines are used as learning algorithms. We evaluate the proposed superpixel tracking on first-person videos and action sports videos.

The Covid-19 pandemic caused a shift in teaching practice towards blended learning for many Higher Education institutions. This led to the rapid adoption of certain digital technologies within existing teaching structures as a means to meet student access needs and facilitate learning. Integration of these technologies caused numerous challenges for practitioners and often provided mixed results. This paper is an attempt to summarise and extend pre-Covid pedagogical research to leverage digital immersive technologies for blended teaching in the post-pandemic era. Focus is given towards the evolution of Virtual Learning Environments through elements of immersive audio-visual technologies, which are shown to be effective when coupled in a blended approach. It is both a review of these methodologies and a case study of the I-Ulysses: Virtual Learning Environment as a point of comparison for evaluating the review.

Video self-supervised learning (VideoSSL) offers significant potential for reducing annotation costs and enhancing a wide range of downstream tasks in video understanding. The ultimate goal of VideoSSL is to achieve human-level video intelligence across a spectrum of tasks, from low-level tasks such as pixel temporal correspondence to high-level complex spatio-temporal tasks like action recognition. However, most existing VideoSSL methods focus on isolated aspects of this spectrum and fail to integrate different levels of task complexity. Our study presents the first comprehensive survey that connects all families of VideoSSL methods. We provide a detailed review of the full spectrum of VideoSSL, from low to high levels, by conceptually linking their self-supervised learning objectives and including a comprehensive categorization. Our extensive evaluation highlights the strengths and limitations of each SSL objective across various downstream task families. We also detail the challenges in current VideoSSL research such as data curation, interpretability, deployment, and privacy concerns, an area that previous surveys have not thoroughly explored. In addressing these challenges, we recognize the strengths of existing methods in addressing these challenges and outline future directions for research.

Objectives: Chylothorax is a relatively rare condition of lymphatic fluid accumulation in the thoracic cavity due to a leakage from the thoracic duct or its tributaries. Patients present with dyspnea, malnutrition, and immunosuppression. Treatment can be conservative or surgical, depending on etiology and clinical course. The optimal management algorithm for chylothorax is still controversial. Methods: This is a retrospective study of all patients with chylothorax treated at our Department of Thoracic Surgery during the 10-year period. Results: A total of 14 patients were identified for the study. Nine patients had chylothorax after lung or esophageal cancer surgery. Four patients had chylothorax in advanced lymphoma. One patient had chylothorax after blunt chest trauma. A conservative approach was initiated in most patients (92%), including pleural drainage, nil per mouth, total parenteral nutrition, and somatostatin 0.1 mg bid subcutaneously. Surgical treatment was indicated in patients with thoracic drain production >800 mL per day beyond the fifth day of treatment and those with blunt thoracic trauma. Two patients had thoracic duct ligation via right-sided thoracotomy, and five patients had video-assisted thoracoscopic thoracic duct ligation with the immediate arrest of chylous leakage. Conclusion: Chylothorax should be treated conservatively initially. Surgical treatment should not be delayed in case of failure beyond the fifth day. In our series of patients, a video-assisted thoracoscopic approach for thoracic duct ligation proved to be minimally invasive, highly efficient, and well tolerated by patients and, therefore, should be the preferable route of surgical treatment.

The paper explores the potential of a low-cost advanced video-based technique for the assessment of structural damage induced to buildings by seismic loading. A low-cost high-speed video camera was utilized for motion magnification (MM) processing of footages of a two-story reinforced concrete frame building subjected to shaking table tests. The damage after seismic loading was estimated by analyzing the dynamic behavior (i.e. in terms of modal parameters) and the structural deformations of the building in the MM videos. The results by MM were compared for method validation to damage assessment obtained by the analyses of conventional accelerometers and high-precision optical markers tracked by a passive 3D motion capture system. Also, 3D laser scanning to obtain an accurate survey of the building geometry before and after the seismic tests was carried out. In particular, accelerometers were also processed and analyzed by using several stationary and non-stationary techniques with the aim to analyze the linear behavior of the undamaged structure and the nonlinear structural behavior during damaging shaking table tests. The proposed MM-based procedure provided accurate estimate of the main modal frequency and the damage location through the analysis of modal shapes, which were confirmed by advanced analyses of accelerometric data.

Along with the popularity of the Internet, people are exposed to more and more ways of micro-videos, and a huge amount of micro-video data has emerged. micro-videos have gradually become the Internet content preferred by the public, and a large number of micro-video apps have also emerged, such as Tiktok and Kwai. Intelligent classification and mining of micro-videos can greatly enhance user experience, improve business operation efficiency and enhance user experience. Through deep intelligent analysis and mining of micro-videos, important information in micro-videos can be extracted to provide an important basis for beautifying videos, content appreciation, video recommendation, content search, etc. In the past, content understanding for short videos often used human work annotation, but in recent years, with the great success of deep convolutional neural networks in image recognition, short video content understanding based on this method has gradually developed. Nowadays, most recognition algorithms extract the feature representation of each frame independently and then fuse them. However, while extracting the feature representation, some low-level semantic features are lost, which makes the algorithm unable to accurately distinguish the category of the video. At present, the algorithm of micro-video recognition based on deep learning has surpassed the iDT algorithm, making these traditional methods fade out of people’s view. In this paper according to the micro-video classification task, a new network model is proposed to concatenate features of each modality into the overall features of various modalities through the network, and then fuse the various modal features with the attention mechanism to obtain the whole micro-video features, which will be used for classification. In order to verify the effectiveness of the algorithm proposed in this paper, experiments are conducted in the public dataset, and it is shown the effectiveness of our model.

Video editing is a high-required job, for it requires skilled artists or workers equipped with plentiful physical strength and multidisciplinary knowledge, such as cinematography, aesthetics. Thus gradually, more and more researches focus on proposing semi-automatical and even fully automatical solutions to reduce workloads. Since those conventional methods are usually designed to follow some simple guidelines, they lack flexibility and capability to learn complex ones. Fortunately, the advances of computer vision and machine learning make up the shortages of traditional approaches and make AI editing feasible. There is no survey to conclude those emerging researches yet. This paper summaries the development history of automatic video editing, and especially the applications of AI in partial and full workflows. We emphasizes video editing and discuss related works from multiple aspects: modality, type of input videos, methology, optimization, dataset, and evaluation metric. Besides, we also summarize the progresses in image editing domain, i.e., style transferring, retargeting, and colorization, and seek for the possibility to transfer those techniques to video domain. Finally, we give a brief conclusion about this survey and explore some open problems.

The automatic classification of bird sounds is an ongoing research topic and several results have been reported for the classification of selected bird species. In this contribution we use an artificial neural network fed with pre-computed sound features to study the robustness of bird sound classification. We investigate in detail if and how classification results are dependent on the number of species and the selection of species in the subsets presented to the classifier. In more detail, a bag-of-birds approach is employed to randomly create balanced subsets of sounds from different species for repeated classification runs. The number of species present in each subset is varied between 10 and 300, randomly drawing sounds of species from a dataset of 659 bird species taken from Xeno-Canto database. We observe that the shallow artificial neural network trained on pre-computed sound features is able to classify the bird sounds relatively well. The classification performance is evaluated using several common measures such as precision, recall, accuracy, mean average precision and area under the receiver operator characteristics curve. All of these measures indicate a decrease in classification success as the number of species present in the subsets is increased. We analyze this dependence in detail and compare the computed results to an analytic explanation assuming dependencies for an idealized perfect classifier. Moreover, we observe that the classification performance depends on the individual composition of the subset and varies across 20 randomly drawn subsets.

For the Remotely Piloted Aircraft Systems (RPAS) market to continue its current growth rate, cost-effective "Detect and Avoid" systems that enable safe beyond visual line of sight (BVLOS) operations are critical. We propose an audio-based "Detect and Avoid" system, composed of microphones and an embedded computer, which performs real-time inferences using a sound event detection (SED) deep learning model. Two state-of-the-art SED models, YAMNet and VGGish, are fine-tuned using our dataset of aircraft sounds and their performances are compared for a wide range of configurations. YAMNet, whose MobileNet architecture is designed for embedded applications, outperformed VGGish both in terms of aircraft detection and computational performance. YAMNet's optimal configuration, with > 70% true positive rate and precision, results from combining data augmentation and undersampling with the highest available inference frequency (i.e. 10 Hz). While our proposed "Detect and Avoid" system already allows the detection of small aircraft from sound in real time, additional testing using multiple aircraft types is required. Finally, a larger training dataset, sensor fusion, or remote computations on cloud-based services could further improve system performance.

Developing efficient Artificial Intelligence (AI)-enabled system to substitute human role in non-destructive testing is an emerging topic of considerable interest. In this study, we propose a novel impact-echo analysis system using online machine learning, which aims at achieving near-human performance for assessment of concrete structures. Current computerized impact-echo systems commonly employ lab-scale data to validate the models. In practice, however, the echo patterns can be far more complicated due to varying geometric shapes and materials of structures. To deal with a large variety of unseen data, we propose a sequential treatment for echo characterization. More specifically, the proposed system can adaptively update itself to approaching human performance in impact-echo data interpretation. To this end, a two-stage framework has been introduced, including echo feature extraction and the model updating scheme. Various state-of-the-art online learning algorithms have been reviewed and evaluated for the task. To conduct experimental validation, we collected 10,940 echo instances from multiple inspection sites with each sample had been annotated by human experts with healthy/defective condition labels. The results demonstrated that the proposed scheme achieved favorable echo pattern classification accuracy with high efficiency and low computation load.

This research aimed to discover how to create a customer experience that includes FEEL, SENSE, THINK, ACT, and RELATE to increase satisfaction with the Subscription Video on Demand (SVoD) application. A descriptive quantitative method was used, and the sample was 423 respondents in Indonesia who had used the application for at least 1 month. Furthermore, this research used probability sampling using a technique for random sampling. Based on the data available, experience accounted for 0.509, or 50.9%, of the application satisfaction. With a beta value of 0.295, the FEEL variable was the only one in this study to significantly and positively affect customer satisfaction; the other variables, SENSE, THINK, ACT, and RELATE, had no discernible effects. It is anticipated that the theoretical foundation provided by this research will be beneficial to the entertainment industry, particularly the SVoD application sector. This includes the product and service development division that focuses on customer inner feelings and emotions.

Convolutional Neural Networks (CNNs) present drawbacks for modeling geometric transformations, such as scaling and rotation, caused by the convolution operation’s locality. Deformable convolution (DCON), a mechanism that substitutes standard convolution, increasing the receptive field to capture relevant features, is a promising approach to solve this drawback and improve the robustness of CNNs. However, the optimal way to replace the standard convolution with its deformable counterpart in a CNN model is unclear. In this study, we clarify this aseveration by conducting several experiments using deformable convolutions applied in the layers that conform a small four-layer CNN model. We also use deformable convolutions on the four-layers of several ResNet CNNs with depths 18, 34, 50, and 101. The models were tested in binary balanced classes with 2D data for image classification: Cats &amp; Dogs, EyesPACS, Spyders &amp; Chickens, and Shapes. After this testing, we evaluated DCON in 3D data for action recognition: UCF101 and Human2 (a dataset we compiled to control movement, clothing and background). The contribution of this research lies in a guideline to use DCON. It can be summarized as follows: if DCON is used on the first layers of the proposal of model (with simple features), the computational resources expressed as the quantity of Flops will tend to increase and produce bigger misclassification than the standard CNN. However, if the DCON is used at the end layers, the quantity of Flops used in the training and testing will decrease, and the classification accuracy will improve by up to 20% about the base model. Moreover, it gains robustness when using deformable convolutions because it can adapt to the region of interest. Also, the best kernel size of the DCON is three. It showed better results than size five. In the last case, the quantity of Flops increase quadratically, but their performance does not increase significantly. With these results, we propose a guideline to use the DCON and contribute to understanding the impact of DCON on the robustness of CNNs.

Short video addiction refers to a psychological dependency on short video applications, characterized by an intense attachment and an inability to control usage, leading to typical addiction symptoms. While its definition bears similarities to substance addiction, significant differences also exist. According to the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5), published in 2013, short video addiction has not yet been officially classified as an addiction disorder. To facilitate more in-depth and standardized research on short video addiction, it is essential to synthesize and organize existing studies on its theoretical foundations and mechanisms.

Background We aimed to evaluate the effectiveness of the ALRYNGO channel-type video laryngoscope with an AI-based glottis guidance system in senior emergency medicine residents for endotracheal intubation. Methods We enrolled twenty patients would be adequate for each device (direct laryngoscope, Pentax-AWS, and ALRYNGO). Before intubation, six senior residents wore a personal protective equipment. To randomize the device in this clinical study, a sealed envelope containing a device-specific identification card was utilized. When intubation began, the person who measured the intubation time divided the total intubation time into three-time intervals. The primary outcome was the intubation time. The secondary outcomes were the glottis view using the Cormack-Lehane grade (C-L grade) and the glottis guidance performance of ALRYNGO’s artificial intelligence. Results In Pentax-AWS and ALRYNGO, all intubations were successful, but the intubation time was longer than with the direct laryngoscope. And among the three, the ALRYNGO and Pentax-AWS had the highest frequency of C-L grade I (easiest intubation) at 80%, and the direct laryngoscope had the lowest frequency of 10%. Conclusions Even if healthcare professionals without experience with the channel-type video laryngoscope improve their performance on airway mannequins after training, their intubation performance may differ when applied to actual patients.

Primary spontaneous pneumothorax (PSP) is a pleural disease that abruptly affects healthy adolescents and young adults, representing a common thoracic disorder in this age group. This study aimed to investigate the necessity of preoperative chest tube insertion in patients with PSP and to re-evaluate current clinical treatment approaches. A retrospective review of medical records was conducted for children and young adults aged 14–30 years, diagnosed with PSP and who underwent Video-assisted thoracoscopic surgery (VATS) between January 2016 and December 2022 at Wonju Severance Christian Hospital. Patients were retrospectively divided into two groups based on their initial treatment: chest tube insertion and non-chest tube insertion. Clinical data including demographics, treatment details, and outcomes were collected and compared. Total 128 cases of PSP were included in the study. The total length of hospital stay was significantly shorter in the non-chest tube group (p=0.000), which was attributed to the omission of pre-operative chest tube insertions. No significant differences were observed between the two groups in terms of postoperative complications or recurrence rates. In cases of young patients with PSP, omitting pre-operative chest tube insertion may be a viable option if the patient is scheduled for VATS.

Video gamers can play to negate the psychological impact of stress (Pine et al., 2020), which may become problematic when users over-rely on the stress-relief potential of gaming. This study used a repeated-measures experimental design to investigate the relationships between stress, video gaming, and problematic video gaming behaviours in a convenience sample of 40 students at a UK university. Results indicated that positive affect increased and negative affect decreased, whilst a biological stress measure (Instantaneous Pulse Rate) also decreased after a short video gaming session (t(36) = 4.82, p < .001, d = 0.79). Results also suggest that video gaming can act as a short-term buffer against the physiological impact of stress. Further research should focus on testing individuals who have been tested for Gaming Disorder as opposed to a general population. Research could also utilise variations of the methodological framework used in this study to examine the intensity of a stress-relief effect under different social situations. The study’s findings in relation to published work are also discussed.

Introduction: Dental students’ use of online material to supplement learning has been studied, but educator awareness and reaction to the findings of this research is unknown. This small local study aimed to investigate dental students’ use of online content as a learning tool from an educator’s perspective.Methods: Educators at an Irish dental school completed a survey based on dental students’ use of online learning. Quantitative descriptive analyses were carried out as appropriate on the data collected, and a subsequent focus group was held to gain deeper insight into survey results. Data were analysed for themes by deductive and inductive coding methods.Results: This study found a sample of educators were aware of some student behaviours around online videos. Most educators correctly thought that students are likely to refer to online videos to prepare for dental procedures. Several educators believed that teachers should incorporate videos into their learning, but do not themselves upload or recommend online videos. Most recalled discussing accuracy and/or relevancy of online content with their students. Fewer thought that students would discuss contradictory videos with them. Focus group participants expressed concern over the accuracy of online content. This along with a lack of time were some reasons deterring them from referring students to online videos. Conclusions: An opportunity exists for dental educators and their students to have local dialogue around (1) student use, critical appraisal, and sharing of dental procedural video material; and (2) perceived benefits and challenges of incorporating both school-produced and online videos into teaching and learning. Although arguably non-generalizable beyond this context, this study may inform future research and serve to spark conversations within schools regarding video use for teaching clinical dental procedures.

In industry 4.0 era, video applications such as surveillance visual systems, video conferencing, or video broadcasting have been playing a vital role. In these applications, for manipulating and tracking objects in decoded video, the quality of decoded video should be consistent because it largely affects to the performance of the machine analysis. To cope with this problem, we propose a novel perceptual video coding (PVC) solution in which a full reference quality metric named Video Multimethod Assessment Fusion (VMAF) is employed together with a deep convolutional neural network (CNN) to obtain the consistent quality while still achieving the high compression performance. First of all, to achieve the consistent quality requirement, we propose a CNN model with an expected VMAF as input to adaptively adjust the quantization parameters (QP) for each coding block. Afterwards, to increase the compression performance, a Lagrange coefficient of Rate-Distortion optimization (RDO) mechanism is adaptively computed under Rate-QP and Quality-QP models. Experimental results show that the proposed PVC has achieved two targets simultaneously: the quality of video sequence is kept consistently with an expected quality level and the bit rate saving of the proposed method is higher than traditional video coding standards and relevant benchmark, notably with around 10% bitrate saving in average.

Previous research on video game player aggression has focused on violent content, while recent studies have examined competitive factors. Few research has examined the solely impacts of competitive factors in video games without violent content on aggression, and it is still unknown what neurological processes of these effects. The present study is the first to examine the the electrophysiological characteristics of short-term competitive video game exposure and aggression. Thirty-five participants played a video game in either competitive or solo mode for 15 minutes, followed by an ERP experiment based on the Oddball paradigm and the hot sauce paradigm to measure aggressive behavior. Results showed that playing competitive game mode was associated with faster judgment to aggressive words, larger P300 amplitudes, and selection of more chili powder. The P300 amplitude partially mediated the relationship between competitive game exposure and aggressive behavior. These findings support the general aggression model.

Non-invasive heart rate (HR) monitoring is important in clinical settings as it plays a critical role in diagnosing a range of health conditions and assessing well-being. Presently, the gold standards for HR measurement are all based on sensors which require skin contact. Apart from inconvenience, contact sensors have proven problematic in certain scenarios – they cannot be used when mechanical isolation of the patient is imperative (burn victims, patients with shaky hands and feet), cause skin damage to premature babies in the ICU and increase the risk of spreading infections. Non-contact HR monitoring using a camera has been recently shown to be a viable alternative. It is now possible to record cardiac-synchronous blood volume variations from facial videos of human subjects under ambient lighting. These variations produce corresponding changes in skin reflectance which can be extracted as a raw reflectance photoplethysmography (rPPG) signal and processed to reveal HR. In this project, an algorithmic framework for webcam-based HR detection was successfully implemented in MATLAB. The investigation was based on 100 self-captured videos (dark-skinned subject) and 48 videos (from 12 subjects, all but one fair-skinned) obtained from COHFACE – an online database of facial videos and corresponding physiological signals. While the performance metrics (mean error, SNR) of the rPPG signals obtained from the self-captured videos were poor (best case mean error of 22%), they were good enough to demonstrate the success of the implementation. The poor results were primarily imputed to skin tone as rPPG SNR is known to be particularly low for dark tones. The results of the COHFACE videos were far superior, with mean error ranging from 3% to 15% (among 8 different rPPG signals) and 0% to 9% under ambient and dedicated lighting, respectively. This investigation sets the foundation for future research directed at optimizing rPPG performance metrics for dark-skinned subjects.

As sonification is supposed to communicate information to users, experimental evaluation of the subjective appropriateness and effectiveness of the sonification design is often desired and sometimes indispensable. Experiments in the laboratory are typically restricted to short-term usage by a small sample size under unnatural conditions. We introduce the multi-platform CURAT Sonification Game that allows us to evaluate our sonification design by a large population during long-term usage. Gamification is used to motivate users to interact with the sonification regularly and conscientiously over a long period of time. In this paper we present the sonification game and some initial analyses of the gathered data. Furthermore, we hope to reach more volunteers to play the CURAT Sonification Game and help us evaluate and optimize our psychoacoustic sonification design and give us valuable feedback on the game and recommendations for future developments.

Successful geophysical exploration works in Gucheng-Yaxi area located in Gaochun District, Jiangsu province, China, have been limited partly due to complex geological condition of the area and high artificial noise in data acquired using electrical and electromagnetic methods. In this work, we deployed the new anti-interference spread spectrum induced polarization method (SSIP) and audio magnetotellurics (AMT) method to detect a copper-polymetallic deposit in the area. Two-dimensional (2D) inversion results at Gucheng-Yaxi Area revealed a high chargeability anomalous zone on SSIP profile that coincided with a zone of moderate resistivity located between two resistor bodies on AMT profile. A follow up 1200 meters drill hole was established at this high chargeability-moderate resistivity zone which encountered polymetallic (copper, lead, zinc, gold and silver) mineralization at the depth ≥ 400 m. Drill hole data analysis showed that mineralization occurs interspaced in marble rock mass at varies depth. Furthermore, several low resistivity-weak chargeability sections were revealed and inferred attributed to Cretaceous sediments and faults. These faults are thought to have played critical role in the polymetallic mineralization genesis. In summary, this work demonstrated the successful of application of SSIP and AMT at detecting a metallic deposit in an area with high artificial noise. Hence the geophysical prospection potential of Gucheng-Yaxi area is great.

In music, the role of the interpreter is to play her/his part manipulating the performance parameters in order to offer a sonic rendition of the piece capable of conveying specific expressive intentions. Since the 1980s there has been a growing interest in computational expressive music performance (EMP). This research field has two fundamental objectives: the understanding of the phenomenon of human musical interpretation and the automatic generation of expressive performances. Rule based, statistical, machine and deep learning approaches have been proposed, most of them devoted to the classical repertoire, in particular to piano pieces. On the contrary, we present an introduction to the role of expressive performance within popular music and to the contemporary ecology of pop music production, based on the use of Digital Audio Workstations (DAWs) and virtual instruments. After an analysis of the tools related to expressiveness commonly available to modern producers we propose a detailed survey of research into the computational EMP field, highlighting the potential and limits of what is present in literature with respect to the context of popular music, which by its nature cannot be completely superimposed on the classical one. In the concluding discussion we suggest possible lines of future research in the field of computational expressiveness applied to pop music.

To assess the usefulness of an attachable video laryngoscope (AVL) by attaching a camera and monitor to a conventional Macintosh laryngoscope (CML). Normal and tongue edema airway scenarios were simulated using a manikin. Twenty physicians performed tracheal intubations using CML, AVL, Pentax AWS® (AWS), and McGrath MAC® (MAC) in each scenario. Ten physicians with more than 10 cases of clinical experience with tracheal intubation using CML were included in the skilled group. Ten physicians with less than 10 cases of clinical experience with tracheal intubation using CML were included in the unskilled groups. The time required to intubate and the success rate were recorded. The degree of difficulty of use and glottic view assessment scored by participants. All 20 participants successfully completed the study. There was no difference in the success rate and time required for tracheal intubation in the normal airway scenarios. For the skilled group, in the tongue edema airway scenario, the AWS had the highest success rate (100%) followed by AVL (60%), MAC (60%), and CML (20%) (p = 0.001). The time required to intubate with the AWS was significantly shorter than with AVL (10.2 vs 22.3 s; p=0.002) or MAC (10.2 vs 23.7 s; p=0.001). There was no significant (p &gt; 0.05) difference between AVL and MAC. The degree of Difficulty of Use for AVL was significantly lower than that for CML (7.8 vs 2.8; p &lt; 0.001). There was no significant (p &gt; 0.05) difference between AVL and other video laryngoscopes. AVL had a higher rate of successful tracheal intubation than CML in the tongue edema scenario. AVL showed a similar success rate and time of tracheal intubation to the MAC. Therefore, AVL may be a possible alternative video laryngoscope device.

Irrational use or misuse of antibiotics, particularly by outpatients, increases antibiotic resistance. A lack of public knowledge about ‘Responsible use of antibiotics’ and ‘How to obtain antibiotics’ is a major cause of this. This study aimed to assess the effectiveness of an educational video about antibiotics and antibiotics use to increase outpatient's knowledge in two public hospitals in East Java, Indonesia. A quasi-experimental research setting was used with a one-group pretest-posttest design, carried out from November 2018 to January 2019. The study population consisted of outpatients, to whom antibiotics were prescribed, in two public hospitals in East Java, Indonesia. Participants were selected using a purposive sampling technique; 98 outpatients at MZ General Hospital in S regency and 96 at SG General Hospital in L regency were included. A questionnaire was used to measure the respondents’ knowledge and consisted of five domains, i.e. definition of infections and antibiotics, obtaining the antibiotics, directions of use, storage instructions, antibiotic resistance. The knowledge test score was the total score of the Guttman scale (a dichotomy of ‘yes’ or ‘no’ answers). To determine the significance of the difference in knowledge before and after providing the educational video and in the knowledge score between hospitals, the (paired) Student’s t-test was applied. The educational videos significantly improved outpatients' knowledge, which increased with 41% in MZ General Hospital and 42% in SG General Hospital. An educational video is a useful method to improve the knowledge of the outpatients regarding antibiotics.

Video super-resolution, which utilizes the relevant information of several low-resolution frames to generate high-resolution images, is a challenging task. One possible solution called sliding window method tries to divide the generation of high-resolution video sequences into independent sub-tasks, and only adjacent low-resolution images are used to estimate the high-resolution version of the central low-resolution image. Another popular method named recurrent algorithm proposes to utilize not only the low-resolution images but also the generated high-resolution images of previous frames to generate the high-resolution image. However, both methods have some unavoidable disadvantages. The former one usually leads to bad temporal consistency and requires higher computational cost while the latter method always can not make full use of information contained by optical flow or any other calculated features. Thus more investigations need to be done to explore the balance between these two methods. In this work, a bidirectional frame recurrent video super-resolution method is proposed. To be specific, a reverse training is proposed that the generated high-resolution frame is also utilized to help estimate the high-resolution version of the former frame. With the contribution of reverse training and the forward training, the idea of bidirectional recurrent method not only guarantees the temporal consistency but also make full use of the adjacent information due to the bidirectional training operation while the computational cost is acceptable. Experimental results demonstrate that the bidirectional super-resolution framework gives remarkable performance that it solves the time-related problems when the generated high-resolution image is impressive compared with recurrent-based video super-resolution method.

In tracking-by-detection paradigm for multi-target tracking, target association is modeled as an optimization problem that is usually solved through network flow formulation. In this paper, we proposed combinatorial optimization formulation and used a bipartite graph matching for associating the targets in the consecutive frames. Usually, the target of interest is represented in a bounding box and track the whole box as a single entity. However, in the case of humans, the body goes through complex articulation and occlusion that severely deteriorate the tracking performance. To partially tackle the problem of occlusion, we argue that tracking the rigid body organ could lead to better tracking performance compared to the whole body tracking. Based on this assumption, we generated the target hypothesis of only the spatial locations of person’s heads in every frame. After the localization of head location, a constant velocity motion model is used for the temporal evolution of the targets in the visual scene. Qualitative results are evaluated on four challenging video surveillance dataset and promising results has been achieved.

Live streaming conferences increase the participation of a diverse audience, help defray travel costs and overcome problems related to travel restrictions. In this article, we lay out tips for implementing live-streaming in scientific meetings. We also cover legal, ethical, and technical aspects implicated with live-streaming scientific talks. To write this article, we leveraged knowledge from our experience in organizing the symposium “Deciphering the Denisovans,” presented at the 88th Annual Meeting of the American Association of Physical Anthropology (AAPA) in Cleveland, OH, in 2019, as well as literature on the topic.

In this study, we examine microscale waterflooding in a randomly close-packed porous medium. Three different porosities are prepared in a microfluidic platform and saturated with silicone oil. Optical video fluorescence microscopy is used to track the water front as it flows through the porous packed bed. The degree of water saturation is compared to water containing two different types of chemical modifiers, sodium dodecyl sulfate (SDS) and polyvinylpyrrolidone (PVP), with water in the absence of a surfactant used as a control. Image analysis of our video data yield saturation curves and calculate fractal dimension, which we use to identify how morphology changes the way an invading water phase moves through the porous media. An inverse analysis based on the implicit pressure explicit saturation (IMPES) simulation technique uses mobility ratio as an adjustable parameter to fit our experimental saturation curves. The results from our inverse analysis combined with our image analysis show that this platform can be used to evaluate the effectiveness of surfactants or polymers as additives for enhancing the transport of water through an oil-saturated porous medium.

Deck inclination and vertical displacements are among the most important technical parameters to evaluate the health status of a bridge and to verify its bearing capacity. Several methods, both conventional and innovative, are used for structural rotations and displacement monitoring; no one of these does allow, at the same time, precision, automation, static and dynamic monitoring without using high cost instrumentation. The proposed system uses a common laser pointer and image processing. The elastic line inclination is measured by analyzing the single frames of a HD video of the laser beam imprint projected on a flat target. For the image processing, a code was developed in Matlab® that provides instantaneous rotation and displacement of a bridge, charged by a mobile load. An important feature is the synchronization of the load positioning, obtained by a GNSS receiver or by a video. After the calibration procedures, a test was carried out during the movements of a heavy truck maneuvering on a bridge. Data acquisition synchronization allowed to relate the position of the truck on the deck to inclination and displacements. The inclination of elastic line was obtained with a precision of 0.01 mrad. The results demonstrate the suitability of the method for dynamic load tests, control and monitoring of bridges.

Depth-sensing technology has led to broad applications of inexpensive depth cameras that can capture human motion and scenes in 3D space. Background subtraction algorithms can be improved by fusing color and depth cues, thereby allowing many issues encountered in classical color segmentation to be solved. In this paper, we propose a new fusion method that combines depth and color information for foreground segmentation based on an advanced color-based algorithm. First, a background model and a depth model are developed. Then, based on these models, we propose a new updating strategy that can eliminate ghosting and black shadows almost completely. Extensive experiments have been performed to compare the proposed algorithm with other, conventional RGB-D algorithms. The experimental results suggest that our method extracts foregrounds with higher effectiveness and efficiency.

This study examined the eye movement patterns of 317 elementary students across reading conditions (audio-assisted reading (AR) and reading-only (R)) and text types (fiction and non-fiction), and identified eye movement parameters that predict their literal comprehension (LC) and inferential comprehension (IC). Participants, randomly assigned to either reading condition and either text type, answered questions assessing their LC and IC. Average fixation duration (AFD), total fixation duration (TFD), and scanpath length were used as eye movement parameters. There were main effects of age on all parameters and interaction effects between age and reading condition on TFD and scanpath length. Controlling for age, TFD had a positive impact on LC of both text types in the AR, while under the R, it affected negatively on IC of both text types. Longer scanpaths predicted IC of fiction in the AR, LC and IC of non-fiction under the AR, and LC of non-fiction within the R. AFD influenced negatively on IC of fiction in the AR, LC and IC of non-fiction in the AR, and LC of non-fiction under the R. These eye movement patterns and predictors indicate children employ different reading strategies based on reading modality and text type.

Over the past few decades, digitalisation has pushed patient care towards a new era, inducing the evolution of health care delivery and enhancing the overall sustainability of health systems worldwide. Despite the ever-evolving technology leading to a change in health care provision, the uptake of these novel technologies by medical professionals is slow, largely because of concerns about the potential impact on patient care and patient safety, and medico-legal implications. Hence, this research aimed to understand doctors’ perceptions of the adoption of digital virtual consultations in the practice setting.In this survey, an online questionnaire, adapted from the construct by Venkatesh and Bala and based on the Technology Acceptance Model by Davis, was distributed to 886 hospital doctors. Altogether 133 responses were obtained.Results suggest that the respondents perceived digital virtual consultations as adjuncts to face-to-face consultations and as able to diminish time and place barriers. Doctors were willing in principle to utilise these alternatives to traditional methods if the appropriate infrastructure and technology were in place. Feasibility and cost-effectiveness studies are recommended to establish the technology-fit factor and the impact of the technology on the workforce, coupled with a stakeholder analysis to include all the actors involved in such a strategy.

(1) Background: Surgical phases form the basic building blocks for surgical skill assessment, feedback and teaching. Phase duration itself and its correlation to clinical parameters has not yet been investigated. Novel commercial platforms provide phase indications but have not been assessed for accuracy yet. (2) Methods: We assess 100 robot-assisted partial nephrectomy videos for phase duration based on previously defined proficiency metrics. We develop an annotation framework and subsequently compare our annotations to an existing commercial solution (Touch Surgery, Medtronic™). We subsequently explore clinical correlations between phase durations and peri-operative parameters. (3) Results: Objective and uniform phase assessment requires precise definitions derived from an iterative revision process. Comparison to a commercial solution shows large differences in definitions across phases. BMI and duration of renal tumor identification correlate positively, as well as tumor complexity and both tumor excision and renorraphy duration. (4) Conclusions: Surgical phase duration can be correlated with certain clinical outcomes. Further research should investigate if retrieved correlations are also clinically meaningful. This requires increasing dataset sizes and facilitation through intelligent computer vision algorithms. Commercial platforms can facilitate this dataset expansion and help unlock the full potential, provided the disclosure of phase annotation details.

In the Versatile Video Coding (VVC) standard, affine motion models have been applied to enhance the resolution of complex motion patterns. However, due to the high computational complexity involved in affine motion estimation, real-time video processing applications face significant challenges. This paper focuses on optimizing affine motion estimation algorithms in the VVC environment and proposes a fast gradient iterative algorithm based on edge detection for efficient computation. Firstly, we establish judging conditions during the construction of affine motion candidate lists to streamline the redundant judging process. Secondly, we employ the Canny edge detection method for gradient assessment in the affine motion estimation process, thereby enhancing the iteration speed of affine motion vectors. Experimental results demonstrate that our affine motion estimation algorithm reduces encoding time by approximately 15%-35% while maintaining video bitrate and quality.

Video segmentation is crucial in a variety of practical applications especially in computer visions. Most of recent works in video segmentation are focusing on Deep learning based video segmentation, there are rooms for improvement in respect of the evolutionary algorithms. This paper aims to propose the novel method to video segmentation by using the optimization of segmentation parameters based on ensemble-based random forest and gradient boosting decision tree. The experimental results show Pareto front of segmentation parameters (hue, brightness, luminance, and saturation). Our optimization model yields accuracy: 85% +/-8.85 % (micro average: 85.00 %), average class precision: 84.88%, and average class recall: 85%. We also show the video segmentation results based on our optimization method and compare our results with Kinect-based video segmentation.

Every (multimedia) service needs to be accessible. Accessibility for multimedia content is typically provided by means of access services, of which subtitling is likely the most widespread one. Up to date, many recommendations and solutions for subtitling classical 2D audiovisual services are available. Likewise, recent efforts have been devoted to devising adequate subtitling solutions for VR360 video content. This paper, for the first time, goes a step beyond, by exploring two key requirements to fulfill remaining challenges towards efficiently subtitling 3D Virtual Reality (VR) content: presentation modes, and guiding methods. By leveraging insights from earlier work on VR360 content, the paper proposes novel presentation modes and guiding methods to not only deal with the freedom to explore the omnidirectional scenes, but also with additional specificities of 3D VR compared to VR360 content: depth, 6 Degrees of Freedom (6DoF), and viewing perspectives. The obtained results prove that always-visible and a novel proposed comic-style presentation mode are far more appropriate than state-of-the-art fixed-positioned subtitles, mainly in terms of immersion, ease and comfort of reading, and identification of speakers, when applied to professional pieces of content with limited displacement of speakers and with limited 6DoF (i.e. users are not expected to largely navigate around the virtual environment). Likewise, even in such limited movement scenarios, the results show that the use of indicators (arrows), as guiding methods, is well received. Overall, the paper provides relevant insights and paves the way toward efficiently subtitling 3D VR content.

Recognition of the human interaction on the unconstrained videos taken from cameras and remote sensing platforms like a drone is a challenging problem. This study presents a method to resolve issues of motion blur, poor quality of videos, occlusions, the difference in body structure or size, and high computation or memory requirement. This study contributes to the improvement of recognition of human interaction during disasters such as an earthquake and flood utilizing drone videos for rescue and emergency management. We used Support Vector Machine (SVM) to classify the high-level and stationary features obtained from Convolutional Neural Network (CNN) in key-frames from videos. We extracted conceptual features by employing CNN to recognize objects from first and last images from a video. The proposed method demonstrated the context of a scene, which is significant in determining the behaviour of human in the videos. In this method, we do not require person detection, tracking, and many instances of images. The proposed method was tested for the University of Central Florida (UCF Sports Action), Olympic Sports videos. These videos were taken from the ground platform. Besides, camera drone video was captured from Southwest Jiaotong University (SWJTU) Sports Centre and incorporated to test the developed method in this study. This study accomplished an acceptable performance with an accuracy of 90.42%, which has indicated improvement of more than 4.92% as compared to the existing methods.

Multi-object tracking (MOT) in airborne videos is a challenging problem due to the uncertain airborne vehicle motion, vibrations of the mounted camera, unreliable detections, size, appearance and motion of the moving objects as well as occlusions due to the interaction between the moving objects and with other static objects in the scene.To deal with these problems, this work proposes a four-stage Hierarchical Association framework for multiple object Tracking in Airborne video (HATA). The proposed framework combines data association-based tracking (DAT) methods and target tracking using a Compressive Tracking approach, to robustly track objects in complex airborne surveillance scenes. In each association stage, different sets of tracklets and detections are associated to efficiently handle local tracklet generation, local trajectory construction, global drifting tracklet correction and global fragmented tracklet linking. Experiments with challenging airborne video datasets show significant tracking improvement compared to existing state-of-art methods.

Aiming at the problems that large amount of video monitoring image data in underground coal mines leads to difficulties in transmission and storage, compressed sensing theory is introduced to encode and decode video images, and a new distributed video coding scheme is proposed. In order to obtain more sparse representation and more general applicability, a block-based adaptive sparse base scheme is proposed. For the acquisition of side information, fixed weight is usually used to synthesize side information and the correlation between different image blocks is neglected, a block-based classification weighted side information generation scheme is proposed. Experimental results show that the block-based classification codec scheme can make full use of inter-frame correlation. Under the appropriate sampling rate, the PSNR value of video reconstruction increases, which effectively improves the quality of video frame reconstruction.

This research study focuses on addressing practical optimization challenges in audio-visual content using advanced computational intelligence methods, with a specific emphasis on privacy-preserving issues. The research will be presented as a proposal and can be conducted based on the provided ideas. Computational intelligence encompasses various approaches, including evolutionary algorithms, learning methods, fuzzy systems, and neural networks, which have become essential tools for tackling complex engineering optimization problems due to computational expenses, dimensional complexities, and interdisciplinary integration. The research objectives include a thorough investigation of optimization challenges in audio-visual content, the delineation of problem characteristics, and the development of relevant methodologies based on these specifications. The main goals of the study, titled "Advanced Computational Intelligence Assisted Less-Expensive Privacy-Preserving Optimization," encompass the development of a metamodel-based learning algorithm integrated with evolutionary computation for privacy-preserving optimization, less-expensive signal watermarking optimization using hybrid metamodeling and evolutionary algorithms, and a closed-loop robust intelligent PID control system applied in real-time dynamic signal watermarking. Additional objectives may be defined as the research progresses and further background review is conducted.

End-to-end learned image compression codecs have notably emerged in recent years. These codecs have demonstrated superiority over conventional methods, showcasing remarkable flexibility and adaptability across diverse data domains while supporting new distortion losses. Despite challenges such as computational complexity, learned image compression methods inherently align with learning-based data processing and analytic pipelines due to their well-suited internal representations. The concept of Video Coding for Machines has garnered significant attention from both academic researchers and industry practitioners. This concept reflects the growing need to integrate data compression with computer vision applications. In light of these developments, we present a comprehensive survey and review of lossy image compression methods. Additionally, we provide a concise overview of two prominent international standards, MPEG Video Coding for Machines and JPEG AI. These standards are designed to bridge the gap between data compression and computer vision, catering to practical industry use cases.

The purpose of this study was to detect mind-wandering experienced by pre-service teachers while learning video lecture on physics. The lecture was videotaped and consisted of a live lecture in a classroom. The lecture was about Gauss's law on physics. We investigated whether oculomotor data and eye movements could be used as a marker to indicate the learner’s mind-wandering. Each data was collected in a study in which 24 pre-service teachers (16 females and 8 males) reported self-caught mind-wandering while learning physics video lecture during30 minutes. A Tobii Pro Spectrum (sampling rate: 300Hz) was used to capture their eye-gaze during learning Gauss's law course video. After watching video lecture, we interviewed pre-service teachers about their mind-wandering experience. We first used the self-caught method to capture the mind-wandering timing of pre-service teachers while learning from video lectures. We detected more accurate mind-wandering segments by comparing fixation duration and saccade count. We investigated two types of oculomotor data (blink count, pupil size) and nine eye movements (average peak velocity of saccades; maximum peak velocity of saccades; standard deviation of peak velocity of saccades; average amplitude of saccades; maximum amplitude of saccades; total amplitude of saccades; saccade count/s; fixation duration; fixation dispersion). The result was that the blink count could not be used as a marker for mind-wandering during learning video lectures among them (oculomotor data and eye movements), unlike previous literatures. Based on the results of this study, we identified elements that can be used as mind-wandering markers while learning from video lectures that are similar to real classes, among the oculomotor data and eye movement mentioned in previous literatures. Also, we found that most participants focused on past thoughts and felt unpleasant after experiencing mind-wandering through interview analysis.

Background: Elucidation of epigenetic mechanisms correlating with neuropathic pain in humans is crucial for the prevention and treatment of this treatment-resistant pain state. In the present study, associations between neuropathic pain characteristics and DNA methylation of the transient receptor potential ankyrin 1(TRPA1) gene were evaluated in chronic pain patients and preoperative patients. Methods: Pain and psychological states were prospectively assessed in patients who suffered chronic pain or were scheduled for thoracic surgery. Neuropathic characteristics were assessed using the Douleur Neuropathique 4 (DN4) questionnaire. DNA methylation levels of the CpG island in the TRPA1 gene were examined using whole blood. Results: Forty-eight adult patients were enrolled in this study. Increases in DNA methylation rates at CpG -51 showed positive correlations with increases in the DN4 score both in preoperative and chronic pain patients. Combined methylation rates at CpG -51 also significantly increased together with increase in DN4 scores. Conclusions: Neuropathic pain characteristics are likely associated with methylation rates at the promoter region of the TRPA1 gene in human peripheral blood.

Capsule endoscopy, which uses a wireless camera to take images of the digestive tract, is emerging as an alternative to traditional colonoscopy. The diagnostic values of these images depend on the quality of revealed underlying tissue surfaces. In this paper, we consider the problem of enhancing the visibility of detail and shadowed tissue surfaces for capsule endoscopy images. Using concentric circles at each pixel for random walks combined with stochastic sampling, the proposed method enhances the details of vessel and tissue surfaces. The framework decomposes the image into two detail layers that contain shadowed tissue surfaces and detail features. The target pixel value is recalculated for the smooth layer using similarity of the target pixel to neighboring pixels by weighting against the total gradient variation and intensity differences. In order to evaluate the diagnostic image quality of the proposed method, we used clinical subjective evaluation with a rank order on selected KID image database and compared to state of the art enhancement methods. The result showed that the proposed method provides a better result in terms of diagnostic image quality and objective quality contrast metrics and structural similarity index.

Clinical rehabilitation and sports performance analysis both require the objectification of movement. Kinovea^© is a free 2D motion analysis software that enables the establishment of kinematics parameters. This low-cost technology has been used in sports sciences, as well as clinical field and research work. Although it has been validated as a tool with which to assess time-related variables, this is not yet the case regarding angular and distance variables. The main objective of this study was to determine the validity and reliability of the Kinovea software in obtaining angular and distance data at different perspectives of 90°, 75°, 60° and 45°. For this purpose, a figure with 29 points was designed (in AutoCAD) and 24 frames analysed. Each frame was examined by three observers who each made two attempts. For each export data item, 20 angles and 20 distance variables were calculated, with intra- and inter-observer reliability also analysed. To evaluate Kinovea reliability and validity a multiple approach was applied involving the following analysis: -systematic error with a two-way ANOVA 2x4; -relative reliability with ICC and CV (95% confidence interval); -absolute reliability with Standard Error. The results thus obtained indicate that the Kinovea software is a valid and reliable tool that is able to measure accurately at distances up to 5 m from the object and at an angle range of 90°–45°. Nevertheless, for optimum results an angle of 90° is suggested.

The COVID19 pandemic had a major impact on emergency medical communication centres (EMCC). A live video facility was made available to second-line physicians in an EMCC with a first-line paramedic to receive emergency calls. The objective of this study was to measure the contribution of live video to remote medical triage. The single-centre retrospective study included all telephone assessments of patients with suspected COVID19 symptoms from 01.04.2020 to 30.04.2021 in Geneva, Switzerland. The organisation of the EMCC and the characteristics of patients who called the two emergency lines (official emergency number and COVID19 number) with suspected COVID19 symptoms were described. A prospective web-based survey of physicians was conducted during the same period to measure the indications, limitations and impact of live video on their decisions. 8,957 patients were included. 2,157 (48.0%) of the 4,493 patients assessed on the official emergency number had dyspnoea. 4,045 (90.6%) of 4,464 patients assessed on the COVID19 number had flu-like symptoms. 1,798 (20.1%) patients were reassessed remotely by a physician, including 405 (22.5%) with live video, successfully in 315 (77.8%) attempts. The web-based survey (107 forms) showed that physicians used live video to assess mainly the breathing (81.3%) and general condition (78.5%) of patients. They felt that their decision was modified in 75.7% (n=81) of cases, and caught 7 (7.7%) patients in life-threatening emergency. Medical triage decisions for suspected COVID19 patients are strongly influenced by the use of live video.

The prolonged lockdown imposed to contain the COVID-19 pandemic prevented many people from direct contact with nature and greenspaces, raising alarms for a possible worsening of mental health. This study investigates the effectiveness of a simple and affordable remedy for improving psychological well-being, based on audio-visual stimuli brought by a short computer video showing forest environments, with an urban video as a control. Randomly selected participants were assigned the forest or urban video, to look at and listen early in the morning, and filled questionnaires. In particular, the State-Trait Anxiety Inventory (STAI) Form Y, collected in baseline condition and at the end of the study, and the Part II of the Sheehan Patient Rated Anxiety Scale (SPRAS), collected every day immediately before and after watching the video. The virtual exposure to forest environments showed effective to reduce perceived anxiety levels in in people forced by lockdown in limited spaces and environmental deprivation. Although significant, the effects were observed only in the short term, highlighting the limitation of the virtual experiences. The reported effects might also represent a benchmark to disentangle the determinants of health effects due to real forest experiences, for example, the inhalation of biogenic volatile organic compounds (BVOC).

Adaptive bitrate (ABR) algorithms optimize the quality of streaming experiences for users in client-side video players especially in unreliable or slow mobile networks. Several rule-based heuristic algorithms can achieve stable performance, but they sometimes fail to adapt properly to changing network conditions. Fluctuating bandwidth may cause algorithms to default to behavior that creates a negative experience for the user. ABR algorithms can be generated with reinforcement learning, a decision-making paradigm in which an agent learns to make optimal choices through interactions with an environment. Training reinforcement learning algorithms for bitrate streaming requires building a simulator for an agent to experience interactions quickly; training an agent in the real environment is infeasible due to the long step times in real environments. This project explores using supervised learning to construct a world-model, or a learned simulator, from recorded interactions. A reinforcement learning agent trained inside of the learned model, rather than a simulator, can outperform rule-based heuristics. Furthermore, agents trained inside the learned world-model can outperform model-free agents in low sample regimes. This work highlights the potential for world-models to quickly learn simulators, and to be used to generate optimal policies.

Detection of the region of interest (ROI) is a critical step in laryngeal image analysis for the delineation of glottis contour. The process can improve both computational efficiency and accuracy of the image segmentation task, which will facilitate subsequent analysis and characterization of the vocal fold vibration as it correlates with voice quality and pathology. This study aims to develop machine learning based approaches for automatic detection of ROI for glottis image sequences captured by high-speed video-endoscopy (HSV), a clinical laryngeal imaging modality. In particular, we first applied the supporting vector machine (SVM) method using histogram of oriented gradients (HOG) feature descriptor, and second, trained a convolutional neural network (CNN) model for this task. Comparisons are made for both approaches in terms of accuracy of recognition and computation time.

Video quality assessment (VQA) plays an important role in video applications for quality evaluation and resource allocation. It aims to evaluate the video quality consistent with the human perception. In this letter, a hierarchical gradient similarity based VQA metric is proposed inspired by the structure of the primate visual cortex, in which visual information is processed through sequential visual areas. These areas are modeled with the corresponding measures to evaluate the overall perceptual quality. Experimental results on the LIVE database show that the proposed VQA metric significantly outperforms the state-of-the-art VQA metrics.

We previously reported our initial experience of subxiphoid single-port robotic-assisted thoracic surgery (SRATS) thymectomy using the single-port robotic surgical system (SPS). However, the potential benefits of this technique remain unknown. Thus, this study examined the multi-institutional experience of SRATS thymectomy and compared perioperative outcomes of this technique with those of subxiphoid single-port video-assisted thoracic surgery (SVATS) thymectomy. Data of patients who underwent subxiphoid SRATS and SVATS thymectomy performed by three thoracic surgeons at three institutions between September 2018 and May 2024 were retrospectively collected. In total, 110 patients were included, with 85 and 25 undergoing SRATS and SVATS thymectomy, respectively. No significant differences were noted in the total operative time (154.46±74.06 vs. 146.76±67.07 min, P=0.674) and conversion rate to median sternotomy (0% vs. 4 %, P=0.227) between the two groups. The SRATS group was associated with a lower conversion rate to multi-port surgery (2% vs. 20%, P=0.006), shorter chest tube drainage duration (1.40±0.94 vs. 2.00±1.29 days, P=0.001), and shorter postoperative hospital stay (2.87±1.26 vs. 5.08±5.20 days, P=0.007). Subxiphoid SRATS thymectomy using the SPS is feasible and can be a good alternative to conventional minimally invasive thymectomy. Further large-scale randomized controlled studies are needed to confirm its benefits.

This paper introduces the improvements in the natural frequency based Structural Health Monitoring (SHM) by applying bio-inspired optimization methods and the vision-based monitoring system for the effective damage detection. This paper proposes a natural frequency extraction method using the motion magnification based vision monitoring system with bio-inspired optimization techniques to estimate the damage location and depth in a cantilever beam. The proposed optimization techniques are inspired by natural processes and biological evolution including Genetic Algorithms, Particle Swarm Optimization, Sea Lion Optimization, and Coral Reefs Optimization. To verify the performances of each bio-inspired optimization methods, the eigenvalues of a two-bay truss structure are used for estimating the damaged elements. Then, using the proposed video motion magnification method, the natural frequency for each of undamaged and damaged cantilever beam have been extracted and compared with the LDV sensor to verify the proposed vision-based monitoring system. The performance of each bio-inspired optimizer for the damage detection has been compared. As a result, Coral Reefs Optimization has showed the lowest average error, around 1%, in the damage detection using natural frequency.

In computer vision, human action recognition is a hot topic, popularized by the development of deep learning. Current models have achieved high accuracy results on public datasets. Despite this success, they require significant computational resources for training. Given that transfer learning based techniques allow reusing what other models have already learned and training models with less computational resources, in this work we propose using a transfer learning based approach for action recognition in videos. We describe a methodology for human action recognition using transfer learning techniques in a custom dataset. The proposed method consists of four stages: 1) human detection and tracking, 2) video preprocessing, 3) feature extraction (using pretrained models with ImageNet), and 4) action recognition using a two-stream model consisting of TCNs, LSTMs, and CNNs layers. The custom dataset is imbalanced with 189, 390, 490, 854, and 890 videos per class, respectively. For feature extraction, we analyzed the performance of seven pretrained models: Inception-v3, MobileNet-v2, MobileNet-v3-L, VGG-16, VGG-19, Xception, and ConvNeXt-L. We show that the best results were obtained with the last one. Finally, using pretrained models for feature extraction allowed training in a PC with a single GPU with an accuracy of 94.9%.

The overall contribution of otolith receptors to eye movements, postural control and perceptual functions is the basis for clinical testing of otolith function. With such wide range of contributions, it is important to recognize that the functional outcomes of these tests may vary depending on the specific method employed to stimulate the hair cells. In this article, we review common methods used for clinical evaluation of otolith function and how different aspects of physiology may affect the functional measurements in these tests. We compare the properties and performance of various clinical tests with the emphasis on the newly-developed video ocular counter roll (vOCR), measurement of ocular torsion on fundus photography, and subjective visual vertical or horizontal (SVV/SVH) testing.

The use of video in education has become ubiquitous as technological developments have markedly improved the ability and facility to create, deliver and view videos. The concomitant pedagogical transformation has created a sense of urgency regarding how video may be used to advance learning. Initial reviews have suggested only limited potential for the use of video in higher education. More recently, a systematic review of studies on the effect of video use on learning in higher education, published in the prestigious Review of Educational Research, found, overall, effects to be positive. In the present paper we critique this study and provide some needed clarity to the state of research on learning via video in higher education. We reveal significant gaps in the study methodology and write-up and use a cognitive processing lens to critically assess and reanalyse study data. We found results of this study to be only applicable to learning requiring lower-level cognitive processing and conclude, consistent with prior research, learning benefits remain limited.

Individuals with autism often experience gastrointestinal issues but the cause is unknown. Many gene mutations that modify neuronal synapse function are associated with autism and therefore may impact the enteric nervous system that regulates gastrointestinal function. A missense mutation in the Nlgn3 gene encoding the cell adhesion protein, Neuroligin-3, was identified in two brothers with autism who both experienced severe gastrointestinal dysfunction. Mice expressing this mutation (Nlgn3R451C mice) are a well-studied preclinical model of autism and show autism-relevant characteristics, including impaired social interaction and communication, as well as repetitive behaviour. We previously showed colonic dysmotility in response to GABAergic inhibition and increased myenteric neuronal numbers in the small intestine in Nlgn3R451C mice bred on a mixed genetic background. Here we show that gut dysfunction is a persistent phenotype of the Nlgn3 R451C mutation in mice backcrossed onto a C57BL/6 background. We report that Nlgn3R451C mice show faster gastrointestinal transit in vivo and have longer small intestines compared to wild-types due to a reduction in smooth muscle tone. In Nlgn3R451C mice, we observed a decrease in resting jejunal diameter and neurally-regulated dysmotility as well as shorter durations of contractile complexes in the ileum. In Nlgn3R451C mouse colons, short contractions were inhibited to a greater extent by the GABAA antagonist, gabazine, compared to wild-type mice. Inhibition of nitric oxide synthesis decreased the frequency of contractile complexes in the jejunum, but not the ileum, in both wild-type and Nlgn3R451C mice. These findings demonstrate that changes in enteric nervous system function contribute to gastrointestinal dysmotility in mice expressing the autism-associated R451C missense mutation in the Neuroligin-3 protein.

“A Picture is worth a thousand words”. Given an image, humans are able to deduce various cause-and-effect captions of past, current, and future events beyond the image. The task of visual commonsense generation aims at generating three cause-and-effect captions (1) what needed to happen before, (2) what is the current intent, and (3) what will happen after for a given image. However, such a task is challenging for machines owing to two limitations: existing approaches (1) directly utilize conventional vision-language transformers to learn relationships between input modalities, and (2) ignore relations among target cause-and-effect captions but consider each caption independently. We propose Cause-and-Effect BART (CE-BART) which is based on (1) Structured Graph Reasoner that captures intra- and inter-modality relationships among visual and textual representations, and (2) Cause-and-Effect Generator that generates cause-and-effect captions by considering the causal relations among inferences. We demonstrate the validity of CE-BART on VisualCOMET and AVSD benchmarks. CE-BART achieves SOTA performances on both benchmarks, while extensive ablation study and qualitative analysis demonstrate the performance gain and improved interpretability.

With the outbreak of coronavirus disease 2019 (COVID-19), there is a need for efficient management of patients with mild or no symptoms, which account for the majority. The aim of this study is to introduce the structure and operation protocol of a living and treatment support centre (LTSC) operated by Seoul National University Hospital in South Korea. The existing accommodation facility was converted into a 'patient centre' where patients was isolated. A few Medical staff here performed medical tests and responded to emergencies. Another part of the LTSC was 'remote monitoring centre'. In this center, patients’ self-measured vital signs and symptoms were monitored twice a day, and the medical staff staying here provided video-consultation via a smartphone. During the 3 weeks from March 5 to March 26, 2020, 113 patients were admitted and treated. LTSC could be an efficient alternative to hospital admission in pandemic situation like COVID-19.

Models of subsurface structures are important for successful deposit exploration but are challenged by the need to integrate data from different geophysical methods. In the present study, we evaluated a method of joint inversion in which audio-magnetotelluric (AMT) and dual frequency induced polarization (DFIP) data sets are inverted simultaneously to produce a consistent 2D resistivity model to show a clear image of subsurface structures. To achieve the objectives, we conducted AMT and DFIP surveys first on the same survey line within the Dongjun lead-zinc deposit in inner Mongolia by developing 31 AMT survey sites with an interstation separation of 40 m on a 1440 m survey track and operated in fifty-three frequencies in the range 1–10,400 Hz to record the resistivity distribution of subsurface to depths exceeding 800 m. The same survey setup up was applied to the DFIP method by utilizing the SQ-3C model with a pole-dipole array configuration and conducted measurements at frequencies of 4 Hz and 4/13 Hz. We first separately inverted AMT and DFIP measurements. The two-dimensional (2D) model obtained from AMT data revealed distinct low resistivity anomalies in the middle of the 2D inversion model. In contrast, the DFIP inversion model showed a high resistive body in the same region. In response to the discrepancies observed in the separate 2D inversion models, we implemented a joint inversion for both the AMT and DFIP datasets. The joint inversion resistivity model shows surficial conducting bodies and a high conductive body along the profile with relatively high Percent Frequency Effect (PEF) indicating high chargeability. The final joint inversion resistivity model clearly images the large silica alteration zone and the Pb-Zn mineralization. This study demonstrates the feasibility of a joint inversion methodology and highlights the value of integrating geophysical methods through joint inversion for enhanced characterization and exploration of lead-zinc ores.

The integration of sign language recognition systems into digital platforms has the potential to bridge communication gaps between the deaf community and the broader population. This paper introduces an advanced Israeli Sign Language (ISL) recognition system designed to interpret dynamic motion gestures, addressing a critical need for more sophisticated and fluid communication tools. Unlike conventional systems that focus solely on static signs, our approach incorporates both Deep Learning and Computer Vision techniques to analyze and translate dynamic gestures captured in real-time video. We provide a comprehensive account of our preprocessing pipeline, detailing every stage from video collection to the extraction of landmarks using MediaPipe, including the mathematical equations used for preprocessing these landmarks and the final recognition process. The dataset utilized for training our model is unique in its comprehensiveness and is publicly accessible, enhancing the reproducibility and expansion of future research. The deployment of our model on a publicly accessible website allows users to engage with ISL interactively, facilitating both learning and practice. We discuss the development process, the challenges overcome, and the anticipated societal impact of our system in promoting greater inclusivity and understanding.

Methylene blue has been electropolymerized on the surface of a stainless steel 316. The addition of sodium oxalate and working at a pH near 11 has allowed to obtain steel electrodes coated with electroactive polymer. This polymer shows electrochromic properties similar to those of the monomer, but also appears electroactivity at more positive potentials which is associated to the active centers in the bridges between monomeric units. The study by means of digital video electrochemistry has allowed on the one hand, to quantify the color changes on the entire surface of the stainless steel simultaneously and by means of the mean color intensities to separate the contribution to the overall polymer response of the active centers of the phenothiazine ring and of the inter-monomer bonds. A reduction mechanism for the polymer compatible with the pH variation of the observed electrochemical behavior is proposed.

Locoregional anaesthetic techniques are invaluable for providing multimodal analgesia for painful surgical procedures. This prospective, randomised study describes a nerve stimulator-guided bra-chial plexus blockade (BPB) in rabbits undergoing orthopaedic surgery in comparison to systemic lidocaine. Premedication was provided with intramuscular (IM) medetomidine, fentanyl and midazolam. Anaesthesia was induced (propofol IV) and maintained with isoflurane. Nine rabbits received a lidocaine BPB (2%; 0.3 ml kg-1), and eight received lidocaine constant rate infusion (CRI) (2 mg kg-1 IV, followed by 100 µg kg-1 minute-1). Rescue analgesia was provided with Fentanyl IV. Carprofen was administered at the end of surgery. Post-operative pain was determined using the Rabbit Grimace Scale (RGS) and a composite pain scale. Buprenorphine was administered accord-ing to pain score for two hours after extubation. Rabbits were filmed during the first two hours to measure distance travelled and behaviours. Food intake and faeces output were compared. Every rabbit in CRI required intraoperative rescue analgesia compared to no rabbits in BPB. How-ever, rabbits in both groups had similar pain scores and there was no difference in administration of postoperative analgesia. There were no significant differences in food intake or faeces produc-tion over 18 hours, and no significant differences in distance travelled, or behaviours examined during the first two hours. BPB seems superior for intraoperative analgesia. Postoperatively both groups were comparable.