• International Journal of Railway
• /
• v.1 no.4
• /
• pp.149-156
• /
• 2008

During maintenance or construction works in or at the tracks of railways, high risks for passengers and railway staff, especially for the workers on the construction site exist. The high risks result out of the movement of rail vehicles, like trains or construction vehicles, which must be faced by using any available technical and operational technologies for securing them against the environment. Therefore, it is necessary to evaluate the level of protection continuously and to identify new and innovative methods and technologies for the protection of the gang (construction worker, machines and material). Especially on construction sites at line sections with two or more parallel tracks but also with single tracks, there are still a lot of incidents and accidents mostly with seriously injured persons or fatalities. These were mainly gang members that breach the railway-loading gage. By using proper warning or protection systems, the avoidance of such accidents must be achieved. The latest developments. in gang protection systems concern on the one hand fixed barriers in the middle between the construction site and the operated track and on the other hand construction vehicles equipped with automatic warning systems. The disadvantage of such protection methods is that the gang can be warned against an approaching train but a monitoring of the gang members cannot be performed. Only one part of a potential dangerous situation will be detected. If the gang members will overhear the acoustic warning signal of the security staff and the workers will not leave the danger zone in the track, the driver of the approaching train had no chance to react to the dangerous situation. An accident is often inevitable. While the detection of acoustic warning signals by the gang members working on a construction site is very difficult, the acoustical planning of an automatic warning system has to be designed for an acoustic short range level of one meter besides the construction vehicle. The decision about the use of today's technical warning system (fixed systems, automatic warning systems, etc.) must be geared to the technical feasibility and the level of safety which is needed. Criteria for decision guidance to block a track should be developed by danger estimation and economical variables. To realize the actual jurisdiction and to minimize the hazards of railway operations by the use of construction vehicles near the tracks further developments are needed. This means, that the warning systems have to be enhanced to systems for protection, which monitor the realization of the warning signal as a precondition for giving a movement authority to a train. This method can protect against accidents caused by predictable wrongdoing. The actual state of the art technique of using a collective warning combined with additional security staff is no longer acceptable. Therefore, the Institute of Transportation System of the German Aerospace Center in Braunschweig (Germany) will develop a gang warning and protection system based upon imaging methods, with optical sensors such as video in visible and invisible ranges, radar, laser, and other. The advantage of such a system based on the possibility to monitor both the gang itself and the railway-loading gauge either of the parallel track or of the same track still in use. By monitoring both situations, the system will be able to generate a warning message for the approaching train, that there are obstacles in the track, so that the train can be stopped to prevent an accident. And also the gang workers will be warned, while they breach their area.

• Imaging Science in Dentistry
• /
• v.50 no.2
• /
• pp.169-174
• /
• 2020

Purpose: Periodontal disease causes tooth loss and is associated with cardiovascular diseases, diabetes, and rheumatoid arthritis. The present study proposes using a deep learning-based object detection method to identify periodontally compromised teeth on digital panoramic radiographs. A faster regional convolutional neural network (faster R-CNN) which is a state-of-the-art deep detection network, was adapted from the natural image domain using a small annotated clinical data- set. Materials and Methods: In total, 100 digital panoramic radiographs of periodontally compromised patients were retrospectively collected from our hospital's information system and augmented. The periodontally compromised teeth found in each image were annotated by experts in periodontology to obtain the ground truth. The Keras library, which is written in Python, was used to train and test the model on a single NVidia 1080Ti GPU. The faster R-CNN model used a pretrained ResNet architecture. Results: The average precision rate of 0.81 demonstrated that there was a significant region of overlap between the predicted regions and the ground truth. The average recall rate of 0.80 showed that the periodontally compromised teeth regions generated by the detection method excluded healthiest teeth areas. In addition, the model achieved a sensitivity of 0.84, a specificity of 0.88 and an F-measure of 0.81. Conclusion: The faster R-CNN trained on a limited amount of labeled imaging data performed satisfactorily in detecting periodontally compromised teeth. The application of a faster R-CNN to assist in the detection of periodontally compromised teeth may reduce diagnostic effort by saving assessment time and allowing automated screening documentation.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.1
• /
• pp.219-223
• /
• 2020

To guarantee AI model's prominent recognition rate and recognition precision, obtaining the large number of data is essential. In this paper, we propose transfer learning-based object detection algorithm for maintaining outstanding performance even when the volume of training data is small. Also, we proposed a tranfer learning network combining Resnet-50 and YOLO(You Only Look Once) network. The transfer learning network uses the Leeds Sports Pose dataset to train the network that detects the person who occupies the largest part of each images. Simulation results yield to detection rate as 84% and detection precision as 97%.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.251-266
• /
• 2022

Structural Health Monitoring (SHM) of critical infrastructure comprises a major pillar of maintenance management, shielding public safety and economic sustainability. Although SHM is usually associated with data-driven metrics and thresholds, expert judgement is essential, especially in cases where erroneous predictions can bear casualties or substantial economic loss. Considering that visual inspections are time consuming and potentially subjective, artificial-intelligence tools may be leveraged in order to minimize the inspection effort and provide objective outcomes. In this context, timely detection of sensor malfunctioning is crucial in preventing inaccurate assessment and false alarms. The present work introduces a sensor-fault detection and interpretation framework, based on the well-established support-vector machine scheme for anomaly detection, combined with a coalitional game-theory approach. The proposed framework is implemented in two datasets, provided along the 1st International Project Competition for Structural Health Monitoring (IPC-SHM 2020), comprising acceleration and cable-load measurements from two real cable-stayed bridges. The results demonstrate good predictive performance and highlight the potential for seamless adaption of the algorithm to intrinsically different data domains. For the first time, the term "decision trajectories", originating from the field of cognitive sciences, is introduced and applied in the context of SHM. This provides an intuitive and comprehensive illustration of the impact of individual features, along with an elaboration on feature dependencies that drive individual model predictions. Overall, the proposed framework provides an easy-to-train, application-agnostic and interpretable anomaly detector, which can be integrated into the preprocessing part of various SHM and condition-monitoring applications, offering a first screening of the sensor health prior to further analysis.

• Journal of Korean Society of Transportation
• /
• v.23 no.4 s.82
• /
• pp.17-28
• /
• 2005

About 91.1% of Railway-Highway Crossings (RHC) in Korea use a Constant Distance Warning System(CDWS), while about 8.9% use a Constant Warning Time System(CWTS). The CDWS does not recognize speed differences of approaching trains and provides only waiting times to vehicles and pedestrians based on the highest speed of approaching trains. Under the CDWS, therefore, low speed trains provide unnecessary waiting times at crossings which often generates complains to vehicle drivers and pedestrians and may cause wrong decisions to pass the crossings. The objective of this research is to improve the safety of the RHC by developing accurate a CWTS. In this research a train speed and location detection system was developed with ultra sonic detectors. Locations of the detectors was decided based on the highest speed and the minimum warning time of Saemaul of 160 km/h. To validate the algorithms of the newly developed systems the lab tests were conducted. The results show that the train detection system provides accurate locations of trains and the maximum error between real speeds of trains and those of the system was 0.07m/s.

• Smart Media Journal
• /
• v.6 no.4
• /
• pp.9-16
• /
• 2017

The railway point machine is an especially important component that changes the traveling direction of a train. Failure of the point machine may cause a serious railway accident. Therefore, early detection of failures is important for the management of railway condition monitoring systems. In this paper, we propose a noise-robust anomaly detection method in railway condition monitoring systems using sound data. First, we extract feature vectors from the spectrogram image of sound signals and convert it into modulation feature to ensure robust performance, and lastly, use the support vector machine (SVM) as an early anomaly detector of railway point machines. By the experimental results, we confirmed that the proposed method could detect the anomaly conditions of railway point machines with acceptable accuracy even under noisy conditions.

• Journal of Korean Society of Forest Science
• /
• v.109 no.1
• /
• pp.23-30
• /
• 2020

The use of increased computing power, machine learning, and deep learning techniques have dramatically increased in various sectors. In particular, image detection algorithms are broadly used in forestry and remote sensing areas to identify forest types and tree species. However, in South Korea, machine learning has rarely, if ever, been applied in forestry image detection, especially to classify tree species. This study integrates the application of machine learning and forest image detection; specifically, we compared the ability of two machine learning data collection methods, namely image data captured by forest experts (D1) and web-crawling (D2), to automate the classification of five trees species. In addition, two methods of characterization to train/test the system were investigated. The results indicated a significant difference in classification accuracy between D1 and D2: the classification accuracy of D1 was higher than that of D2. In order to increase the classification accuracy of D2, additional data filtering techniques were required to reduce the noise of uncensored image data.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.4
• /
• pp.259-266
• /
• 2016

Recently, CCTV cameras are emplaced actively to reinforce security and intelligent surveillance systems have been under development for detecting and monitoring of the objects in the video. In this study, we propose a method for detection of upper body in intelligent surveillance system using FCM-based RBFNN classifier realized with the aid of HOG features. Firstly, HOG features that have been originally proposed to detect the pedestrian are adopted to train the unique gradient features about upper body. However, HOG features typically exhibit a very high dimension of which is proportional to the size of the input image, it is necessary to reduce the dimension of inputs of the RBFNN classifier. Thus the well-known PCA algorithm is applied prior to the RBFNN classification step. In the computer simulation experiments, the RBFNN classifier was trained using pre-classified upper body images and non-person images and then the performance of the proposed classifier for upper body detection is evaluated by using test images and video sequences.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.3
• /
• pp.401-406
• /
• 2021

Recently, mean-teacher models based on convolutional recurrent neural networks are popularly used in audio event detection. The mean-teacher model is an architecture that consists of two parallel CRNNs and it is possible to train them effectively on the weakly-labelled and unlabeled audio data by using the consistency learning metric at the output of the two neural networks. In this study, we tried to improve the performance of the mean-teacher model by using additional derivative features of the log-mel spectrum. In the audio event detection experiments using the training and test data from the Task 4 of the DCASE 2018/2019 Challenges, we could obtain maximally a 8.1% relative decrease in the ER(Error Rate) in the mean-teacher model using proposed derivative features.

• Journal of Biomedical Engineering Research
• /
• v.44 no.3
• /
• pp.211-217
• /
• 2023

Recently, many studies have introduced artificial intelligence systems in the surgical process to reduce the incidence and mortality of complications in patients. Bleeding is a major cause of operative mortality and complications. However, there have been few studies conducted on detecting bleeding in surgical videos. To advance the development of deep learning models for detecting intraoperative hemorrhage, three models have been trained and compared; such as, YOLOv5, RetinaNet50, and RetinaNet101. We collected 1,016 bleeding images extracted from five surgical videos. The ground truths were labeled based on agreement from two specialists. To train and evaluate models, we divided the datasets into training data, validation data, and test data. For training, 812 images (80%) were selected from the dataset. Another 102 images (10%) were used for evaluation and the remaining 102 images (10%) were used as the evaluation data. The three main metrics used to evaluate performance are precision, recall, and false positive per image (FPPI). Based on the evaluation metrics, RetinaNet101 achieved the best detection results out of the three models (Precision rate of 0.99±0.01, Recall rate of 0.93±0.02, and FPPI of 0.01±0.01). The information on the bleeding detected in surgical videos can be quickly transmitted to the operating room, improving patient outcomes.