Integration of improved YOLOv5 for face mask detector and auto-labeling to generate dataset for fighting against COVID-19.

One of the most effective deterrent methods is using face masks to prevent the spread of the virus during the COVID-19 pandemic. Deep learning face mask detection networks have been implemented into COVID-19 monitoring systems to provide effective supervision for public areas. However, previous works have limitations: the challenge of real-time performance (i.e., fast inference and low accuracy) and training datasets. The current study aims to propose a comprehensive solution by creating a new face mask dataset and improving the YOLOv5 baseline to balance accuracy and detection time. Particularly, we improve YOLOv5 by adding coordinate attention (CA) module into the baseline backbone following two different schemes, namely YOLOv5s-CA and YOLOV5s-C3CA. In detail, we train three models with a Kaggle dataset of 853 images consisting of three categories: without a mask "NM," with mask "M," and incorrectly worn mask "IWM" classes. The experimental results show that our modified YOLOv5 with CA module achieves the highest accuracy mAP@0.5 of 93.9% compared with 87% of baseline and detection time per image of 8.0 ms (125 FPS). In addition, we build an integrated system of improved YOLOv5-CA and auto-labeling module to create a new face mask dataset of 7110 images with more than 3500 labels for three categories from YouTube videos. Our proposed YOLOv5-CA and the state-of-the-art detection models (i.e., YOLOX, YOLOv6, and YOLOv7) are trained on our 7110 images dataset. In our dataset, the YOLOv5-CA performance enhances with mAP@0.5 of 96.8%. The results indicate the enhancement of the improved YOLOv5-CA model compared with several state-of-the-art works.

Visual Algorithm of VR E-Sports for Online Health Care.

The need for non-face-to-face online health care has emerged through the era of "untact". However, there is a lack of standardization work and research cases on the exercise effect of immersive content. In this study, the possibility of the exercise effect of VR e-sports among e-sports cases were presented through a visual algorithm analysis. In addition, the evaluation criteria were established. The research method compares and analyzes e-sports cases and VR e-sports cases by applying existing evaluation research cases. It also sets up a new evaluation standard. As for the analysis result, the device immersion method and interaction range were set through an algorithm analysis; FOV and frame immersion were set through typification; the user recognition method and interaction method were set through the visual diagram. Then, each derived result value was quantified and a new evaluation criterion was proposed.

A Novel Model on Reinforce K-Means Using Location Division Model and Outlier of Initial Value for Lowering Data Cost.

Today, semi-structured and unstructured data are mainly collected and analyzed for data analysis applicable to various systems. Such data have a dense distribution of space and usually contain outliers and noise data. There have been ongoing research studies on clustering algorithms to classify such data (outliers and noise data). The K-means algorithm is one of the most investigated clustering algorithms. Researchers have pointed out a couple of problems such as processing clustering for the number of clusters, K, by an analyst through his or her random choices, producing biased results in data classification through the connection of nodes in dense data, and higher implementation costs and lower accuracy according to the selection models of the initial centroids. Most K-means researchers have pointed out the disadvantage of outliers belonging to external or other clusters instead of the concerned ones when K is big or small. Thus, the present study analyzed problems with the selection of initial centroids in the existing K-means algorithm and investigated a new K-means algorithm of selecting initial centroids. The present study proposed a method of cutting down clustering calculation costs by applying an initial center point approach based on space division and outliers so that no objects would be subordinate to the initial cluster center for dependence lower from the initial cluster center. Since data containing outliers could lead to inappropriate results when they are reflected in the choice of a center point of a cluster, the study proposed an algorithm to minimize the error rates of outliers based on an improved algorithm for space division and distance measurement. The performance experiment results of the proposed algorithm show that it lowered the execution costs by about 13-14% compared with those of previous studies when there was an increase in the volume of clustering data or the number of clusters. It also recorded a lower frequency of outliers, a lower effectiveness index, which assesses performance deterioration with outliers, and a reduction of outliers by about 60%.

Consistency of Medical Data Using Intelligent Neuron Faster R-CNN Algorithm for Smart Health Care Application.

The purpose of this study is to increase interest in health as human life is extended in modern society. Hence, many people in hospitals produce much medical data (EMR, PACS, OCS, EHR, MRI, X-ray) after treatment. Medical data are stored as structured and unstructured data. However, many medical data are causing errors, omissions and mistakes in the process of reading. This behavior is very important in dealing with human life and sometimes leads to medical accidents due to physician errors. Therefore, this research is conducted through the CNN intelligent agent cloud architecture to verify errors in reading existing medical image data. To reduce the error rule when reading medical image data, a faster R-CNN intelligent agent cloud architecture is proposed. It shows the result of increasing errors of existing error reading by more than 1.4 times (140%). In particular, it is an algorithm that analyses data stored by actual existing medical data through Conv feature map using deep ConvNet and ROI Projection. The data were verified using about 120,000 databases. It uses data to examine human lungs. In addition, the experimental environment established an environment that can handle GPU's high performance and NVIDIA SLI multi-OS and multiple Quadro GPUs were used. In this experiment, the verification data composition was verified and randomly extracted from about 120,000 medical records and the similarity compared to the original data were measured by comparing about 40% of the extracted images. Finally, we want to reduce and verify the error rate of medical data reading.

Face Recognition at a Distance for a Stand-Alone Access Control System.

Although access control based on human face recognition has become popular in consumer applications, it still has several implementation issues before it can realize a stand-alone access control system. Owing to a lack of computational resources, lightweight and computationally efficient face recognition algorithms are required. The conventional access control systems require significant active cooperation from the users despite its non-aggressive nature. The lighting/illumination change is one of the most difficult and challenging problems for human-face-recognition-based access control applications. This paper presents the design and implementation of a user-friendly, stand-alone access control system based on human face recognition at a distance. The local binary pattern (LBP)-AdaBoost framework was employed for face and eyes detection, which is fast and invariant to illumination changes. It can detect faces and eyes of varied sizes at a distance. For fast face recognition with a high accuracy, the Gabor-LBP histogram framework was modified by substituting the Gabor wavelet with Gaussian derivative filters, which reduced the facial feature size by 40% of the Gabor-LBP-based facial features, and was robust to significant illumination changes and complicated backgrounds. The experiments on benchmark datasets produced face recognition accuracies of 97.27% on an E-face dataset and 99.06% on an XM2VTS dataset, respectively. The system achieved a 91.5% true acceptance rate with a 0.28% false acceptance rate and averaged a 5.26 frames/sec processing speed on a newly collected face image and video dataset in an indoor office environment.

Fully Differential Touch Screen Controller with Wide Input Dynamic Range for Thin Displays.

As today's smartphone displays become thinner, the coupling capacitance between the display electrodes and touch screen panel (TSP) electrodes is increasing significantly. The increased capacitance easily introduces time-varying display signals into the TSP, deteriorating the touch performance. In this research, we demonstrate that the maximum peak display noise in the time domain is approximately 30% of the maximum voltage difference of the display grayscale through analysis of the structure and operation of displays. Then, to mitigate display noise, we propose a circuit solution that uses a fully differential charge amplifier with an input dynamic range wider than the maximum peak of the display noise. A test chip was fabricated using a 0.35 µm CMOS process and achieved a signal-to-noise ratio of 41 dB for a 6-mm-diameter metal pillar touch when display pulses with 5-V swing were driven at 100 kHz.

PLC-Integrated Sensing Technology in Mountain Regions for Drone Landing Sites: Focusing on Software Technology.

In the Republic of Korea, one of the most widely discussed subjects related to future logistics technology is the drone-based delivery (transportation) system. Much (around 75%) of Korea's territory consists of mountainous areas; however, the costs of installing internet facilities for drone landing sites are very high compared to other countries. Therefore, this paper proposes the power-line communication (PLC) system introduced in the author's previous study as an alternative solution. For the system design, a number of lightning rods are used together with a monitoring system. The system algorithm performs substantial data analysis. Also, as the author found that instantaneous high-voltage currents were a major cause of fire incidents, a three-phase three-wire connection was used for the installation of the lightning rods (Bipolar Conventional Air Terminal). Thus, based on the PLC technology, an artificial intelligence (AI) which avoids lightning strikes at the drone landing site by interworking with a closed-circuit television (CCTV) monitoring system when a drone flies over the mountain regions is proposed in this paper. The algorithm was implemented with C++ and Unity/C#, whereas the application for the part concerning the integrated sensing was developed with Java Android.

An Indoor Location-Based Control System Using Bluetooth Beacons for IoT Systems.

The indoor location-based control system estimates the indoor position of a user to provide the service he/she requires. The major elements involved in the system are the localization server, service-provision client, user application positioning technology. The localization server controls access of terminal devices (e.g., Smart Phones and other wireless devices) to determine their locations within a specified space first and then the service-provision client initiates required services such as indoor navigation and monitoring/surveillance. The user application provides necessary data to let the server to localize the devices or allow the user to receive various services from the client. The major technological elements involved in this system are indoor space partition method, Bluetooth 4.0, RSSI (Received Signal Strength Indication) and trilateration. The system also employs the BLE communication technology when determining the position of the user in an indoor space. The position information obtained is then used to control a specific device(s). These technologies are fundamental in achieving a "Smart Living". An indoor location-based control system that provides services by estimating user's indoor locations has been implemented in this study (First scenario). The algorithm introduced in this study (Second scenario) is effective in extracting valid samples from the RSSI dataset but has it has some drawbacks as well. Although we used a range-average algorithm that measures the shortest distance, there are some limitations because the measurement results depend on the sample size and the sample efficiency depends on sampling speeds and environmental changes. However, the Bluetooth system can be implemented at a relatively low cost so that once the problem of precision is solved, it can be applied to various fields.