• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.115-125
• /
• 2021

Due to various ICT Technology innovations and Digital Transformation, the Internet of Things(IoT) environment is increasingly requiring intelligence, decentralization, and automated service, especially an advanced and stable smart service environment in the Industrial Internet of Things(IIoT) where communication network(5G), data analysis and artificial intelligence(AI), and digital twin technology are combined. In this study, we propose IIoT Edge middleware systems for flexible interface with heterogeneous devices such as facilities and sensors at various industrial sites and for quick and stable data collection and processing.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.4
• /
• pp.121-125
• /
• 2022

This paper deals with the development of a deep-learning-based robot that recognizes various types of stairs and performs a mission to go up to the target floor. The overall motion sequence of the robot is performed based on the ROS robot operating system, and it is possible to detect the shape of the stairs required to implement the motion sequence through rapid object recognition through YOLOv4 and Cuda acceleration calculations. Using the ROS operating system installed in Jetson Nano, a system was built to support communication between Arduino DUE and OpenCM 9.04 with heterogeneous hardware and to control the movement of the robot by aligning the received sensors and data. In addition, the web server for robot control was manufactured as ROS web server, and flow chart and basic ROS communication were designed to enable control through computer and smartphone through message passing.

• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.346-351
• /
• 2023

With the release of numerous open driving datasets, the demand for domain adaptation in perception tasks has increased, particularly when transferring knowledge from rich datasets to novel domains. However, it is difficult to solve the change 1) in the sensor domain caused by heterogeneous LiDAR sensors and 2) in the environmental domain caused by different environmental factors. We overcome domain differences in the semi-supervised setting with 3-stage model parameter training. First, we pre-train the model with the source dataset with object scaling based on statistics of the object size. Then we fine-tine the partially frozen model weights with copy-and-paste augmentation. The 3D points in the box labels are copied from one scene and pasted to the other scenes. Finally, we use the knowledge distillation method to update the student network with a moving average from the teacher network along with a self-training method with pseudo labels. Test-Time Augmentation with varying z values is employed to predict the final results. Our method achieved 3rd place in ECCV 2022 workshop on the 3D Perception for Autonomous Driving challenge.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.333-335
• /
• 2022

원격 하드웨어 관리 기술은 BMC 관리 기술을 사용하여 자사의 하드웨어를 원격으로 제어하고 모니터링 할 수 있는 여러 기능들을 제공하며, 이를 기반으로 대규모의 클러스터 관리를 담당한다. 자체적인 서버 관리 기술로 Dell의 iDRAC, HP의 iLO, Supermicro의 SSM 등이 있으며, 클러스터 관리 도구로는 BCM, Warewulf, xCAT, Grendel 등이 활용된다. 그러나 대부분의 자체 하드웨어 서버 관리기술은 단일 서버 관리 기능만 지원하거나, 하드웨어 센서를 추가하거나 수정할 수 있는 관리 기능을 지원하지 않는다. 또한 대규모를 지원하는 주요 클러스터 관리 도구도 관리되는 서버의 종류가 제한되거나, 지원되는 하드웨어 센서를 추가하거나 수정하기 어렵다. 이를 위해 본 논문에서는 각각 다른 하드웨어 센서 아이디를 가지고 있는 여러 서버들로 이루어진 대규모 이기종 하드웨어를 통합적으로 관리, 제어, 모니터링하기 위한 센서 템플릿 기술을 소개한다.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.3
• /
• pp.293-302
• /
• 2023

This study examines and proposes standardization approaches to address the heterogeneous issues of metadata in drone imagery within the agricultural sector. Image metadata comes in various formats depending on different camera manufacturers, with most utilizing EXIF and XMP. The metadata of cameras used in fixed-wing and rotary-wing platforms, along with the metadata requirements in image alignment software, were analyzed for sensors like DJI XT2, MicaSense RedEdge-M, and Sentera Double4K. In the agricultural domain, multispectral imagery is crucial for vegetation analysis, making the provision of such imagery essential. Based on Pix4D SW, a comparative analysis of metadata attributes was performed, and necessary elements were compiled and presented as a proposed standardization (draft) in the form of tag information.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1223-1237
• /
• 2024

Autonomous vehicles use onboard sensors to sense the surrounding environment. In complex autonomous driving scenarios, the detection and recognition capabilities are constrained, which may result in serious accidents. An efficient way to enhance the detection and recognition capabilities is establishing collaborations with the neighbor vehicles. However, the collaborations introduce additional challenges in terms of the data heterogeneity, communication cost, and data privacy. In this paper, a novel personalized federated learning framework is proposed for addressing the challenges and enabling efficient collaborations in autonomous driving environment. For obtaining a global model, vehicles perform local training and transmit logits to a central unit instead of the entire model, and thus the communication cost is minimized, and the data privacy is protected. Then, the inference similarity is derived for capturing the characteristics of data heterogeneity. The vehicles are divided into clusters based on the inference similarity and a weighted aggregation is performed within a cluster. Finally, the vehicles download the corresponding aggregated global model and train a personalized model which is personalized for the cluster that has similar data distribution, so that accuracy is not affected by heterogeneous data. Experimental results demonstrate significant advantages of our proposed method in improving the efficiency of collaborative perception and reducing communication cost.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.28 no.5
• /
• pp.222-227
• /
• 2018

$Zn_{1-x}Co_x$ Zeolitic Imidazolate Framework (ZIF) (x = 0~0.05) were prepared by the co-precipitation of $Zn^{2+}$ and $Co^{2+}$ using 2-methylimidazole, which were converted into pure and Co-doped ZnO nanoparticles by heat treatment at $600^{\circ}C$ for 2 h. Homogeneous Zn/Co ZIFs were achieved at x < 0.05 owing to the strong coordination of the imidazole linker to $Zn^{2+}$ and $Co^{2+}$, facilitating atomic-scale doping of Co into ZnO via annealing. By contrast, heterogeneous Zn/Co ZIFs were formed at $x{\geq}0.05$, resulting in the formation of $Co_3O_4$ second phase. To investigate the potential as high-performance gas sensors, the gas sensing characteristics of pure and Co-doped ZnO nanoparticles were evaluated. The sensor using 3 at% Co-doped ZnO exhibited an unprecedentedly high response and selectivity to trimethylamine, whereas pure ZnO nanoparticles did not. The facile, bimetallic ZIF derived synthesis of doped-metal oxide nanoparticles can be used to design high-performance gas sensors.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.5C
• /
• pp.355-364
• /
• 2012

Target processing mechanisms are necessary to collect target information, real-time data fusion, and tactical environment recognition for cooperative engagement ability. Among these mechanisms, the target tracking starts from predicting state of speed, acceleration, and location by using sensors' measurements. However, it can be a problem to give the reliability because the measurements have a certain uncertainty. Thus, a technique which uses multiple sensors is needed to detect the target and increase the reliability. Also, data fusion technique is necessary to process the data which is provided from heterogeneous sensors for target tracking. In this paper, a target tracking algorithm is proposed based on probabilistic data association(PDA) by fusing radar and ESM sensor measurements. The radar sensor's azimuth and range measurements and the ESM sensor's bearing-only measurement are associated by the measurement fusion method. After gating associated measurements, state estimation of the target is performed by PDA filter. The simulation results show that the proposed algorithm provides improved estimation under linear and circular target motions.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.4
• /
• pp.50-58
• /
• 2017

Recently, some methods of converging heterogeneous fire sensor data have been proposed for effective fire detection, but the rule-based methods have low adaptability and accuracy, and the fuzzy inference methods suffer from detection speed and accuracy by lack of consideration for images. In addition, a few image-based deep learning methods were researched, but it was too difficult to rapidly recognize the fire event in absence of cameras or out of scope of a camera in practical situations. In this paper, we propose a novel fire detection system combining a deep learning algorithm based on CNN and fuzzy inference engine based on heterogeneous fire sensor data including temperature, humidity, gas, and smoke density. we show it is possible for the proposed system to rapidly detect fire by utilizing images and to decide fire in a reliable way by utilizing multi-sensor data. Also, we apply distributed computing architecture to fire detection algorithm in order to avoid concentration of computing power on a server and to enhance scalability as a result. Finally, we prove the performance of the system through two experiments by means of NIST's fire dynamics simulator in both cases of an explosively spreading fire and a gradually growing fire.

• KIISE Transactions on Computing Practices
• /
• v.21 no.1
• /
• pp.64-69
• /
• 2015

Place awareness is an essential for location-based services that are widely provided to smartphone users. However, traditional GPS-based methods are only valid outdoors where the GPS signal is strong and also require symbolic place information of the physical location. In this paper, environmental sounds and images are used to recognize important aspects of each place. The proposed method extracts feature vectors from visual, auditory and location data recorded by a smartphone with built-in camera, microphone and GPS sensors modules. The heterogeneous feature vectors were then learned by an ensemble learning method that learns each group of feature vectors for each classifier respectively and votes to produce the highest weighted result. The proposed method is evaluated for place recognition using a data group of 3000 samples in six places and the experimental results show a remarkably improved recognition accuracy when using all kinds of sensory data comparing to results using data from a single sensor or audio-visual integrated data only.