• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.5
• /
• pp.267-276
• /
• 2016

Human detection technologies are widely used in smart homes and autonomous vehicles. However, in order to detect human, autonomous vehicle researchers have used a high-resolution LIDAR and smart home researchers have applied a camera with a narrow detection range. In this paper, we propose a novel method using a low-cost and low-resolution LIDAR that can detect human fast and precisely without complex learning algorithm and additional devices. In other words, human can be distinguished from objects by using a new human characteristics function which is empirically extracted from the characteristics of a human. In addition, we verified the effectiveness of the proposed algorithm through a number of experiments.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.5
• /
• pp.358-365
• /
• 2016

We propose a novel application of random forest, a machine learning-based general classification algorithm, to analyze the influence of design attributes on the silicon-to-SPICE (S2S) gap. To improve modeling accuracy, we introduce magnification of learning data as well as randomization for the counting of design attributes to be used for each tree in the forest. From the automatically generated decision trees, we can extract the so-called importance and impact indices, which identify the most significant design attributes determining the S2S gap. We apply the proposed method to actual silicon data, and observe that the identified design attributes show a clear trend in the S2S gap. We finally unveil 10nm key fin-shaped field effect transistor (FinFET) structures that result in a large S2S gap using the measurement data from 10nm test vehicles specialized for model-hardware correlation.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.3
• /
• pp.251-257
• /
• 2012

Unmanned ground vehicles have important military, reconnaissance, and materials handling application. Many of these applications require the UGVs to move at high speeds through uneven, natural terrain with various compositions and physical parameters. This paper presents a framework for high speed autonomous navigation based on the integrated real time traversability. Specifically, the proposed system performs real-time dynamic simulation and calculate maximum traversing velocity guaranteeing safe motion over rough terrain. The architecture of autonomous navigation is firstly presented for high-speed autonomous navigation. Then, the integrated real time traversability, which is composed of initial velocity profiling step, dynamic analysis step, road classification step and stable velocity profiling step, is introduced. Experimental results are presented that demonstrate the method for a $6{\times}6$ autonomous vehicle moving on flat terrain with bump.

• 한국방재학회:학술대회논문집
• /
• 2008.02a
• /
• pp.629-632
• /
• 2008

Risk-based security impact evaluation may be affected by various factors according to numerous combinations of explosive devices, cutting devices, impact vehicles, and specific attack location to consider. Presently, in planning and design phases, designers are still often uncertain of their responsibility, lack of information and training of security. Therefore, designers are still failing to exploit the potential to reduce threats on site. In this study, the concept of security impact assessment is introduced in order to derive the performing design for safety in design phase. For this purpose, a framework for security impact assessment model using risk-based approach for bridge structures is suggested. The suggested model includes of information survey, classification of terror threats, and quantitative estimation of severity and occurrence.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.12
• /
• pp.3197-3218
• /
• 2012

Compared with traditional itinerary planning, intention-oriented itinerary recommendations can provide more flexible activity planning without requiring the user's predetermined destinations and is especially helpful for those in unfamiliar environments. The rank and classification of points of interest (POI) from location-based social networks (LBSN) are used to indicate different user intentions. The mining of vehicles' physical trajectories can provide exact civil traffic information for path planning. This paper proposes a POI category-based itinerary recommendation framework combining physical trajectories with LBSN. Specifically, a Voronoi graph-based GPS trajectory analysis method is utilized to build traffic information networks, and an ant colony algorithm for multi-object optimization is implemented to locate the most appropriate itineraries. We conduct experiments on datasets from the Foursquare and GeoLife projects. A test of users' satisfaction with the recommended items is also performed. Our results show that the satisfaction level reaches an average of 80%.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.105-110
• /
• 2022

Traffic sign recognition plays an important role in solving traffic-related problems. Traffic sign recognition and classification systems are key components for traffic safety, traffic monitoring, autonomous driving services, and autonomous vehicles. A lightweight model, applicable to portable devices, is an essential aspect of the design agenda. We suggest a lightweight convolutional neural network model with residual blocks for traffic sign recognition systems. The proposed model shows very competitive results on publicly available benchmark data.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.335-337
• /
• 2024

This paper presents a new open-world object detection method emphasizing uncertainty representation in machine learning models. The focus is on adapting to real-world uncertainties, incrementally updating the model's knowledge repository for dynamic scenarios. Applications like autonomous vehicles benefit from improved multi-class classification accuracy. The paper reviews challenges in existing methodologies, stressing the need for universal detectors capable of handling unknown classes. Future directions propose collaboration, integration of language models, to improve the adaptability and applicability of open-world object detection.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.6
• /
• pp.96-106
• /
• 2020

To solve the limitation of traffic monitoring that occur from embedded sensor such as loop and piezo sensors, the thermal imaging camera was installed on the roadside. As the length of Class 1(passenger car) is getting longer, it is becoming difficult to classify from Class 3(2-axle truck) by using an embedded sensor. The collected images were labeled to generate training data. A total of 17,536 vehicle images (640x480 pixels) training data were produced. CNN (Convolutional Neural Network) was used to achieve vehicle classification based on thermal image. Based on the limited data volume and quality, a classification accuracy of 97.7% was achieved. It shows the possibility of traffic monitoring system based on AI. If more learning data is collected in the future, 12-class classification will be possible. Also, AI-based traffic monitoring will be able to classify not only 12-class, but also new various class such as eco-friendly vehicles, vehicle in violation, motorcycles, etc. Which can be used as statistical data for national policy, research, and industry.

• Journal of Korean Society of Transportation
• /
• v.28 no.6
• /
• pp.43-54
• /
• 2010

In recent years there have been studies on tour based approaches for freight travel demand modelling. The purpose of this paper is to analyze tour type choice behavior of commercial vehicles which are divided into round trips and chained tours. The methods of the study are based on the decision tree and the logit model. The results indicates that the explanation variables for classifying tour types of commercial vehicles are loading factor, average goods quantity, and total goods quantity. The results of the decision tree method are similar to those of logit model. In addition, the explanation variables for tour type classification of small trucks are not different from those for medium trucks', implying that the most important factor on the vehicle tour planning is how to load goods such as shipment size and total quantity.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.14 no.4
• /
• pp.52-61
• /
• 2015

PCE(Passenger Car Equivalents) is used to analysis of road capacity and LOS(Level of Service). In this study calculates PCE by number of lane and 12 vehicle type by MOLIT(Minister of Land, Infra Structure and Transport) using individual vehicle data. The results of the calculation, PCEs are increased when high vehicle classification level, many number of lanes and weekend. Heavy vehicle factors are smaller than KHCM on 4, 6 lane. Also, In this study estimates of PCE variation model by heavy vehicle percentage. Impact of Heavy vehicles on PCEs is the most sensitive on 2 lane. The results of the study, heavy vehicles low impact on PCE on multi-lane and business trips are a little in weekend.