Kinmen Island was in a state of combat readiness during the 1950s–1980s. It opened for tourism in 1992, when all troops withdrew from the island. Most military installations, such as bunkers, anti airborne piles, and underground tunnels, became deserted and disordered. The entries to numerous underground bunkers are closed or covered with weeds, creating dangerous spaces on the island. This study evaluates the feasibility of using Electrical Resistivity Tomography (ERT) to detect and discuss the location, size, and depth of underground tunnels. In order to discuss the reliability of the 2D-ERT result, this study built a numerical model to validate the correctness of in situ measured data. In addition, this study employed the artificial intelligence deep learning technique for reprocessing and predicting the ERT image and discussed using an artificial intelligence deep learning algorithm to enhance the image resolution and interpretation. A total of three 2D-ERT survey lines were implemented in this study. The results indicate that the three survey lines clearly show the tunnel location and shape. The numerical simulation results also indicate that using 2D-ERT to survey underground tunnels is highly feasible. Moreover, according to a series of studies in Multilayer Perceptron of deep learning, using deep learning can clearly show the tunnel location and path and effectively enhance the interpretation ability and resolution for 2D-ERT measurement results.

Mobile Edge Computing and Communication (MECC) can be deployed in close proximity with sensing devices and act as middleware between cloud and local networks. The health and fitness movement has become extremely popular recently. Endurance activities, such as marathons, triathlons, and cycling have also grown in popularity. However, with more people participating in these activities, more accidents and injuries occur—ranging from heat stroke, to heart attacks, shock, or hypoxia. All physical training activities include a risk of injury and accidents. Therefore, any research that offers a means of reducing injury risk will significantly contribute to the personal fitness field. Moreover, with the growing popularity of wearable devices and the rise of the MECC, the development and application of wearable devices that can connect to the MECC has become widespread, producing many new innovations. Although many wearable devices, such as wrist straps and smart watches, are available and able to detect individual physiological data, they cannot monitor the human body in a state of motion. Therefore, this study proposes a set of monitoring parameters for a novel wearable device connected to the MECC based on fitness management to assist fitness trainers in effective prompted strength training, and to offer timely warnings in the event of an injury risk. The data collected by the monitoring device using fuzzy theory include risk factor, body temperature, heart rate, and blood oxygen concentration. The proposed system can display in real-time the current physiological state of a wearer/user. The introduction of this device will hopefully enable trainers to immediately and effectively control and monitor the intensity of a training session, while increasing training safety, and offer crucial and immediate diagnostic information so that the correct treatment can be applied without delay in the event of injury.

In this study, a new feature selection algorithm, the neighborhood-relationship feature selection (NRFS) algorithm, is proposed for identifying rat electroencephalogram signals and recognizing Chinese characters. In these two applications, dependent relationships exist among the feature vectors and their neighboring feature vectors. Therefore, the proposed NRFS algorithm was designed for solving this problem. By applying the NRFS algorithm, unselected feature vectors have a high priority of being added into the feature subset if the neighboring feature vectors have been selected. In addition, selected feature vectors have a high priority of being eliminated if the neighboring feature vectors are not selected. In the experiments conducted in this study, the NRFS algorithm was compared with two feature algorithms. The experimental results indicated that the NRFS algorithm can extract the crucial frequency bands for identifying rat vigilance states and identifying crucial character regions for recognizing Chinese characters.

Cardiopulmonary resuscitation (CPR) is an emergency procedure performed on a person experiencing cardiac arrest to manually preserve brain function until spontaneous breathing and blood circulation can be restored. If performed timely and properly, it can improve the survival rate of a person experiencing cardiac arrest. The promotion of CPR has always been an important task for countries around the world. Countries around the world often hold relevant study camps and seminars to improve the public’s awareness of CPR. On the basis of this rationale, this paper proposes an interactive teaching aid kit for CPR that uses a CPR manikin and tutoring software to facilitate CPR learning among trainees. The CPR manikin is equipped with sensors that determine whether the CPR steps are performed correctly. Data from the sensors are sent to the tutoring software through wireless transmission. The software provides video demonstrations and textual instructions concerning the standard CPR procedure. In this software, the interactive interface displays real-time information about the trainee’s CPR process, such as information on the CPR step being performed and the number of chest compression and breaths given. Thus, this teaching aid kit allows trainees to learn CPR without an instructor. This system may enable CPR to become a readily learnable skill for the general population.