Number Of Frames Research Articles

Human Motion Recognition Using Temporal Foot-Lift Features Extracted from a Small Number of Skeleton Data Frames and Multi Classifiers

Human Motion Recognition Using Temporal Foot-Lift Features Extracted from a Small Number of Skeleton Data Frames and Multi Classifiers

Pengolahan Citra Berbasis Video Proccesing dengan Metode Frame Difference untuk Deteksi Gerak

This study discusses the detection of motion of objects in video by utilizing the Frame difference method which aims to process video so as to produce Frames on moving objects. The use of mobile cameras produces video data that is used as test data, the test data is processed with the Frame difference method so as to produce a number of Frames on moving objects in order to detect moving objects in the video because the function of this method is a form of video background reduction that is simplified by a number of pixels in the video. This method process is based on the difference between two consecutive frames in the video aimed at finding differences that occur during the detection process. When processed for detection, the absolute value in the pixel is greater than the predetermined threshold value, it will be considered as a moving object, so that the detection results from the motion detection process will form a box object on the moving object. In this study, the test data used used 20 video data samples with descriptions, 10 test data with bright quality (daytime) and 10 unlit test data (night) with the aim of being able to see how much the level of performance accuracy of the Frame difference method. The test results obtained 16 out of 20 test data that were successfully detected correctly (True Positive), there were 2 test data that resulted in a False Positive error, and 2 test data that resulted in a False Negative error. This shows that the Frame difference method can provide a fairly high level of accuracy in detecting moving objects in the video. The percentage level of accuracy with confussion matrix testing has a precission value of 88%, recal 88% and an accuracy value of 80%.

An Enhanced Human Gait Recognition System using UALNN Classifier

Human gait recognition is a biometric identification method that uses a person’s gait patterns to identify them. Gait Recognition (GR) is the steps to follow in recognizing walking style of an individual. It identifies a person as of a longer distance with higher precision owing to its unique characteristics; thus, it is mostly utilized for tracking purposes. In computer vision software, specifically, to track the same individual across multiple scenarios, the individual recognition across numerous cameras is a significant task. However, owing to the position of caught image or video, human identification by means of GR could be limited. Therefore, for person re-identification, a novel GR methodology has been proposed here. Five phases were undergone by the proposed methodology. Initially, from an openly accessible dataset, the input video is collected, which is then transmuted into a number of frames. To eliminate the noise from the frames, the Mean Modified Filter (MMF) is utilized after frame conversion. The Gaussian Taxicab Mixture Model (GTMM) is employed to get rid of the background from the frames. After that, Similarity Histogram Silhouette Segmentation (SHSS) model is utilized to segment the humans’ silhouette as of the background removed frames; thus, generating the energy image. The features are extracted from this energy image. The Uniform Alex Neural Network classifier (UALNN) uses these features to identify the human gait. Improved recognition performance is attained from the experiential outcomes. The overall recognition outcomes obtained concluded that the proposed methodology is highly promising.

The complete mitochondrial genomes of five critical phytopathogenic Bipolaris species: features, evolution, and phylogeny

In the present study, three mitogenomes from the Bipolaris genus (Bipolaris maydis, B. zeicola, and B. oryzae) were assembled and compared with the other two reported Bipolaris mitogenomes (B. oryzae and B. sorokiniana). The five mitogenomes were all circular DNA molecules, with lengths ranging from 106,403 bp to 135,790 bp. The mitogenomes of the five Bipolaris species mainly comprised the same set of 13 core protein-coding genes (PCGs), two rRNAs, and a certain number of tRNAs and unidentified open reading frames (ORFs). The PCG length, AT skew and GC skew showed large variability among the 13 PCGs in the five mitogenomes. Across the 13 core PCGs tested, nad6 had the least genetic distance among the 16 Pleosporales species we investigated, indicating that this gene was highly conserved. In addition, the Ka/Ks values for all 12 core PCGs (excluding rps3) were < 1, suggesting that these genes were subject to purifying selection. Comparative mitogenomic analyses indicate that introns were the main factor contributing to the size variation of Bipolaris mitogenomes. The introns of the cox1 gene experienced frequent gain/loss events in Pleosporales species. The gene arrangement and collinearity in the mitogenomes of the five Bipolaris species were almost highly conserved within the genus. Phylogenetic analysis based on combined mitochondrial gene datasets showed that the five Bipolaris species formed well-supported topologies. This study is the first report on the mitogenomes of B. maydis and B. zeicola, as well as the first comparison of mitogenomes among Bipolaris species. The findings of this study will further advance investigations into the population genetics, evolution, and genomics of Bipolaris species.

Multifold enhancement of quantum SNR by using an EMCCD as a photon number resolving device

Electron multiplying charge-coupled devices (EMCCDs), owing to their high quantum efficiency and spatial resolution, are widely used to study typical quantum optical phenomena and related applications. Researchers have already developed a procedure that enables one to statistically determine whether a pixel detects a single photon, based on whether its output is higher or lower than the estimated noise level. However, these techniques are feasible at extremely low photon numbers (≈0.15 mean number of photons per pixel per exposure), allowing for at most one photon per pixel. This limitation necessitates a very large number of frames required for any study. In this work, we present a method to estimate the mean rate of photons per pixel per frame for arbitrary exposure time. Subsequently, we make a statistical estimate of the number of photons (≥ 1) incident on each pixel. This allows us to effectively use the EMCCD as a photon number resolving device. This immediately augments the acceptable light levels in the experiments, leading to significant reduction in the required experimentation time. As evidence of our approach, we quantify contrast in quantum correlation exhibited by a pair of spatially entangled photons generated by a spontaneous parametric down conversion process. In comparison with conventional methods, our method realizes an enhancement in the signal-to-noise ratio (SNR) by approximately a factor of 3 for half the data collection time. This SNR can be easily enhanced by minor modifications in experimental parameters such as exposure time, etc.

A two-stream sign language recognition network based on keyframe extraction method

Sign language recognition (SLR) tasks are typically performed on a large number of continuous frames of sign language videos, making it challenging to utilize information efficiently and accurately from such a vast amount of data. Firstly, to efficiently utilize the information, it is necessary to select key information from numerous video frames to summarize the video. Therefore, this paper proposes a new method for key frame extraction that efficiently summarizes video information and addresses the issues of key frame clustering and data imbalance present in previous methods. Secondly, for more accurate information utilization, it is essential to learn the correct sign language expression features from a large dataset. Hence, we establish the Full-hand two-stream network to focus on the most crucial hand features in sign language expressions. The Full stream employs attention blocks to extract deep-level information and establishes temporal dependencies using global attention module. The Hand stream utilizes hand attention to focus on hand-specific feature information. Ultimately, our approach achieves state-of-the-art results on the CSL–500 Dataset and competitive results on the LSA64 Dataset. This paper validates the effectiveness of keyframe extraction methods and two-stream networks on the AUTSL dataset.

Variable Temporal Length Training for Action Recognition CNNs.

Most current deep learning models are suboptimal in terms of the flexibility of their input shape. Usually, computer vision models only work on one fixed shape used during training, otherwise their performance degrades significantly. For video-related tasks, the length of each video (i.e., number of video frames) can vary widely; therefore, sampling of video frames is employed to ensure that every video has the same temporal length. This training method brings about drawbacks in both the training and testing phases. For instance, a universal temporal length can damage the features in longer videos, preventing the model from flexibly adapting to variable lengths for the purposes of on-demand inference. To address this, we propose a simple yet effective training paradigm for 3D convolutional neural networks (3D-CNN) which enables them to process videos with inputs having variable temporal length, i.e., variable length training (VLT). Compared with the standard video training paradigm, our method introduces three extra operations during training: sampling twice, temporal packing, and subvideo-independent 3D convolution. These operations are efficient and can be integrated into any 3D-CNN. In addition, we introduce a consistency loss to regularize the representation space. After training, the model can successfully process video with varying temporal length without any modification in the inference phase. Our experiments on various popular action recognition datasets demonstrate the superior performance of the proposed method compared to conventional training paradigm and other state-of-the-art training paradigms.

Optimization and impact of sensitivity mode on abbreviated scan protocols with population-based input function for parametric imaging of [18F]-FDG for a long axial FOV PET scanner

BackgroundThe long axial field of view, combined with the high sensitivity of the Biograph Vision Quadra PET/CT scanner enables the precise deviation of an image derived input function (IDIF) required for parametric imaging. Traditionally, this requires an hour-long dynamic PET scan for [18F]-FDG, which can be significantly reduced by using a population-based input function (PBIF). In this study, we expand these examinations and include the scanner’s ultra-high sensitivity (UHS) mode in comparison to the high sensitivity (HS) mode and evaluate the potential for further shortening of the scan time.MethodsPatlak Ki and DV estimates were determined by the indirect and direct Patlak methods using dynamic [18F]-FDG data of 6 oncological patients with 26 lesions (0–65 min p.i.). Both sensitivity modes for different number/duration of PET data frames were compared, together with the potential of using abbreviated scan durations of 20, 15 and 10 min by using a PBIF. The differences in parametric images and tumour-to-background ratio (TBR) due to the shorter scans using the PBIF method and between the sensitivity modes were assessed.ResultsA difference of 3.4 ± 7.0% (Ki) and 1.2 ± 2.6% (DV) was found between both sensitivity modes using indirect Patlak and the full IDIF (0–65 min). For the abbreviated protocols and indirect Patlak, the UHS mode resulted in a lower bias and higher precision, e.g., 45–65 min p.i. 3.8 ± 4.4% (UHS) and 6.4 ± 8.9% (HS), allowing shorter scan protocols, e.g. 50–65 min p.i. 4.4 ± 11.2% (UHS) instead of 7.3 ± 20.0% (HS). The variation of Ki and DV estimates for both Patlak methods was comparable, e.g., UHS mode 3.8 ± 4.4% and 2.7 ± 3.4% (Ki) and 14.4 ± 2.7% and 18.1 ± 7.5% (DV) for indirect and direct Patlak, respectively. Only a minor impact of the number of Patlak frames was observed for both sensitivity modes and Patlak methods. The TBR obtained with direct Patlak and PBIF was not affected by the sensitivity mode, was higher than that derived from the SUV image (6.2 ± 3.1) and degraded from 20.2 ± 12.0 (20 min) to 10.6 ± 5.4 (15 min). Ki and DV estimate images showed good agreement (UHS mode, RC: 6.9 ± 2.3% (Ki), 0.1 ± 3.1% (DV), peak signal-to-noise ratio (PSNR): 64.5 ± 3.3 dB (Ki), 61.2 ± 10.6 dB (DV)) even for abbreviated scan protocols of 50–65 min p.i.ConclusionsBoth sensitivity modes provide comparable results for the full 65 min dynamic scans and abbreviated scans using the direct Patlak reconstruction method, with good Ki and DV estimates for 15 min short scans. For the indirect Patlak approach the UHS mode improved the Ki estimates for the abbreviated scans.

Behavior of rock bolt plates made of engineering fiber composites: Experimental investigations, 3D surface characterization and numerical models

Bearing plates made from plastic composites can be used as an alternative to their steel counterparts in rock bolt or soil nail applications. To achieve this goal, an existing recycled high-density polyethylene bearing plate was investigated and later modified to improve its engineering properties. Laboratory studies were conducted to determine the failure load of the existing and modified plates, and a numerical model was developed for complementary analysis. The results of both efforts clearly showed that the existing bearing plate was not adequate in terms of strength and creep properties, as it quickly yielded with large displacements at relatively low loads. In order to enhance the strength of the plate, both geometric and material modifications are made by our research group to obtain a more efficient plate. Numerical models were used to determine the frame layout, and a series of analyses were performed to evaluate the effects of frame thickness, number and arrangement. Once the design was optimized and finalized, a mold was created to match the new geometry for manufacturing new plates through injection molding. A test setup was also established in the laboratory and numerous compression tests were performed on the manufactured new plates. The measured load-displacement behavior of plates made of polyethylene and polyamide with a variety of additives were discussed separately. It was determined that the new plastic plates reinforced with polyamide through various additives have the potential to reach a strength up to 200–240 kN, which is at least two times higher than the existing one, with distinct economic advantages.

TQU-SLAM Benchmark Dataset for Comparative Study to Build Visual Odometry Based on Extracted Features from Feature Descriptors and Deep Learning

The problem of data enrichment to train visual SLAM and VO construction models using deep learning (DL) is an urgent problem today in computer vision. DL requires a large amount of data to train a model, and more data with many different contextual and conditional conditions will create a more accurate visual SLAM and VO construction model. In this paper, we introduce the TQU-SLAM benchmark dataset, which includes 160,631 RGB-D frame pairs. It was collected from the corridors of three interconnected buildings comprising a length of about 230 m. The ground-truth data of the TQU-SLAM benchmark dataset were prepared manually, including 6-DOF camera poses, 3D point cloud data, intrinsic parameters, and the transformation matrix between the camera coordinate system and the real world. We also tested the TQU-SLAM benchmark dataset using the PySLAM framework with traditional features such as SHI_TOMASI, SIFT, SURF, ORB, ORB2, AKAZE, KAZE, and BRISK and features extracted from DL such as VGG, DPVO, and TartanVO. The camera pose estimation results are evaluated, and we show that the ORB2 features have the best results (Errd = 5.74 mm), while the ratio of the number of frames with detected keypoints of the SHI_TOMASI feature is the best (rd=98.97%). At the same time, we also present and analyze the challenges of the TQU-SLAM benchmark dataset for building visual SLAM and VO systems.

Understanding the impact of persistence and propagation on the Age of Information of broadcast traffic in 5G NR-V2X sidelink communications

The current Cellular V2X (C-V2X) standard for direct communication between vehicles is based on the so called Semi-Persistent Scheduling (SPS) algorithm. It is based on the multiple access structure of 5G New Radio (NR) and exploits sensing and persistence to realize a randomized multiple access. We consider the application of SPS to support periodic broadcast traffic where no acknowledgments are provided. Persistence is a key feature, which consists of a node using the same resource for its transmissions for multiple frames. The specific resource used is randomly selected from among those that are perceived to be idle, and reselected anew after a randomized number of frames. We define a model to gain insight into the interplay between persistence and key performance metrics for the type of traffic considered, namely probability of successful delivery and Age of Information (AoI). A core version of the model is validated against simulations and used to show that there exists an optimal level that minimizes AoI. The model is then extended to account for a distance-dependent propagation model, allowing further insight into the effects of the interplay between sender–receiver distance and persistence. Finally, an even more detailed model is investigated, using ns-3-based simulations. This further analysis confirms the qualitative behaviors revealed by the analytical model and provides more insight into the complex interactions of system parameters and channel characteristics. The obtained results help to identify the limits of SPS, opening the way to system-principled parameter optimization and design of more powerful variants of the multiple access scheme.

DRIVER DROWSINESS DETECTION SYSTEM

The proposed system utilizes facial landmark detection and eye aspect ratio calculation to detect drowsiness in real-time from a webcam feed. It employs the dlib library for face detection and facial landmark prediction. The eye aspect ratio (EAR) is computed from the distances between specific points on the eyes. When the EAR falls below a predefined threshold for a certain number of consecutive frames, it triggers an alert indicating potential drowsiness. The alert includes visual cues on the video feed, an auditory alert using the playsound library, and even sends an instant WhatsApp message using pywhatkit to notify a designated contact about the drowsiness. This system serves as a useful tool for monitoring driver fatigue or alertness in various contexts, promoting safety and awareness. Its capacity to swiftly identify and alert users to the onset of drowsiness represents a significant leap forward in safety technology. By mitigating the risk of accidents stemming from fatigue-induced impairments, this project underscores the pivotal role of computer vision in real-time human behavior monitoring, offering a versatile and invaluable tool for fostering safety and awareness across various domains. Keywords: Drowsiness Detection; Python; Whatsapp messaging; Webcam feed; Computer Vision; Alert System; Real-time monitoring; Eye-Aspect Ratio; Frame Processing; Facial Recognition.

Factorized and progressive knowledge distillation for CTC-based ASR models

Knowledge distillation (KD) is a popular model compression method to improve the performance of lightweight models by transferring knowledge from a teacher model to a student model. However, applying KD to connectionist temporal classification (CTC) ASR model is challenging due to its peaky posterior property. In this paper, we propose to address this issue by treating non-blank and blank frames differently for two main reasons. First, the non-blank frames in the teacher model’s posterior matrix and hidden representations provide more acoustic and linguistic information than the blank frames, but the frame number of non-blank frames only accounts for a small fraction of all frames, leading to a severe learning imbalance problem. Second, the non-blank tokens in the teacher’s blank-frame posteriors exhibit irregular probability distributions, negatively impacting the student model’s learning. Thus, we propose to factorize the distillation of non-blank and blank frames and further combine them into a progressive KD framework, which contains three incremental stages to facilitate the student model gradually building up its knowledge. The first stage involves a simple binary classification KD task, in which the student learns to distinguish between non-blank and blank frames, as the two types of frames are learned separately in subsequent stages. The second stage is a factorized representation-based KD, in which hidden representations are divided into non-blank and blank frames so that both can be distilled in a balanced manner. In the third stage, the student learns from the teacher’s posterior matrix through our proposed method, factorized KL-divergence (FKL), which performs different operation on blank and non-blank frame posteriors to alleviate the imbalance issue and reduce the influence of irregular probability distributions. Compared to the baseline, our proposed method achieves 22.5% relative CER reduction on the Aishell-1 dataset, 23.0% relative WER reduction on the Tedlium-2 dataset, and 17.6% relative WER reduction on the LibriSpeech dataset. To show the generalization of our method, we also evaluate our method on the hybrid CTC/Attention architecture as well as on scenarios with cross-model topology KD.

Identification of Circular Patterns in Capsule Endoscopy Bubble Frames.

A significant number of frames captured by the wireless capsule endoscopy are involved with varying amounts of bubbles. Whereas different studies have considered bubbles as nonuseful agents due to the fact that they reduce the visualization quality of the small intestine mucosa, this research aims to develop a practical way of assessing the rheological capability of the circular bubbles as a suggestion for future clinical diagnostic purposes. From the Kvasir-capsule endoscopy dataset, frames with varying levels of bubble engagements were chosen in two categories based on bubble size. Border reflections are present on the edges of round-shaped bubbles in their boundaries, and in the frequency domain, high-frequency bands correspond to these edges in the spatial domain. The first step is about high-pass filtering of border reflections using wavelet transform (WT) and Differential of Gaussian, and the second step is related to applying the Fast Circlet Transform (FCT) and the Hough transform as circle detection tools on extracted borders and evaluating the distribution and abundance of all bubbles with the variety of radii. Border's extraction using WT as a preprocessing approach makes it easier for circle detection tool for better concentration on high-frequency circular patterns. Consequently, applying FCT with predefined parameters can specify the variety and range of radius and the abundance for all bubbles in an image. The overall discrimination factor (ODF) of 15.01, and 7.1 showing distinct bubble distributions in the gastrointestinal (GI) tract. The discrimination in ODF from datasets 1-2 suggests a relationship between the rheological properties of bubbles and their coverage area plus their abundance, highlighting the WT and FCT performance in determining bubbles' distributions for diagnostic objectives. The implementation of an object-oriented attitude in gastrointestinal analysis makes it intelligible for gastroenterologists to approximate the constituent features of intra-intestinal fluids. this can't be evaluated until the bubbles are considered as non-useful agents. The obtained results from the datasets proved that the difference between the calculated ODF can be used as an indicator for the quality estimation of intraintestinal fluids' rheological features like viscosity, which helps gastroenterologists evaluate the quality of patient digestion.

Intelligent speech elderly rehabilitation learning assistance system based on deep learning and sensor networks

Recently, deep learning has been proved to significantly improve the quality of speech recognition. Convolutional neural networks are often used in speech recognition tasks because of their special network structure and powerful learning function. In order to solve the problem that the traditional convolutional neural network can not reflect the one-dimensional basic attributes of speech signal, this paper proposes to set the number of frames for one dimension of convolution kernel, and use one-dimensional model and two-dimensional convolutional network model for speech recognition. By moving the convolution kernel of time axis and frequency band, it can adapt to the time change of speech signal and maintain the correlation between frequency bands to a great extent. At the same time, this paper also discusses the speech signal preprocessing, feature parameter extraction and regularization algorithm. Due to the lack of hospital resources, the lag of information technology, the poor ability of accompanying and other reasons, the current accompanying service for elderly rehabilitation can not meet the needs of elderly patients. The rapid development and wide use of information technology provide opportunities for the optimization of health services for the elderly. In view of the difficulty of word memory and interpretation in current rehabilitation courses, a VR intelligent teaching system based on intelligent voice technology is developed. The application results show that the system can effectively improve the ability of language expression and word writing. At present, the system of intelligent speech function has not been completed, and lacks speech synthesis function. The next research will focus on the use of speech synthesis technology, in order to realize the man-machine dialogue between people and the system, and show a more real training situation.

Biomechanical Analyses of Scoop in Field Hockey

Field hockey is an Olympic sport played all over the world. Hockey is played with a stick where one requires endurance, agility, balance coordination, and high skill to convert the shot. There are various kinds of skills i.e. hitting, dribbling, scooping, tackling etc. Only scoop was selected for the study in different phases (stance phase, execution phase, follow through phase). Field hockey scoop is the aerial passing by lifting the ball from the ground inserting head of hockey stick under the ball. Scoop plays vital role in competitive field hockey games. The aim of the study was to find out the kinematic difference in the elbow joint, knee joint, and ankle joint. The objective of the study was to find out the angular differences of elbow joint, knee joint, and ankle joint in different phases of delivery of field hockey scoop shot. Researchers hypothesised that there are significance differences in elbow joint angle, knee joint angle, and ankle joint angle during delivering of field hockey scoop shot. Six males inter university players aged from 20-24 years were selected for the study and at least they represented at inter university games /national level. Set of the camera is at 1.10 m in height and 3.70 meters. The focal length is 5.6, the resolution is 1080, and the frame rate is 100 per sec. A Sony FRD-AX700 camera was placed 3.7 meters apart on the right side of the hockey player. Angle of elbow joint, angle of knee joint, angle ankle joint, cadence, stride length, and numbers of frames were analysed using Kinovea 0.9.5 software. This research will help the players to execute scoop after knowing elbow joint angle, knee joint angle, and ankle joint angle. Key Words: Field Hockey, Scoop, Elbow, Ankle, Knee.

Differences in 5'untranslated regions highlight the importance of translational regulation of dosage sensitive genes

BackgroundUntranslated regions (UTRs) are important mediators of post-transcriptional regulation. The length of UTRs and the composition of regulatory elements within them are known to vary substantially across genes, but little is known about the reasons for this variation in humans. Here, we set out to determine whether this variation, specifically in 5’UTRs, correlates with gene dosage sensitivity.ResultsWe investigate 5’UTR length, the number of alternative transcription start sites, the potential for alternative splicing, the number and type of upstream open reading frames (uORFs) and the propensity of 5’UTRs to form secondary structures. We explore how these elements vary by gene tolerance to loss-of-function (LoF; using the LOEUF metric), and in genes where changes in dosage are known to cause disease. We show that LOEUF correlates with 5’UTR length and complexity. Genes that are most intolerant to LoF have longer 5’UTRs, greater TSS diversity, and more upstream regulatory elements than their LoF tolerant counterparts. We show that these differences are evident in disease gene-sets, but not in recessive developmental disorder genes where LoF of a single allele is tolerated.ConclusionsOur results confirm the importance of post-transcriptional regulation through 5'UTRs in tight regulation of mRNA and protein levels, particularly for genes where changes in dosage are deleterious and lead to disease. Finally, to support gene-based investigation we release a web-based browser tool, VuTR, that supports exploration of the composition of individual 5'UTRs and the impact of genetic variation within them.

Real Time Driver Drowsiness Detection Using Visual Behavior

One of the main factors contributing to traffic accidents is falling asleep behind the wheel. Although it cannot be totally avoided, this model can help prevent it. A system called drowsiness detection keeps drivers from nodding off while operating a vehicle. Both passengers and other drivers will be safer thanks to this technology. The algorithm can monitor the space between the driver's eyes by employing an infrared camera in front of the vehicle. The technology sounds an alert to alert the driver to take control of the vehicle when the region comes under curtain measurement for a number of consecutive frames. The alarm goes off when the driver opens their eyes again and the area passes above the safe zone. As a result, this may wake up the motorist and save lives. The algorithm's accuracy is 96%.

Optimizing the Design Structure of Recycled Aluminum Pressing Machine using the Finite Element Method

Optimizing the Design Structure of Recycled Aluminum Pressing Machine using the Finite Element Method

Evaluation of the Limitation of Operational Parameters of the IEEE 802.11 ac Network in the 20MHz Channel

IEEE 802.11 wireless network technologies are widely used to create corporate and personal local networks for data exchange and access to Internet resources. The main principle of operation of IEEE 802.11 networks is the principle of competitive access, according to which all wireless network users have the same access rights to the information transmission environment. This method of access leads to the occurrence of collisions in networks with a large number of users, which complicates the process of network functioning and leads to the degradation of quality indicators. The purpose of the study is to estimate the limit values of the operational characteristics of the IEEE 802.11 ac wireless network in the mode with the highest transmission rate (MCS8) in a frequency channel of 20 MHz with one spatial stream, provided that the network has a significant number of active stations with a saturated load. An alternative model of processes in IEEE 802.11 networks based on the concept of a virtual competitive window is used for research. According to the concept of virtual contention window (VCW), the process of data transmission in a network with competitive access is considered as a quasi-stationary process. Numerical data were obtained and graphs of channel bandwidth, transmission delay, and delay non-uniformity were given in the presence of one to sixteen active stations with a saturated load in the network, in the case of transmission of frames with a data volume of 512 or 1500 bytes. The maximum possible bandwidth of the channel with a frequency band of 20 MHz (68.387 bit/s) was determined, in the case of using frames with the maximum load (11454 bytes) provided by the standard. Estimated data on the number of collisions occurring in a network with a saturated load and the number of frames transmitted at various stages of channel access are also provided. The frame transmission delay increases almost proportionally to the number of active stations and varies from 0.605 ms to 5.293 ms, in the case of loading all data frames of 512 bytes, and from 0.785 to 6.41 ms, in the case of a load of 1500 bytes, for changes in the number of active stations in the network from 2 to 16. The unevenness of the delay exceeds the average delay and grows non-linearly, in the case of an increase in the number of active stations from 1 to 6 (CWmin=15), and linearly — with a further increase in the number of stations (over 6). The obtained results are useful for reasonable planning of wireless networks and configuration of network equipment parameters.