Earticle

현대 사회의 고층화된 대형 건축물은 화재 발생 시 막대한 인명 피해를 초래할 수 있으나, 기존의 정적 대피 시스템은 화재 확산, 연기, 건물 붕괴 등에 따른 경로 변화를 실시간으로 반영하지 못하여 오히려 대피를 지연시키는 한계를 지닌다. 이러한 문제를 해결하고자 본 연구는 BLE(Bluetooth Low Energy) 위치 추적 기술을 활용한 지능형 화재 대피 시스템을 제안한다. 본 시스템은 저전력, 저비용의 장 점을 가진 BLE 비콘의 RSSI(Received Signal Strength Indicator) 데이터를 활용하고, RSSI의 간섭 및 왜곡 문제를 보완하기 위해 핑거프린팅 기법을 적용하여 실시간 위치를 정확하게 추정한다. 또한, BLE 태그와 화재 감지 센서로부터 수집된 사용자 위치 및 환경 정보를 Flask 웹 서버로 전송하며, 서버에서는 이 데이터를 바탕으로 잔류 인원의 실시간 위치를 추정하고, 화재 상황과 비상구 위치를 반영한 그래프 모델 위에서 A* 알고리즘을 사용하여 최적의 동적 대피 경로를 산출한다. 본 연구는 기존 정적 시스템의 한계를 극복하 고 실시간 화재 대응이 가능한 지능형 대피 지원의 기초를 마련한다.

Modern high-rise buildings can cause massive casualties in the event of a fire. However, existing static evacuation systems have limitations, such as delaying evacuation due to insufficient real-time response to changes in evacuation routes caused by fire spread, smoke, and building collapse. To address this issue, this study proposes an intelligent fire evacuation system utilizing BLE(Bluetooth Low Energy) location tracking technology. This system utilizes the RSSI(Received Signal Strength Indicator) data of BLE beacons, which offer low power and cost. To compensate for RSSI interference and distortion, it applies a fingerprinting technique to accurately estimate real-time location. Furthermore, user location and environmental information collected from BLE tags and fire detection sensors are transmitted to a Flask web server. Based on this data, the server estimates the real-time locations of remaining occupants and, using the A* algorithm on a graph model reflecting the fire situation and emergency exit locations, derives optimal dynamic evacuation routes. This study overcomes the limitations of existing static systems and establishes the foundation for intelligent evacuation support capable of real-time fire response.

본 연구는 지능형 로봇에 대한 이해, 지능형 로봇의 위해성 분석, 지능형 로봇 안전관리 주요현황, 지능형 로봇 안전관리 추진방안 등을 통한 지능형 로봇 안전관리 발전방안을 제시하였다. 본 연구에서 도출된 연구결과는 다음과 같다. 첫째, 지능형 로봇 개발 및 보급 촉진법, 시행령, 시행규칙 등 관련법규에 지능형 로봇의 안전관리를 실질적으로 규제할 수 있는 조항을 신설하거나 별도의 법규를 제정하고, 나아가 윤리 및 안전 관련법규에도 지능형 로봇에 대한 안전관리 관련조항을 신설하는 방안을 추진해야 한다. 둘째, 지능형 로봇에 대한 안전관리를 보장하기 위해 국가적, 국제적인 합의를 통한 ‘로봇윤리헌장’의 제정이 필요하다. 이와 병행해 인간과 로봇의 공존을 위한 로봇윤리헌장의 대국민 홍보를 통해 일반인들의 지능형 로봇에 대한 안전관리 의식을 유도하고 지능형 로봇의 권리에 대한 이해를 제고하여야 한다. 셋째, 경호경비 관련 업계 및 학계는 지능형 로봇이 경호경비산업에 미치는 중대한 영향을 인식하고 지능형 로봇에 대한 안전관리 및 그 활용방안을 모색하여야 한다. 군사 로봇, 보안 로봇 등 지능형 로봇의 운용, 관리뿐만 아니라 이로부터 인간을 안전하게 보호하는 것도 경호경비의 한 분야로 부각될 전망이므로 이에 대한 적극적인 논의와 대응이 필요하다.

The purpose of this study is to progress the development plan of safety management on the intelligent robot through safety analysis on the intelligent robot, major present condition of safety management on the intelligent robot, enforcement method of safety management on the intelligent robot. The following is the result of the study. First, we have to establish the provision or the special legislation to regulate the safety management of the intelligent robot substantially in the intelligent robot development and supply promotion law, the enforcement ordinance, the enforcement regulation. And, we should propel to establish the provision on the safety management of the intelligent robot in the laws related on ethics and safety. Second, we should establish the Robot Ethical Charter through the national and international agreement to give a guarantee against the safety management of the intelligent robot. Furthermore, we have to induces people's interest on the safety management of the intelligent robot through offering the public information of the Robot Ethical Charter for coexistence of human and robot and have to understand about rights of the intelligent robot. Third, the security industry and learned circles have to recognize the important effect that the intelligent robot gets in the security industry and try to grope the safety management and the application plan on the intelligent robot. Also, the security industry and learned circles should concern not only using and managing of the intelligent robot including the military robot, the security robot but also protecting human from the intelligent robot.

본 논문은 다기능 소화기 제작의 문제점을 고찰하고 개선 방안을 제시하기 위한 연구이다. 센서를 응용한 하드 웨어 및 소프트웨어 설계 기술 확보하고 지능형 소화용 기구를 위한 GUI 형태의 사용자 인터페이스 설계 기술의 확보와 분사노즐에 대한 시뮬레이션을 통한 효율적인 설계로 제품 개발의 기술적 우위로 소방기술의 선진화에 기여할 것으로 판단된다. 이러한 다기능 친환경 소화기 개발로 소방산업의 경쟁력을 확보하여 편안하고 안락한 삶을 영위하고 화재로부 터 안전한 SAFE KOREA를 정착시키는데 기여할 것으로 기대된다.

This study is to investigate the problems of the production of multifunctional fire extinguishers and to suggest improvement measures. We acquire hardware and software design technology applying sensor and acquire user interface design skill of GUI for intelligent fire extinguishing apparatus. In addition, through the simulation of the injection nozzle, it can be contributed to advancement of fire prevention technology through technological advantage by product development through efficient design.It is anticipated that it will contribute to make safe and comfortable life by securing competitiveness of fire-fighting industry through development of multi-functional environment-friendly fire extinguisher, and to establish SAFE KOREA safe from fire.

건물 외부에 설치된 각종 기상 측정센서에서 전송된 현재의 외부 기상조건과 일자별, 특수일별 건물 에너지 사용량과의 관계를 인공 지능기법으로 분석하고 학습을 통한 예측기능을 갖도록 함으로써, 일자별, 특수일별, 계절별 그리고 기상조건에 따른 익일 전력 사용 량을 예측하고 이에 따른 부하의 On/Off 우선순위를 결정하는 기능을 갖는 지능형 직접부하제어 시스템 구조를 설계한다.

The electric utility has the responsibility of reducing the impact of peaks on electricity demand and related costs. Therefore, they have introduced Direct Load Control System (DLCS) to automate the external control of shedding customer load that it controls. The existing DLCS have been operated only depend on On/Off signal from the electric utility. That kind of DLCS operating has been successfully used until now. But since the number of customer load participating in the DLC program are keep increasing, On/Off signal control from the electric utility is no longer meets the needs of many different kind of customers. Therefore, In this paper, the author suggest the design of direct load control system using weather sensors to meet the diversity of different customer needs.

비행중인 드론에는 매우 다양한 주파수 성분의 진동이 발생되고, 이러한 진동 환경에서 드론에 장착된 카메라로부터 깨끗하고 안정된 영상을 획득하기 위해서는 짐발 시스템의 안정화 설계가 필요하다. 짐발 시스템은 카메라 모듈을 지지 하는 구조와 외부로 부터의 진동을 차단하면서 정확한 각도를 추종하는 안정화기로 구성된다. 본 논문에서는 짐발시스 템의 한 축에 대한 동역학 모델을 세우고 이에 대한 고전적인 PID제어기를 적용하여 본다. 또한 시스템에 대한 동적 모 델 없이 Intelligent-PID 제어기를 설계하고, 두 제어기의 성능을 MATLAB/Simulink을 이용한 시뮬레이션으로 비교하여 본다. 이들을 통하여, Intelligent-PID 제어기는 동역학 모델을 거의 필요로 하지 않고도 설계가 가능하고, 모델의 특성이 변하여도 제어기의 파라미터를 재조정할 필요가 없이 진동을 차단하고 각도를 추종 할 수 있는 제어강인성을 보인다.

A flying drone generates vibrations in a great variety of frequencies, and it requires a gimbal system stabilization loop design in order to obtain clean and accurate image from the camera attached to the drone under this environment. The gimbal system for drone comprises the structure that supports the camera module and the stabilization loop which follows the precise angle while blocking the vibration from outside. This study developed a dynamic model for one axis for the stabilization loop design of a gimbal system for drones and applied classical PID controller and intelligent PID controller. The Stabilization loop design was developed by using MATLAB/Simulink and compared the performance of each controller through simulation. Especially, the intelligent PID controller can be designed almost without the dynamic model and it demonstrates that the angle can be followed without readjusting the parameters of the controller even when the characteristics of the model changes.

This paper proposes an intelligent sensing framework for Internet-of-Things platforms, where sensor measurements stem from multiple causes. Sensors are selectively chosen for data collection to identify the cause with partial measurements. We employ variational deep embedding, a generative model capable of clustering and generation, to identify causes, cluster measurements accordingly, and determine causes for estimating complete measurements from partial data. These estimates aid in efficient sensor selection for data collection. Results demonstrate early and reliable cause sensing and complete measurement estimation using the proposed framework.

This paper investigates the use of artificial intelligence (AI) image detection and discrimination technology to address issues related to mixed assortments and defects encountered in the fastener manufacturing and packaging processes. The defect detection system primarily utilizes the YOLOv4-tiny model with parameter setting and data augmentation techniques. The mixed assortments detection system is constructed using U-Net-Light and Siamese network. The research results demonstrate that the developed systems can indeed replace or assist on-site personnel in conducting efficient and accurate inspections and screenings.

This paper considers an Intelligent Reconfigurable Surface (IRS)-enhanced Ambient Backscatter Communication (AmBC)-enabled Wireless Body Area Network (WBAN) system. We study the Base Station (BS) transmit power minimization problem, where the BS’s transmit beamforming vector and IRS’s reflecting coefficients are jointly optimized, subjected to the Signal-to-Noise Ratio (SNR) requirements of intra-WABN communication and throughput requirement of primary communication. To solve the non-convex problem, a near-optimal algorithm based on Semi-Definite Relaxation (SDR) and Successive Convex Approximation (SCA), and a low complexity algorithm based on IRS elements partition are proposed. Numerical results show that the two proposed algorithms considerably outperform the baseline schemes.

The vision of space exploration includes missions to deep space that produce significant amounts of video data and require reliable video streaming back to the Earth. The Internet of Deep Space Things (IoDST) is envisioned to provide communication services for video data streaming for the mission spacecrafts. Ensuring reliable communications in IoDST requires Transmission Control Protocol (TCP) layer functionalities. However, current TCP Congestion Control (CC) protocols provide poor performance in IoDST communications primarily owing to the dependence on pre-defined rules to determine the transmission rate in a single path TCP flow. This paper proposes a Multi-Path TCP (MPTCP) CC design for data streaming transmission in IoDST. We utilized Scalable Video Coding (SVC)-based streaming to overcome the Head-of-Line (HoL) blocking and proposed an intelligent CC scheme based on Q-learning and Deep Q-Network (DQN) to solve the problems of challenging link conditions in IoDST. Our proposed CC scheme determines the optimal congestion window for data transmission in IoDST communications to maximize the TCP throughput performance and streaming data playback. Simulation results show that our proposed CC scheme achieves TCP throughput performance by up to approximately 257.14% and 73.08% compared to TCP CUBIC and TCP Westwood. In addition, video streaming playback by up to approximately 164.86%, 104.17%, 75%, 157.89% and 66% compared to TCP CUBIC, TCP BBR, TCP Westwood, DRL-TCP and QLE-DS, respectively. Finally the total streaming data transfer time by up to approximately 61%, 20%, 63%, 21% and 19% compared to TCP CUBIC, TCP BBR, TCP Westwood, DRL-TCP and QLE-DS, respectively.

Estimating the location of a target in search-and-rescue operations is quite challenging when the target is not responding. Therefore, in this paper, we investigate the passive target localization problem using mobile unmanned aerial vehicles (UAVs), where multiple mobile UAVs receive the time-difference-of-arrival (TDOA) measurements from the source UAV. Unlike traditional TDOA for static UAVs, the problem becomes more challenging when considering the mobility of UAVs. Therefore, we propose a novel TDOA model for target localization with mobile UAVs. We also measure the performance limit inequality between its Cramer-Rao lower bound (CRLB) and the mean-squared error (MSE).

This paper considers the intelligent reflecting surface-aided MIMO secrecy rate maximization. We apply the alternating optimization to maximize the secrecy rate of the MIMO wiretap channels. We first provide the closed-form solution to each subproblem of optimizing reflecting unit coefficient and show that the sequence generated by the coordinate descent method converges to a stationary point of the main optimization problem. Numerical results show that the intelligent reflecting surface significantly increases secrecy rates in MIMO wiretap channels.

This paper presents a novel approach to detection of malicious network traffic using artificial neural networks suitable for use in deep packet inspection based intrusion detection systems. Experimental results using a range of typical benign network traffic data (images, dynamic link library files, and a selection of other miscellaneous files such as logs, music files, and word processing documents) and malicious shell code files sourced from the online exploit and vulnerability repository exploitdb [1], have shown that the proposed artificial neural network architecture is able to distinguish between benign and malicious network traffic accurately. The proposed artificial neural network architecture obtains an average accuracy of 98%, an average area under the receiver operator characteristic curve of 0.98, and an average false positive rate of less than 2% in repeated 10-fold cross-validation. This shows that the proposed classification technique is robust, accurate, and precise. The novel approach to malicious network traffic detection proposed in this paper has the potential to significantly enhance the utility of intrusion detection systems applied to both conventional network traffic analysis and network traffic analysis for cyber?physical systems such as smart-grids.

Open Radio Access Network (RAN) is an important architecture design shift for 5G and next generation telecommunications networks. With open RAN, mobile network operators would be able to mix and match multi-vendor RAN solutions as long as the solutions comply with open standards. O-RAN Alliance is the global leader in standardizing the open RAN architecture, where RAN Intelligent Controller (RIC) is positioned centrally as the brain of a RAN to manage and optimize the RAN operations. Open-source projects play a key role in accelerating the adoption of open RAN architecture, especially the use of RIC. However, the fast pace of development and the lack of documentation in open-source projects create steep learning curve for beginners. In this paper, we first provide an overview of widely used open-source RIC projects and discuss their pros and cons. We then share our first-hand experience to use RIC in our campus 5G network that consists of commercial-grade RAN solutions. In particular, we developed a suite of three RAN control applications (i.e., energy efficiency, interference management, and predictive maintenance) on an open-source RIC, and we deploy and evaluate them on a commercial-grade 5G network in a university campus. For these RIC applications, we design and evaluate different ML models based on real-world data collected from our 5G network, which we publish together with this paper. Our experimental results show that AI-based RIC applications can achieve more than 90% of accuracy in inferring the situation of the RAN for each given task. Our energy-saving RIC application can reduce 65% of energy consumption of the RAN over a simulated period of one year. Our project also validates the feasibility to interfacing an open-source RIC with existing commercial-grade 5G solutions.

For efficient, controllable, and secure communication, different technologies are integrated with sixth-generation (6G) networks. Backscatter communication (BackCom) is an energy harvesting communication technology which is very efficient for 6G networks and Internet of Things (IoT) applications. For seamless and controllable signal propagation, reconfigurable intelligent surface (RIS) is particularly effective which provides better signal quality through its electronically controlled smart beamforming techniques. This article provides an overview and research directions regarding promising RIS-assisted BackCom. A secured RIS-assisted BackCom for seamless, reliable, and efficient communication is also presented in this study. The research findings reveal that when we deploy RIS-assisted BackCom, the channel gain, data transmission rate, and energy efficiency of the signal reflecting surfaces are all substantially enhanced.

Pig breeding management directly contributes to the profitability of pig farms, and pregnancy diagnosis is an important factor in breeding management. Therefore, the need to diagnose pregnancy in sows is emphasized, and various studies have been conducted in this area. We propose a computer-aided diagnosis system to assist livestock farmers to diagnose sow pregnancy through ultrasound. Methods for diagnosing pregnancy in sows through ultrasound include the Doppler method, which measures the heart rate and pulse status, and the echo method, which diagnoses by amplitude depth technique. We propose a method that uses deep learning algorithms on ultrasonography, which is part of the echo method. As deep learning-based classification algorithms, Inception-v4, Xception, and EfficientNetV2 were used and compared to find the optimal algorithm for pregnancy diagnosis in sows. Gaussian and speckle noises were added to the ultrasound images according to the characteristics of the ultrasonography, which is easily affected by noise from the surrounding environments. Both the original and noise added ultrasound images of sows were tested together to determine the suitability of the proposed method on farms. The pregnancy diagnosis performance on the original ultrasound images achieved 0.99 in accuracy in the highest case and on the ultrasound images with noises, the performance achieved 0.98 in accuracy. The diagnosis performance achieved 0.96 in accuracy even when the intensity of noise was strong, proving its robustness against noise.

Due to the complex functioning of Smart Healthcare Systems (SHS), many security concerns have been raised in the past. It provisions the attackers to hamper the working of SHS in a variety of ways, e.g., injection of false data to replace vital signs, tampering of medical devices to prevent informing critical situations, etc. In this work, a novel ML-based framework, i.e., SmartHealth is proposed to secure IoMT devices in SHS. SmartHealth watches the vital signs gathered through different IoMT to analyze the change in various body activities to differentiate between normal activities and dangerous security attacks. The performance of the SmartHealth is also analyzed for three different dangerous attacks. During performance analysis, it has been observed that SmartHealth can identify wicked activities in IoMT 92% times accurately with an F1-score of 90%.

Edge computing has emerged as a promising paradigm for addressing the latency, bandwidth, and scalability challenges associated with traditional cloud-centric architectures. Computation offloading, the process of transferring computational tasks from edge devices to more powerful remote servers or cloud infrastructure, plays a crucial role in optimizing performance and resource utilization in edge computing systems. However, traditional computation offloading techniques often face limitations related to latency, network dependency, and scalability. In this survey, we explore the integration of digital twin (DT) technology into edge computing environments to empower intelligent computation offloading decisions. DTs, virtual representations of physical entities or systems that mirror their real-world counterparts, offer opportunities to enhance situational awareness, optimize resource allocation, and enable more informed decision-making at the edge. We provide a comprehensive overview of DTs empowered intelligent computation offloading, covering the fundamentals of DTs, traditional computation offloading techniques, and their limitations in edge computing. Additionally, we discuss how DTs can address these challenges and improve computation offloading strategies, along with practical applications and use cases across various domains. Finally, we identify open research challenges and opportunities for future exploration in this emerging field. Through this survey, we aim to provide researchers, practitioners, and stakeholders with insights into the potential of DTs to revolutionize computation offloading for edge computing and drive innovation in this rapidly evolving area.

This paper investigates the performance of using multiple intelligent reflecting surface (IRS)-assisted communication as compared to the hybrid approach. We demonstrate that for practical scenarios with a limited amount of radiated power, the performance can be significantly enhanced by increasing numbers of IRS. Upper bounds are derived for multiple IRSs using both ideal and quantization phase errors over different channel environments. The proposed method having multiple-IRSs is validated for both Rician and Rayleigh fading scenarios, including ideal and quantization phase errors. The proposed method shows a significant improvement in terms of achievable rate by increasing number of IRS over hybrid IRS-relay scheme. A degradation in performance is observed by assuming phase quantization errors. Finally, it is demonstrated that increasing number of reflecting elements improve the achievable rate, but gets saturate with further increase in the number of reflecting elements.