Damage to the units related to driving and running of the railway vehicle may cause an inevitable accident due to defects and malfunctions in operation. In order to prevent such an accident, a non-destructive diagnostic technology that detects the damage is required. Previous researchers have researched and developed a monitoring system of the infrared thermography method to diagnose the condition of the railway vehicle driving and driving units. A system for monitoring running of the railway vehicle and temperature condition of the drive unit at a vehicle speed of 30 to 100 km/h was constructed, and a study on its applicability was conducted. In this study, a system for diagnosing an abnormal condition of the driving and running units while the vehicle is running with an infrared thermography diagnostic system was installed in the depot and operation route, and evaluation of the abnormal condition of the driving and running units was performed. The results show that the diagnosis system using infrared thermography can be used to identify abnormal conditions in the driving and running units of a railway vehicle. The diagnosis system can effectively inspect the normal and abnormal conditions in operation of a railway vehicle.

Deaf people use their own national sign or finger languages for communication. They have a lot of inconvenience in both social and financial problems. In this study, a finger language recognition system using an ensemble machine learning algorithm with an armband sensor of 8 channel surface electromyography (sEMG) is introduced. The algorithm consisted of signal acquisition, digital filtering, feature vector extraction, and an ensemble classifier based on artificial neural network (EANN). It was evaluated with Korean finger language (14 consonants, 17 vowels and 7 numbers) in 20 normal subjects. EANN was categorized with the number of classifiers (1 to 10) and the size of training data (50 to 1500). Mean accuracies and standard deviations for each structure were then obtained. Results showed that, as the number of classifiers (1 to 8) and the size of training data (50 to 300) were increased, the average accuracy of the E-ANN classifier was increased while the standard deviation was decreased. Statistical analysis showed that the optimal E-ANN structure was composed with 8 classifiers and 300 training data. This study suggested that E-ANN was more accurate than the general ANN for sign/finger language recognition.