This paper presents history and evolution of object detection technologies in recent years. Since the introduction of face detection technology by P. Viola and M. Jones in the early 2000s, various object detection methods have been proposed. In particular, deep learning technology has been attracted much attention at IMAGENET Large Scale Visual Recognition Challenge 2012, many excellent object detection methods using deep learning have been proposed. Therefore, this paper focuses on object detection technologies and explains how they have evolved from the past to the present.

　In order to decrease fatal traffic accidents, early detection of sudden changes in driver’s physical condition is desired. In this paper, we reported an example of modeling process of "driver’s normal behavior model," which is a part of driver state sensing technology we are developing. By combining machine learning and domain knowledge, we have achieved the model for normal steering operation that had both high prediction accuracy and high interpretability/explainability under real-world conditions.

　In recent years, the development of AI technology has led to rapid improvements in various fields, such as image recognition, language processing, and time series analysis. In the automotive field, driver assistance systems using cameras and sensors have already been put to practical use, and research on automatic driving is also active. On the other hand, some operators have just started to conduct tests of forward monitoring using cameras and sensors in railway. In this paper, we introduce our proposed research on AI application and anomaly detection using cameras and sensors in trains to improve train safety.

　Appropriate maintenance of tracks is vital for the safe operation of railways. Proper managing track facilities is necessary to prevent buckling of rails. Due to social backgrounds of a shortage of workers, a decrease in skilled engineers, and a decrease in passenger income, inspection methods with a low-cost and no need of experience are desired. Therefore, we have developed a method that estimates each image's kilometers, rail gaps, wooden sleeper deterioration, and ballast shape using only inexpensive camcorders. This paper describes the outline of the method and its application results.

　This paper describes a position verification method for the aircraft position reporting system called Automatic Dependent Surveillance-Broadcast (ADS-B). The verification method exploits a wireless signal feature, in particular, Time Difference of Arrival (TDOA). In this paper, the principle of the method is firstly described in a generalized form with several possible features. A formulation specific for TDOA is then given. Finally, an experimental result is provided. This ADS-B example is expected to be a useful reference for other position reporting systems.

　This paper presents a diagnostic method for rolling bearings using deep learning instead of conventional rule-based diagnostic methods which requires human and time costs. However, deep learning has two major problems. One is difficulty in acquiring large amount of data under the operation with damaged rolling bearings for training, and the other is difficulty in interpreting the diagnostic results. As a solution to these problems, this paper introduces transfer learning and a method to visualize the input data points contributing to the diagnostic results.

　The subject of this paper is to realize high-speed rotation by stabilizing the rotation of an non-controlled magnetic levitation motor using a diamagnetic disc. The non-controlled magnetic levitation motor has a small rigidity of the magnetic bearing, and it is difficult to rotate at a stable high speed. As a countermeasure, the permanent magnets attached to the upper and lower parts of the levitated rotor are surrounded by copper blocks, and the eddy current generated inside the copper blocks stabilizes the levitated rotor. As a result, the levitation rotor can rotate at high speed. However, as the rotational speed of the levitation rotor increases, the aerodynamic attractive force between the permanent magnet array for floating the diamagnetic disc and the diamagnetic disc increases. Above 4800 rpm, it was found that the permanent magnet array and the diamagnetic disc were in contact due to the attractive force.