Vibrio vulnificus on wound culture slide.Discussion: While history taking is sometimes considered a lost art, it is vital in the care of our patients.What could have been brushed off as necrotizing fasciitis, with thorough a patient history, the differential was broadened, as was antibiotic coverage, to include doxycycline.Discovering that the patient had consumed raw oysters and swam in the gulf coast changed the management of this patient early in the course of his illness.Interestingly, about 90 percent of those infected with V. vulnificus are male and 95 percent have liver disease, diabetes, or are immunocompromised.Often times, our patients can tell us exactly what is wrong with them if we simply listen.

To recognize actions using a neural network model, it is necessary to extract the correct frames from the video for the input of model. Extraction of frames is an important issue that could be poor recognition results or costs computation time. This study proposes a new extraction method that combines optical flow and fuzzy rules. First, optical flow is used to calculate the values of the x and y vectors of the motion in consecutive frames. After expert discussion, rules are formulated to define the optical flow values for each action as fuzzy semantic words and stored as a fuzzy rule base. For the experiment, serving action is further subdivided into tossing, hitting and receiving parts in table tennis video. Using fuzzy rules based on the x and y optical flow values of different actions, the current action type can be determined, and action frames can be extracted more accurately, improving the accuracy of table tennis action recognition, the final result of table tennis action recognition reached up to 69.8% accuracy.

In recent years, many deep learning techniques have been widely applied in sports events. Therefore, the research based on the collection of big data and applied to the analysis of the overall playing tactics of table tennis is competitive. This study proposes a structure to support this idea, which includes the match video collection raw database, video processing, action classification machine learning model, knowledge database and big data analysis website. Under the above structure, this research focuses on using machine learning model to automatically classify the types of serve motions. The table tennis motion dataset is created by professional players. They cut and label the competition video to complete the database. Then, use these data to train a 3-dimension convolutional neural network (3D-CNN). This experiment selected three common types of serve motions to classify. After training the model, with the validation dataset, the accuracy can reach 89.5%. This result shows that machine learning models have sufficient accuracy to recognize motion categories in table tennis serve motions. Therefore, the proposed method will also be extended to all kinds of motion classification to accomplish efficient and accurate table tennis player competition record. Finally, hoping this model structure can be applied to the variety of sports.

Abstract Background: Health-related physical fitness reduces the risk of chronic disease, promotes quality of life and has enormous economic benefits considering the global health care costs resulting from obesity. However, relatively limited information is available regarding the dose–response relationship between health-related physical fitness and obesity risk. This study aimed to determine the associations of health-related physical fitness with body mass index (BMI) distribution and overweight/obesity risk among adults aged 23-64 years in Taiwan.Methods: We conducted a cross-sectional study and reviewed the data derived from the Scientific Physical Fitness Testing Program, Sports Administration, Ministry of Education in Taiwan. Responses from 16,939 participants (7,761 men; 9,178 women) aged 23-64 years from the database were collected in this study. Each participant completed a series of health-related physical fitness measurements, including cardiorespiratory fitness (3-min progressive knee-up and step [3MPKS] test), muscular fitness (hand grip strength), and flexibility (sit-and-reach test). Anthropometric measurements included body height, weight, and BMI. The quartiles of health-related physical fitness results were identified as the dependent variable in the multiple linear and multiple logistic regression analysis to determine the associations of the health-related physical fitness measurements with the BMI distribution and the overweight/obesity risk as well as the dose–response relationship.Results: The 3MPKS test and relative hand grip strength were significantly negatively associated with BMI and overweight/obesity risk with a dose–response relationship in both men and women. However, the sit-and-reach test was partially related to BMI and overweight/obesity risk in adults.Conclusions: Higher levels of the 3MPKS test and relative grip strength were associated with lower BMI and overweight/obesity risk in both sexes. Cardiorespiratory fitness and muscular fitness were effective predictors of BMI distribution and overweight/obesity risk in Taiwanese adults.

We propose a neural fuzzy inference network (NFIN) based on a symbiotic Taguchi-based modified differential evolution (STMDE) algorithm for solving nonlinear control problems. The proposed STMDE algorithm not only uses the Taguchi method in its search for the best individual but also employs adjustable parameter control to tune the scaling factor, which can prevent a solution from being trapped at local optima and reinforce the search ability. Moreover, symbiotic evolution (SE) is applied to improve the structure of individual compositions. Unlike the traditional differential evolution (DE) algorithm, SE regards each individual in a population as being the partial solution to a problem instead of the full solution. Compared with traditional DE, the proposed STMDE algorithm reduces the error by 7.95, 4.51, 5.22, and 51.34% in terms of regulation performance, noise rejection ability, robustness to parameter variation of the controlled system, and controller tracking capability, respectively. In addition, our experimental results also indicate that the proposed STMDE algorithm exhibits superior performance to other algorithms used for solving nonlinear temperature-sensing control problems.

In this study, we aimed to determine the associations among health-related physical fitness measurements, waist circumference (WC), and abdominal obesity risk in Taiwanese adults. We conducted a cross-sectional study based on data from the 2017 Taiwan Scientific Physical Fitness Survey (the TSPFS). We collected the responses from 17,973 participants (7907 men and 10,066 women) aged 23–64 years for this study. The participants completed the study protocol with a standardized structural questionnaire and a series of health-related physical fitness measurements. The fitness measurements included cardiorespiratory fitness (measured by a 3-min progressive knee-up and step test), muscular fitness (measured by a hand grip strength test), and flexibility (measured by a sit-and-reach test). Our anthropometric measurements included height, weight, WC, hip circumference (HC), body mass index (BMI), and waist-to-hip ratio (WHR). We identified the quartiles of the health-related physical fitness results as the dependent variable in the multiple linear and multiple logistic regression analysis to determine the associations of the physical fitness measurements with WC distribution and abdominal obesity risk. We also considered the dose–response relationship. We found that cardiorespiratory fitness, relative grip strength, and flexibility were each significantly negatively associated with WC, but absolute grip strength was significantly positively associated with WC. We also found that higher levels of cardiorespiratory fitness, relative grip strength, and flexibility were each associated with a lower risk of abdominal obesity. Moreover, our secondary finding was of a dose–response relationship between physical fitness performance, WC, and abdominal obesity risk. In short, health-related physical fitness was an effective predictor of waist circumference for both sexes of Taiwanese adults, and higher levels of health-related physical fitness were associated with lower risks of abdominal obesity in Taiwanese adults.

The rapid development of urban intelligence has turned intelligent transport system (ITS) development into a primary goal of traffic management. Automated license plate recognition (ALPR) for moving vehicles is a core aspect of ITS. Most ALPR systems send images back to a server for license plate recognition. To reduce delays and bandwidth use during image transmission, this study proposes an edge-AI-based real-time ALPR (ER-ALPR) system, in which an AGX XAVIER embedded system is embedded on the edge of a camera to achieve real-time image input to an AGX edge device and to enable real-time automatic license plate character recognition. To assess license plate characters and styles in a realistic setting, the proposed ER-ALPR system applies the following approaches: (1) image preprocessing; (2) You Only Look Once v4-Tiny (YOLOv4-Tiny) for license plate frame detection; (3) virtual judgment line for determining whether a license plate frame has passed; (4) the proposed modified YOLOv4 (M-YOLOv4) for license plate character recognition; and (5) a logic auxiliary judgment system for improving license plate recognition accuracy. We tested the proposed ER-ALPR system in selected real-life test environments in Taiwan. In experiments, the proposed ER-ALPR system achieved license plate character recognition rates of 97% and 95% in the day and at night, respectively. Through the AGX system, the proposed ER-ALPR system achieves a high recognition rate at a low computational cost.

This study proposes a knowledge-based neural fuzzy controller (KNFC) for mobile robot navigation control. An effective knowledge-based cultural multi-strategy differential evolution (KCMDE) is used for adjusting the parameters of KNFC. The KNFC is applied in PIONEER 3-DX mobile robots to achieve automatic navigation and obstacle avoidance capabilities. A novel escape approach is proposed to enable robots to autonomously avoid special environments. The angle between the obstacle and robot is used and two thresholds are set to determine whether the robot entries into the special landmarks and to modify the robot behavior for avoiding dead ends. The experimental results show that the proposed KNFC based on the KCMDE algorithm has improved the learning ability and system performance by 15.59% and 79.01%, respectively, compared with the various differential evolution (DE) methods. Finally, the automatic navigation and obstacle avoidance capabilities of robots in unknown environments were verified for achieving the objective of mobile robot control.

The relationships between different functional fitness performance and abdominal obesity among the elderly have not been widely discussed in the literature. The present study aimed to investigate the associations between functional fitness test performance and abdominal obesity in Taiwanese elderly people. A total of 22,399 items of data from the National Physical Fitness Survey Databases in Taiwan (NPFSD 2014-15) were reviewed and analyzed. The quartiles of functional fitness test results were identified as the dependent variable in the multiple linear regression analysis to examine the association between functional fitness and abdominal obesity status. The results showed that body balance (odds ratios (ORs) listed from 1.18 to 2.29, p < 0.05) and flexibility (ORs listed from 1.23 to 2.16, p < 0.05) were critically associated with abdominal obesity. However, measurements related to muscle strength revealed the limited effect sizes for abdominal obesity. From a disability prevention perspective, the development of muscle strength in the elderly should be emphasized and encouraged to maintain their daily capabilities instead of satisfaction with a lean body.

Detection of the facial skin condition enables people to better understand skin problems and helps them select appropriate treatment methods and maintenance products.We collected facial images of different skin problems by using an image optical sensor.To overcome the problem of insufficient training data, the collected dataset was expanded through data augmentation.In the field of computer vision, deep learning is often used for solving image recognition problems with high accuracy.Therefore, we used a convolutional neural network (CNN) to detect facial images of different skin problems.To overcome the difficulty of parameter selection and increase the recognition rate and robustness of the CNN, the parameters of the CNN were optimized using the Taguchi method.Eight control factors in the convolutional layer and the L36 orthogonal array (OA) were used in experiments.Analysis of variance was used for statistical analysis in the design of the experiments to obtain the optimal parameter combination for the developed CNNs.The experimental results indicate that the CNN optimized using the Taguchi method had an accuracy of 86.95%.The accuracy of the optimized CNN was 7.24% higher than that of the original CNN.The experimental results prove that the proposed hyperparameter optimization method can effectively improve the accuracy of network detection.

In this study, we proposed an interval type-2 fuzzy neural network (IT2FNN) based on an improved particle swarm optimization (PSO) method for prediction and control applications. The noise-suppressing ability of the proposed IT2FNN was superior to that of the traditional type-1 fuzzy neural network. We proposed dynamic group cooperative particle swarm optimization (DGCPSO) with superior local search ability to overcome the local optimum problem of traditional PSO. The proposed model and related algorithms were verified through the accuracy of prediction and wall-following control of a mobile robot. Supervised learning was used for prediction, and reinforcement learning was used to achieve wall-following control. The experimental results demonstrated that DGCPSO exhibited superior prediction and wall-following control.

In general, a convolutional neural network (CNN) consists of one or more convolutional layers, pooling layers, and fully connected layers. Most designers adopt a trial-and-error method to select CNN parameters. In this study, an AlexNet network with optimized parameters is proposed for face image recognition. A Taguchi method is used for selecting preliminary factors and experiments are performed through orthogonal table design. The proposed method filters out factors that are significantly affected. Finally, experimental results show that the proposed Taguchi-based AlexNet network obtains 87.056% and 98.72% average accuracy of image gender recognition in the CIA and MORPH databases, respectively. In addition, the average accuracy of the proposed Taguchi-based AlexNet network is 1.576% and 3.47% higher than that of the original AlexNet network in CIA and MORPH databases, respectively.

This study proposed a reinforcement Q-learning-based deep neural network (RQDNN) that combined a deep principal component analysis network (DPCANet) and Q-learning to determine a playing strategy for video games. Video game images were used as the inputs. The proposed DPCANet was used to initialize the parameters of the convolution kernel and capture the image features automatically. It performs as a deep neural network and requires less computational complexity than traditional convolution neural networks. A reinforcement Q-learning method was used to implement a strategy for playing the video game. Both Flappy Bird and Atari Breakout games were implemented to verify the proposed method in this study. Experimental results showed that the scores of our proposed RQDNN were better than those of human players and other methods. In addition, the training time of the proposed RQDNN was also far less than other methods.

In the current age of information explosion, the extraction of relevant data from a large information pool, which includes images, has become crucial. Because of the easy availability of imaging devices, millions of images are being added to the image pool every day. Current image contrast enhancement methods have some drawbacks. First, for images captured in extreme lighting conditions, such as backlit images and extremely bright or dark images, extant image contrast enhancement methods cannot retain the brightness distribution details of the original image, resulting in image distortion. Second, the methods can only achieve global contrast enhancement but not local contrast enhancement. Third, these methods cannot satisfy the Human Visual System mapping curve, resulting in nonsmooth or distorted images. In this study, a novel image expand enhancement system based on fuzzy theory is proposed. This system has two major features: (1) the expand model is designed such that the correlations between light intensity and the intensity of an image captured in this light are considered to achieve local contrast enhancement, and (2) an extreme case of images processing step that is capable of enhancing. The proposed model has a fusion framework; therefore, the image fusion model can represent the relationship between the original image and the expanded image. Next, the fusion model describes some expected statistical properties of the desired intensity of the expand image. Thus, the details of the original image are retained. Experimental results revealed that the proposed algorithm is capable of adaptively enhancing the contrast of the original image while simultaneously extruding the details of objects in the image. The resulting enhanced image can be effectively used for image information analysis and other image-processing tasks.

In past few decades, the development of the biometric identification techniques, such as fingerprint, iris, finger vein, and so on, has become quite mature and related applications have become very popular. The advance of GPU acceleration techniques and the impact of deep neural networks increase not only the accuracy, but also the popularity of face recognition systems. Although face recognition systems alleviate the problem of person identification, their applications would reveal a new challenging task, that is face spoofing and presentation attacks. No matter in a form of photos, videos, or 3D masks, face spoofing attacks can not only restrict the application of a face recognition system, but also increase its vulnerability in regard of security issues. Consequently, in this paper, a deep neural network scheme for face anti-spoofing and liveness detection is proposed to prevent the existing face recognition systems from common face spoofing attacks. The experimental results have demonstrated the robustness of the proposed method against print, cut, and replay attacks.

This paper addresses a sonar behavior-based fuzzy controller (BFC) for mobile robot wall-following control. The wall-following task is usually used to explore an unknown environment. The proposed BFC consists of three sub-fuzzy controllers, including Straight-based Fuzzy Controller, Left-based Fuzzy Controller, and Right-based Fuzzy Controller. The proposed wall-following controller has three characteristics: the mobile robot keeps a distance from the wall, the mobile robot has a high moving velocity, and the mobile robot has a good robustness ability of disturbance. The proposed BFC will be used to control the real mobile robot. The Pioneer 3-DX mobile robot has sonar sensors in front and sides, and it is used in this study. The inputs of BFC are sonar sensors data and the outputs of BFC are robot's left/right wheel speed. Experimental results show that the proposed BFC successfully performs the mobile robot wall-following task in a real unknown environment.

This paper presents an effective navigation control method for mobile robots in an unknown environment. The proposed behavior manager (BM) switches between two behavioral control patterns, wall-following behavior (WFB) and toward-goal behavior (TGB), based on the relationship between the mobile robot and the unknown environment. An interval type-2 fuzzy neural controller with a dynamic-group particle swarm optimization (DGPSO) algorithm is proposed to provide WFB control and obstacle avoidance for mobile robots. In the WFB learning process, the input signal of a controller is the distance between the wall and the sonar sensors, and its output signal is the speed of two wheels of a mobile robot. A fitness function, which operates on the total distance traveled by the mobile robot, distance from the side wall, angle to the side wall, and moving speed, evaluates the WFB performance of the mobile robot. In addition, an escape mechanism is proposed to avoid a dead cycle. Experimental results reveal that the proposed DGPSO is superior to other methods in WFB and navigation control.

For photographs taken in outdoor environments, the air medium causes light attenuation, which reduces image quality; this effect is particularly obvious in hazy environments. To eliminate the hazy effect in images and improve the image quality, the present study proposes an efficient hybrid method. The proposed fuzzy estimator was adopted to estimate variations in light attenuation, and morphological erosion and a neuro-fuzzy filter proposed by this study were employed to refine the transmission map and eliminate the halation. Finally, an estimated mean value for atmospheric light was applied to calculate the color vector of atmospheric light to eliminate the color cast. Experimental results indicate that the proposed hybrid method is superior to other dehazing methods.