Video Sources Research Articles

RETRACTED ARTICLE: Toward trustworthy human suspicious activity detection from surveillance videos using deep learning

AbstractIn today’s world, suspicious or unusual activities express threats and danger to others. For the prevention of various security issues, an automatic video detection system is very important. It is difficult to consecutively monitor camera videos recorded in public places to detect any abnormal event, so an automated video detection system is needed. The study objective is to create an intelligent and trustworthy system that will take a video stream as input and detect what kind of suspicious activity is happening in that video to reduce the time that consumes watching the video. In this work, we use three models Convolutional Neural Network (CNN), GRU, and ConvLSTM model. These models are trained on the same dataset of 6 suspicious activities of humans that are: Running, Punching, Falling, Snatching, Kicking, and Shooting. The dataset consists of various videos related to each activity. Different deep learning techniques are applied in the proposed work: preprocessing, data annotation model training, and classification. The frames are extracted from the source video, and then features are calculated through the model in Inception v3, a Convolutional Neural Network variant. On the same dataset, the CNN model attains 91.55% accuracy, the ConvLSTM model attains 88.73% accuracy, and the GRU model attains 84.01% accuracy. The performance of the proposed models is evaluated using a confusion matrix, F1-Score, precision, and recall. The proposed model proved better than other models in terms of performance and accuracy. The findings of this study prove helpful unusual events by examining a person's abnormal behavior.

Interactive landscape–scale cloud animation using DCGAN

This article presents an interactive method for 3D cloud animation at the landscape scale by employing machine learning. To this end, we utilize deep convolutional generative adversarial network (DCGAN) on GPU for training on home-captured cloud videos and producing coherent animation frames. We limit the size of input images provided to DCGAN, thereby reducing the training time and yet producing detailed 3D animation frames. This is made possible through our preprocessing of the source videos, wherein several corrections are applied to the extracted frames to provide an adequate input training data set to DCGAN. A significant advantage of the presented cloud animation is that it does not require any underlying physics simulation. We present detailed results of our approach and verify its effectiveness using human perceptual evaluation. Our results indicate that the proposed method is capable of convincingly realistic 3D cloud animation, as perceived by the participants, without introducing too much computational overhead.

Mpox (monkeypox) information on TikTok: analysis of quality and audience engagement

BackgroundOnline information on mpox (monkeypox) is not well studied. We have analysed the video content, information quality, and audience engagement of mpox-related videos on TikTok.MethodsUsing a hashtag-based searching strategy, we...

A Performance Enhancement of Deepfake Video Detection through the use of a Hybrid CNN Deep Learning Model

In the current era, many fake videos and images are created with the help of various software and new AI (Artificial Intelligence) technologies, which leave a few hints of manipulation. There are many unethical ways videos can be used to threaten, fight, or create panic among people. It is important to ensure that such methods are not used to create fake videos. An AI-based technique for the synthesis of human images is called Deep Fake. They are created by combining and superimposing existing videos onto the source videos. In this paper, a system is developed that uses a hybrid Convolutional Neural Network (CNN) consisting of InceptionResnet v2 and Xception to extract frame-level features. Experimental analysis is performed using the DFDC deep fake detection challenge on Kaggle. These deep learning-based methods are optimized to increase accuracy and decrease training time by using this dataset for training and testing. We achieved a precision of 0.985, a recall of 0.96, an f1-score of 0.98, and support of 0.968.

Popular science and education of cosmetic surgery in China: Quality and reliability evaluation of Douyin short videos.

Douyin APP is the short video APP with the largest number of users in China. This study aimed to evaluate the quality and reliability of short videos about cosmetic surgery on Douyin. In August 2022, we retrieved and screened 300 short videos related to cosmetic surgery from Douyin, extracted basic video information, encoded the contentand identified the video source. The quality and reliability of short video information were evaluated using the DISCERN instrument. A total of 168 short videos of cosmetic surgery were included in the survey, and the video sources included personal accounts and institutional accounts. Overall, the total proportion of institutional accounts (47/168, 27.98%) is significantly less than that of personal accounts (121/168, 72.02%); nonhealth professionals received the most praises, comments and even collections and reposts, while for-profit academic organizations or institutions received the least. The DISCERN scores of 168 short videos of cosmetic surgery were 3.74-4.58 (average 4.22). Content reliability (p = .04) and overall short video quality (p = .02) are significantly different, but short videos published from different sources have no significant difference in treatment selection (p = .052). The overall information quality and reliability of short videos about cosmetic surgery on Douyin are satisfactory in China. The participants were involved in developing research questions, study design, management and conduct, interpretation of evidence and dissemination.

Recording and analysing physical control variables used in clarinet playing: A musical instrument performance capture and analysis toolbox (MIPCAT)

Measuring fine-grained physical interaction between the human player and the musical instrument can significantly improve our understanding of music performance. This article presents a Musical Instrument Performance Capture and Analysis Toolbox (MIPCAT) that can be used to capture and to process the physical control variables used by a musician while performing music. This includes both a measurement apparatus with sensors and a software toolbox for analysis. Several of the components used here can also be applied in other musical contexts. The system is here applied to the clarinet, where the instrument sensors record blowing pressure, reed position, tongue contact, and sound pressures in the mouth, mouthpiece, and barrel. Radiated sound and multiple videos are also recorded to allow details of the embouchure and the instrument’s motion to be determined. The software toolbox can synchronise measurements from different devices, including video sources, extract time-variable descriptors, segment by notes and excerpts, and summarise descriptors per note, phrase, or excerpt. An example of its application shows how to compare performances from different musicians.

Quality of Information in Gallstone Disease Videos on TikTok: Cross-sectional Study.

TikTok was an important channel for consumers to access and adopt health information. But the quality of health content in TikTok remains underinvestigated. Our study aimed to identify upload sources, contents, and feature information of gallstone disease videos on TikTok and further evaluated the factors related to video quality. We investigated the first 100 gallstone-related videos on TikTok and analyzed these videos' upload sources, content, and characteristics. The quality of videos was evaluated using quantitative scoring tools such as DISCERN instrument, the Journal of American Medical Association (JAMA) benchmark criteria, and Global Quality Scores (GQS). Moreover, the correlation between video quality and video characteristics, including duration, likes, comments, and shares, was further investigated. According to video sources, 81% of the videos were posted by doctors. Furthermore, disease knowledge was the most dominant video content, accounting for 56% of all the videos. The mean DISCERN, JAMA, and GQS scores of all 100 videos are 39.61 (SD 11.36), 2.00 (SD 0.40), and 2.76 (SD 0.95), respectively. According to DISCERN and GQS, gallstone-related videos' quality score on TikTok is not high, mainly at fair (43/100, 43%,) and moderate (46/100, 46%). The total DISCERN scores of doctors were significantly higher than that of individuals and news agencies, surgery techniques were significantly higher than lifestyle and news, and disease knowledge was significantly higher than news, respectively. DISCERN scores and video duration were positively correlated. Negative correlations were found between DISCERN scores and likes and shares of videos. In GQS analysis, no significant differences were found between groups based on different sources or different contents. JAMA was excluded in the video quality and correlation analysis due to a lack of discrimination and inability to evaluate the video quality accurately. Although the videos of gallstones on TikTok are mainly provided by doctors and contain disease knowledge, they are of low quality. We found a positive correlation between video duration and video quality. High-quality videos received low attention, and popular videos were of low quality. Medical information on TikTok is currently not rigorous enough to guide patients to make accurate judgments. TikTok was not an appropriate source of knowledge to educate patients due to the low quality and reliability of the information.

Pixel-Based Swallow Measurements: Correcting Nonsquare Pixels

This research note illustrates the effects of video data with nonsquare pixels on the pixel-based measures obtained from videofluoroscopic swallow studies (VFSS). Six pixel-based distance and area measures were obtained from two different videoflouroscopic study units; both yielding videos with nonsquare pixels with different pixel aspect ratios (PARs). The swallowing measures were obtained from the original VFSS videos and from the videos after their pixels were squared. The results demonstrated significant multivariate effects both in video type (original vs. squared) and in the interaction between video type and sample (two video recordings of different patients, different PARs, and opposing tilt angles of the external reference). A wide range of variabilities was observed on the pixel-based measures between original and squared videos with the percent deviation ranging from 0.1% to 9.1% with the maximum effect size of 7.43. This research note demonstrates the effect of disregarding PAR to distance and area pixel-based parameters. In addition, we present a multilevel roadmap to prevent possible measurement errors that could occur. At the planning stage, the PAR of video source should be identified, and, at the analyses stage, video data should be prescaled prior to analysis with PAR-unaware software. No methodology in prior absolute or relative pixel-based studies reports adjustment to the PAR prior to measurements nor identify the PAR as a possible source of variation within the literature. Addressing PAR will improve the precision and stability of pixel-based VFSS findings and improve comparability within and across clinical and research settings. https://doi.org/10.23641/asha.21957134.

Research on unbalanced mining of highway project key data based on knowledge graph and cloud model

Various stages of highway project construction process involve text, image, audio, video and other related data sources involving many participants, forming a huge amount of data. Accurately tracing the source of responsibility, refining and applying the unbalanced data in the highway project archives is of great significance for realizing the intelligent transformation of highway construction project management. This paper firstly sorts out the construction process of highway projects and the main data sources, constructs a data association network between construction entities and construction process, as well as a knowledge map of highway construction data. Then, according to the highway construction stage, an index system based on 12 key data is constructed by using the entropy weight cloud model method, and the importance of the data is evaluated. Thirdly, based on the unbalanced characteristics of highway project data, a method of mining big data in highway project archives using classification evaluation indexes is proposed, and the accuracy of this method is verified by case calculation. Finally, taking the Shizong Qiubei Expressway in China as an example, the intelligent management and control suggestions for key data of transportation projects are proposed. It is found that the key data with special importance rate in highway construction include construction data, supervision data and completion data. Boosting algorithm is more accurate than the traditional SMOTE algorithm for unbalanced data mining, which helps to save the project construction cost and improve the quality of data extraction in the project archives. This study provides a theoretical reference for key data traceability of highway project intelligent management and control platform and the improvement of intelligent management efficiency.

Evaluation of Information Reliability and Quality of Youtube™ Videos About White Spot Lesions

Objective: The aim of this study was to determine the quality and reliability of the information provided by YouTube™ videos about white spot lesion. Methods: YouTube™ videos were searched for the term 'white spot lesion' (WSL) by relevance. 142 videos about WSL were analyzed and 56 videos that met the inclusion criteria were evaluated. Video demographics (number of views, duration, number of likes, number of comments) viewing rate, primary purpose, video sources were determined and the reliability and the quality of the listed videos were evaluated with modified DISCERN (ModDISCERN) scale and the Global Quality Scale (GQS). Kruskall-Wallis, Mann–Whitney U test, Spearman’s correlation coefficients and Intra-class Correlation Coefficient were used for statistical analyses. Results: The majority of YouTube™ videos analyzed on WSL were uploaded by YouTube™ channels (50%), with 29% uploaded by dentists and 21% by companies. The mean/standard deviation (SD) ModDISCERN score, showing the reliability of the information in the videos, was 2.71±1.22; and the mean/SD GQS value showing the video quality was 2.71±1.14. 25% of the videos’ GQS value was >3, and the reliability of the information in these videos was significantly higher than the videos with a GQS of ≤3 (3.93 vs. 2.31; P<0.001). There was a high correlation between GQS and ModDISCERN scores in all 3 video source groups (Dentist r=0.805, Company r=0.757, YouTube™ Channel r=0.917; P<0.01). Conclusion: The information reliability and video quality of most YouTube™ videos about WSL, is not sufficient. Orthodontists and dentists should direct their patients to reliable information sources about WSL.

COVID-19 Information on YouTube: Analysis of Quality and Reliability of Videos in Eleven Widely Spoken Languages across Africa.

Whilst the coronavirus disease 2019 (COVID-19) vaccination rollout is well underway, there is a concern in Africa where less than 2% of global vaccinations have occurred. In the absence of herd immunity, health promotion remains essential. YouTube has been widely utilised as a source of medical information in previous outbreaks and pandemics. There are limited data on COVID-19 information on YouTube videos, especially in languages widely spoken in Africa. This study investigated the quality and reliability of such videos. Medical information related to COVID-19 was analysed in 11 languages (English, isiZulu, isiXhosa, Afrikaans, Nigerian Pidgin, Hausa, Twi, Arabic, Amharic, French, and Swahili). Cohen's Kappa was used to measure inter-rater reliability. A total of 562 videos were analysed. Viewer interaction metrics and video characteristics, source, and content type were collected. Quality was evaluated using the Medical Information Content Index (MICI) scale and reliability was evaluated by the modified DISCERN tool. Kappa coefficient of agreement for all languages was p < 0.01. Informative videos (471/562, 83.8%) accounted for the majority, whilst misleading videos (12/562, 2.13%) were minimal. Independent users (246/562, 43.8%) were the predominant source type. Transmission of information (477/562 videos, 84.9%) was most prevalent, whilst content covering screening or testing was reported in less than a third of all videos. The mean total MICI score was 5.75/5 (SD 4.25) and the mean total DISCERN score was 3.01/5 (SD 1.11). YouTube is an invaluable, easily accessible resource for information dissemination during health emergencies. Misleading videos are often a concern; however, our study found a negligible proportion. Whilst most videos were fairly reliable, the quality of videos was poor, especially noting a dearth of information covering screening or testing. Governments, academic institutions, and healthcare workers must harness the capability of digital platforms, such as YouTube to contain the spread of misinformation.

Nonlinear remote monitoring system of manipulator based on network communication technology

Abstract In order to study the nonlinear remote monitoring system of the manipulator based on the network communication technology, a research method of the nonlinear remote monitoring system of the manipulator based on the network communication technology is proposed. In this article, in the Visual C++ environment, the transmission control protocol/internet protocol technology is used to build a remote monitoring system for the robotic arm, and it mainly realizes the function of the robotic arm running according to the trajectory in the remote. When storing video, you need to specify the ID of the video source, i.e., the synchronization source in the real-time transport protocol data packet header identifies the robot, which can monitor more clearly. The remote monitoring technology is widely used in the modern automation industry, which not only further extends the human space activity ability, but also removes the human from the dangerous and complex working environment. Therefore, the remote monitoring technology has broad application prospects.

TikTok and adolescent vision health: Content and information quality assessment of the top short videos related to myopia.

Despite the increasing recognition of the public health value of social media platforms, TikTok short videos focusing on adolescent vision health have not received much attention. We aimed to evaluate the content, sources, and information quality of myopia-related videos on TikTok. The top 200 most-liked myopia-related videos on the Chinese version of TikTok were queried and screened on March 12, 2022. The descriptive characteristics, contents, and sources of the selected 168 videos were obtained, and their overall quality, reliability, understandability, and actionability were assessed using the validated scoring instruments DISCERN and PEMAT-A/V. Medical professionals were the main source (45.8%, 77/168) of videos. Misinformation (10.1%, 17/168) was mainly attributable to for-profit organizations (20%, 3/15) and individual non-medical users (31.3%, 10/32). However, their videos enjoyed the highest numbers of "likes," "comments," and "shares" (P < 0.05). The mean reliability and overall quality regarding treatment choice were (2.5 ± 0.5) and (3.1 ± 0.9), respectively. Videos on TikTok showed relatively high understandability (84.7%) and moderate actionability (74.9%). Video producers tended to partly or fully provide information regarding management (81.5%, 137/168) and outcome (82.1%, 138/168), and to ignore or only slightly mention content related to definition (86.9%, 146/169) and signs (82.1%, 138/168). The five video sources showed significant differences in the prevalence of misleading information (P < 0.001), publication reliability (P < 0.001), overall quality (P = 0.039), content score (P = 0.019), and understandability (P = 0.024). Considering the moderate-to-poor reliability and variable quality across video sources, the substantial myopia-related content on TikTok should be treated with caution. Nevertheless, TikTok videos may serve as a surrogate or supplement for information dissemination if providers can ensure more comprehensive and accurate content.

Synchronized Multistream Transport Using RIST

Many broadcast contribution applications require synchronized content decoding. In such applications, there are several video sources (typically cameras), whose content needs to be transported using encoders to an equivalent number of remote decoders. At the decoders, the playback needs to be synchronized—frames that arrive together at the encoders are required to come out together at the decoders. Typical applications are sports and worship, where multiple camera angles are generated and need to be played in lockstep. There are a few products available today in the market that provide such functionality over IP, using proprietary protocols. The Reliable Internet Stream Transport (RIST) Activity Group (AG) is completing the work on an open industry specification for providing synchronized multistream transport. This article provides a technical description of the methods in the specification, as well as some actual field performance data.

Wireless Deep Video Semantic Transmission

In this paper, we design a new class of high-efficiency deep joint source-channel coding methods to achieve end-to-end video transmission over wireless channels. The proposed methods exploit nonlinear transform and conditional coding architecture to adaptively extract semantic features across video frames, and transmit semantic feature domain representations over wireless channels via deep joint source-channel coding. Our framework is collected under the name deep video semantic transmission (DVST). In particular, benefiting from the strong temporal prior provided by the feature domain context, the learned nonlinear transform function becomes temporally adaptive, resulting in a richer and more accurate entropy model guiding the transmission of current frame. Accordingly, a novel rate adaptive transmission mechanism is developed to customize deep joint source-channel coding for video sources. It learns to allocate the limited channel bandwidth within and among video frames to maximize the overall transmission performance. The whole DVST design is formulated as an optimization problem whose goal is to minimize the end-to-end transmission rate-distortion performance under perceptual quality metrics or machine vision task performance metrics. Across standard video source test sequences and various communication scenarios, experiments show that our DVST can generally surpass traditional wireless video coded transmission schemes. The proposed DVST framework can well support future semantic communications due to its video content-aware and machine vision task integration abilities.

Serghei Cretu and neo-traditional music: the path of creation in the Soviet period

Th e study „Sergei Cretu and neo-traditional music: the creative path in the Soviet period” sketches a brief portrait of the artist, highlighting the important biographical data on specialized studies, the context of professional evolution in the Soviet period of the 1960s-1980s, marked by the so-called „new wave of folklore”. Special emphasis is placed on the reflection of his activity as a dulcimer player, arranger and composer in the Popular Stage Orchestra and in the „Folclor” Orchestra of the Moldovan Republican Television and Radio Broadcasting Company. The main compartments and aesthetic directions in the his interpretive and compositional creation, the structure of the genres and styles, including the place, the sources and the social motivations of the works of Soviet ideological inspiration and instrumentalization are also highlighted. The study capitalizes on documents, data and information from the Archive of the „Teleradio-Moldova” Company, materials from the press of the time, audio and video sources as well as a series of concepts from modern specialty literature, able to promote the interpretation and analysis of cultural facts.

Pelphix: Surgical Phase Recognition from X-ray Images in Percutaneous Pelvic Fixation.

Surgical phase recognition (SPR) is a crucial element in the digital transformation of the modern operating theater. While SPR based on video sources is well-established, incorporation of interventional X-ray sequences has not yet been explored. This paper presents Pelphix, a first approach to SPR for X-ray-guided percutaneous pelvic fracture fixation, which models the procedure at four levels of granularity - corridor, activity, view, and frame value - simulating the pelvic fracture fixation workflow as a Markov process to provide fully annotated training data. Using added supervision from detection of bony corridors, tools, and anatomy, we learn image representations that are fed into a transformer model to regress surgical phases at the four granularity levels. Our approach demonstrates the feasibility of X-ray-based SPR, achieving an average accuracy of 99.2% on simulated sequences and 71.7% in cadaver across all granularity levels, with up to 84% accuracy for the target corridor in real data. This work constitutes the first step toward SPR for the X-ray domain, establishing an approach to categorizing phases in X-ray-guided surgery, simulating realistic image sequences to enable machine learning model development, and demonstrating that this approach is feasible for the analysis of real procedures. As X-ray-based SPR continues to mature, it will benefit procedures in orthopedic surgery, angiography, and interventional radiology by equipping intelligent surgical systems with situational awareness in the operating room.

Automated Video-Based Face Detection Using Harris Hawks Optimization with Deep Learning

Face recognition technology automatically identifies an individual from image or video sources. The detection process can be done by attaining facial characteristics from the image of a subject face. Recent developments in deep learning (DL) and computer vision (CV) techniques enable the design of automated face recognition and tracking methods. This study presents a novel Harris Hawks Optimization with deep learning-empowered automated face detection and tracking (HHODL-AFDT) method. The proposed HHODL-AFDT model involves a Faster region based convolution neural network (RCNN)-based face detection model and HHO-based hyperparameter optimization process. The presented optimal Faster RCNN model precisely recognizes the face and is passed into the face-tracking model using a regression network (REGN). The face tracking using the REGN model uses the features from neighboring frames and foresees the location of the target face in succeeding frames. The application of the HHO algorithm for optimal hyperparameter selection shows the novelty of the work. The experimental validation of the presented HHODL-AFDT algorithm is conducted using two datasets and the experiment outcomes highlighted the superior performance of the HHODL-AFDT model over current methodologies with maximum accuracy of 90.60% and 88.08% under PICS and VTB datasets, respectively.

YouTube as a source of information on coccydynia

In recent years, the use of YouTube for obtaining medical information has increased. In this article, we aimed to determine the usefulness, quality,and reliability of YouTube videos on coccydynia. Coccydynia and "coccyx pain" were searched for on YouTube on October 2, 2022. The study comprised 80 of the 120 videos that were discovered as a consequence of the search and met the inclusion criteria. The videos' videometric properties were noted. Depending on whether the content utilized information from evidence-based scientific sources,the videos were separated into two groups: useful and misleading. The measure popularity, the Video Power Index (VPI) was applied. To measure reliability, the modified DISCERN (mDISCERN) was applied. To evaluate quality, the Global Quality Score (GQS) was applied. This study found that 28.7% of the video sources were from physicians and 73.8% of the videos were classified as useful, while 26.2% were classified as misleading. Videos posted by doctors and academic institutions/professional organizations were all in the useful group, while all videos uploaded by independent users and patients were in the misleading group. The useful videos had higher VPI, GQS, and mDISCERN scores, indicating that videos posted by healthcare professionals and academic institutions were more reliable and of higher quality than those from patients and independent users. The significant number of the coccydynia-related YouTube videos were reliable, useful, and of high quality. Healthcare providers should be aware of the value of YouTube's health-related content and maintain high-quality content.

Evaluation of YouTube Videos on Hepatocellular Carcinoma.

As in every field, online information has become increasingly used in health. However, it is well known that some information online containing health advice is incorrect and may even include false statements. For this reason, it is crucial for public health that individuals reach reliable, high-quality resources when they are trying to obtain health information. Studies have been conducted on the quality and reliability of online information about many diseases, but no similar study has been found in the literature on hepatocellular carcinoma (HCC). In this descriptive study, videos on YouTube (www.youtube.com) about HCC were evaluated using the Global Quality Scale (GQS) and the modified DISCERN tool. While 129 (89.58%) of the videos examined within the study were considered useful, 15 (10.42%) were misleading. The GQS scores of the videos considered useful were significantly higher than the scores of the misleading videos, with a median (min-max) score of 4 (2-5) (P < 0.001). When we compared the DISCERN scores, the scores of the useful videos were significantly higher (P < 0.001) than the scores of the misleading videos. YouTube should be considered a complex structure where accurate and reliable health information can be presented, as well as erroneous and misleading information. Users should understand the importance of video sources and focus their research on videos from doctors, academics, and universities.