Earticle

The high-frequency band, crucial for supporting the 5G/6G system, faces challenges of signal obstruction by obstacles. This is attributed to significant path loss resulting from radio straightness and short radio distance. To address these challenges, there is a growing interest in leveraging non-terrestrial networks (NTNs) and reconfigurable intelligent surfaces (RISs), utilizing high-altitude satellites as base stations or terminals. Within a three-dimensional NTN system, the vulnerability of wireless signals to eavesdropping due to the open nature of the environment is a notable drawback. To mitigate this vulnerability, this paper introduces an algorithm designed to maximize the secrecy rate. The proposed algorithm optimizes security performance by fine-tuning the base station and RIS beamforming vectors. This optimization is achieved through successive convex approximation and minorization?maximization algorithms. Simulation results affirm the superiority of the proposed algorithm in terms of secrecy rate over existing techniques.

Unmanned aerial vehicles (UAVs) and reconfigurable intelligent surfaces (RISs) have garnered considerable research interest in the fields of 5G and 6G wireless communication due to their remarkable flexibility and cost-effectiveness. However, the inherent openness of wireless communication environments renders these technologies vulnerable to eavesdropping. This paper presents a penalty-based successive convex approximation algorithm and a minorize?maximization algorithm to optimize the transmission beamforming vector, RIS beamforming vector, and UAV?RIS trajectory. The objective of this study was to enhance the physical layer security performance of wireless communication systems using UAVs and RISs. Our simulation results demonstrate that the proposed technique achieves a higher security transmission rate compared to existing techniques.

The large amplitude variations of OFDM signals generate in-band distortion and out-of-band radiation. In recent years, cubic metric (CM) has been verified as a more accurate metric to measure the amplitude variations. In this paper, the PTS technique is used to decrease the CM of OFDM signals. To overcome the search complexity of an exhaustive search based PTS technique, we introduce an improved backtracking search (IBS) optimization algorithm. Simulations are conducted to show the advantages of the proposed IBS based PTS approach compared with the conventional OFDM, and several state-of-the-art methods in terms of search complexity and CM reduction performance.

High-risk pregnancy endangers both mother and baby, with one maternal death every two minutes in 2023. This study has proposed three Gradient Boosting models?GB-Base, GB-SMOTE, and ZOA-GB?using the West Lombok Pregnancy Risk Prediction Dataset. GB-Base and GB-SMOTE have achieved 90.46% and 90.28% accuracy, while ZOA-GB, using 10 selected features, has reached 88.89%. GB-SMOTE has shown the best performance with an F-score of 84.41%. SHAP has identified Maternal Age, Hemoglobin, and Parity as key features, and DiCE has validated feature-driven prediction control. The study is limited by a single-source dataset, the absence of external-validation, and unexplored optimizers.

The objective of cloud task scheduling is to partition tasks on shared resources to minimize energy consumption and makespan. Recently, several meta-heuristics for task scheduling were proposed and achieved encouraging results. However, their performance is far from the ideal state and needs more improvement. This paper introduces an enhanced sunflower optimization (ESFO) algorithm for improving the performance of existing task scheduling. It finds optimal scheduling in a polynomial time. The experiments show that ESFO outperformed its counterparts. The amount of improvement in comparison with the best counterpart is 0.73% and 2.24% respectively in terms of makespan and energy consumption.

The primary objective of task scheduling involves scheduling the task on resources and minimizing the objective of the schedule. In this study, we proposed mean grey wolf optimization algorithm to enhance the system performance there by depleting the scheduling issues. The main objective of this method is minimizing the makespan and energy consumption. The objective of the proposed algorithms has been evaluated using CloudSim toolkit for standard workload (left-skewed & right-skewed). The outcome of the simulation result shows that the proposed Mean GWO algorithm renders comparatively ample result than the other existing algorithms.

This paper proposes a new intrusion detection system (IDS) based on a combination of a multilayer perceptron (MLP) network, and artificial bee colony (ABC) and fuzzy clustering algorithms. Normal and abnormal network traffic packets are identified by the MLP, while the MLP training is done by the ABC algorithm through optimizing the values of linkage weights and biases. The CloudSim simulator and NSL-KDD dataset are used to verify the proposed method. Mean absolute error (MAE), root mean square error (RMSE), and the kappa statistic are considered as evaluation criteria. The obtained results have indicated the superiority of the proposed method in comparison with state-of-the-art methods.

The proximal policy optimization (PPO) algorithm is a promising algorithm in reinforcement learning. In this paper, we propose to add an action mask in the PPO algorithm. The mask indicates whether an action is valid or invalid for each state. Simulation results show that, when compared with the original version, the proposed algorithm yields much higher return with a moderate number of training steps. Therefore, it is useful and valuable to incorporate such a mask if applicable.

Task scheduling is one of the most important issues in heterogeneous environments when high efficiency is required. Because task scheduling is a Nondeterministic Polynomial (NP)-hard problem, many evolutionary algorithms have been adopted to solve this problem. Since the convergence speed of solutions in population-based algorithms is low, they are integrated with local search algorithms. Thus, in this paper, to optimize the task scheduling makespan, a hybrid particle swarm optimization and hill climbing algorithm is proposed. The experimental results on random and scientific Directed Acyclic Graph (DAG) showed that the proposed algorithm performs effectively in terms of the makespan compared to the current well-known heuristic and particle swarm optimization algorithms.

고객의 요구에 대한 빠른 대응과 유연하고 효율적으로 새로운 제품을 적기에 개발하기 위해서는 제품 플랫폼에 기초한 대량 맞춤이 절실히 요구된다. 이러한 목적을 달성하기 위하여 기업들은 상대적으로 생산비용을 낮게 유지하면서 대량생산의 이점을 유지하고 동시에 고객의 요구사항을 만족시키기 위해, product family를 도입하고 가능하면 작은 변화를 통하여 제품의 다양성을 유지하고자 한다. Product family를 설계할 때 중요한 이슈 중에 하나는 제품의 공통성과 차별성간의 절충점을 찾아내는 것인데, 본 연구에서는 설계자들이 product family 재설계를 용이하게 하기 위한 방법론을 제안한다. 이를 위하여 본 연구에서는 ant colony 알고리즘과 product family의 공통성 평가지수를 이용하여 product family 재설계 방법론을 개발한다. 제안한 방법론은 복잡하고 반복적인 많은 계산과정을 가지고 있는 다른 방법과 달리 메타 휴리스틱 알고리즘을 적용하여 인간의 간섭을 줄이고, 실험결과의 정확도, 반복성 및 강건성을 향상시킨다. 본 연구에서는 컴퓨터 마우스 제품군을 대상으로 제안한 방법의 타당성을 검증하였고, 추가적으로 product family 레벨과 부품 레벨의 product family 재설계 추천방안도 제시하였다.

신체영역무선통신망(WBAN)에서 클러스터 헤드(CH) 선출 및 최적경로의 라우팅은 에너지 효율 향상과 네트워크 노드 운영수명 연장을 위해 해결해야 할 이슈이다. 이러한 연구를 위해 본 논문에서는 BKOA알고리즘과 그리드 기반 멀티홉 라우팅 프레임워크를 결합한 하이브리드 BKOA-GRID를 제안한다. 시뮬레이션 수행결과 제안된 BKOA-GRID는 PSO, LEACH, EEUC 등 기존 알고리즘보다 노드생존율 90%, 잔류에너지 지속성은 총 에너지의 약 60%를 유지하여 높은 에너지 효율을 보였다.

Cluster head(CH) election and optimal path routing in a Wireless Body Area Network(WBAN) are issues that must be addressed to improve energy efficiency and extend the operating life of network nodes. To address these issues, this paper proposes a hybrid BKOA-GRID (Black Kite Optimization Algorithm-GRID) framework, which integrates the Black Kite Optimization Algorithm with a grid-based multi-hop routing structure. Simulation results demonstrate that the proposed BKOA-GRID exhibits superior energy efficiency compared to existing algorithms such as PSO, LEACH, and EEUC, maintaining a node survival rate of 90% and preserving approximately 60% of the total residual energy.

An UHF () RFID tag antenna is optimized and designed using a genetic algorithm (GA). The tag antenna impedance should be matched to the conjugate of the impedance of the tag IC Chip. The chip impedance has real and capacitive imaginary parts due to the parasitic capacitance of the RFID chip. A GA linked with a commercially available antenna simulation program optimizes the UHF tag antenna to match a commercially available RFID chip. This method shows that any RFID antenna can be designed for any commercial RFID chip with any impedance.

본 연구의 목적은 주석 필터를 사용한 high-pitch 기반 저선량 프로토콜이 적용된 전산화단층영상에서 발생하는 화질 저하 문제를 해결하기 위해 융합형 노이즈 제거 알고리즘을 모델링하고 그 kernel size를 최적화하는 것이다. CT 영상을 획득하기 위하여 AAPM CT performance phantom을 사용하였으며, 고주파 신호 손실 저감을 위하여 median-modified Wiener filter에 Richardson-Lucy 복원 알고리즘이 혼합된 융합형 노이즈 제거 알고리즘을 모델 링하였다. 알고리즘 적용 후의 노이즈 개선 정도를 객관적으로 평가하기 위하여 정량적 평가인자인 coefficient of variation (COV), contrast to noise ratio (CNR), 그리고 natural image quality evaluator (NIQE)를 계산하였다. 그 결과, 7 × 7의 kernel size에서 가장 우수한 영상특성을 나타내었고, 최적화된 융합형 노이즈 제거 알고리즘이 적용된 주석 필터를 사용한 high-pitch 기반 저선량 프로토콜이 적용된 영상을 알루미늄 필터 및 저선량 프로토콜이 적용되지 않은 주석 필터 영상과 비교하였을 때 COV 값은 각각 약 2.36배 및 3.95배, CNR 값은 4.36배 및 7.31배, 그리고 NIQE 값은 1.43배 및 1.45배 향상되었다. 결론적으로, 본 연구를 통해 kernel size가 7 × 7으로 최적화 된 융합형 노이즈 제거 알고리즘을 적용함으로써 주석 필터를 사용한 high-pitch 기반 저선량 프로토콜은 CT 영상의 화질 저하 문제를 해결하는 데에 있어 효과적임을 확인하였다.

In this study, computed tomography (CT) images were obtained using American Association of Physicists in Medicine CT performance phantom to quantitatively evaluate changes in image quality due to the application of high-pitch-based low-dose protocols using tin filters. Median modified Wiener filter algorithm and the Richardson-Lucy restoration algorithm were used fusion noise reduction algorithm, and kernel size was set from 3 × 3 to 15 × 15. We applied a fusion noise reduction algorithm from the acquired images, and quantitatively evaluated the effectiveness of reducing radiation dose and improving image quality. In addition, tin filter images without aluminum filters and low-dose protocols were obtained for comparative evaluation. As a result, the kernel size of 7 × 7 showed the best image quality, it was confirmed that images with low-dose protocols applied with optimized algorithms improved coefficient of variation values by 2.36 times and 3.95 times, contrast to noise ratio values by 4.36 times and 7.31 times, and natural image quality evaluator values by 1.43 times and 1.45 times. In conclusion, if high-pitch based low-dose protocols using tin filters can be stably used by applying the fusion noise reduction algorithm, it is expected that to reduce the exposure dose and provide patient-centered care services.

이 논문은 다목적 최적화 알고리듬을 이용하여 오일샌드 저류층에서 생산성이 높으면서도 최적의 에너지효 율을 갖는 SAGD(Steam Assisted Gravity Drainage) 공법의 운영조건을 선정하는 기법을 제안한다. 기존의 SAGD 공 법 최적화 연구들은 경제성인자가 고정된 단목적 최적화에 집중하였다. 이 연구에서는 회수율 최대화와 누적증기오 일비 최소화 관점에서 비지배관계에 놓이는 최적 생산운영 시나리오를 선정하였다. 이를 통하여 특정 목적함수에 편 향된 하나의 최종해만을 도출하는 기존 방법의 한계를 개선하였다. 제안한 방법으로 선정된 최적운영 시나리오들은 기존 방법과 달리 유가상황 및 비용 변화에 따라 추가적인 최적화 작업 없이 광구운영 의사결정에 유용하게 활용할 수 있다.

This paper proposes multi-objective optimization of the Steam Assisted Gravity Drainage (SAGD) process for improving the energy efficiency and recovery factor of oil sand reservoirs. Previous studies conducted on optimizing the SAGD process have focused on single-objective optimization with fixed economic factors. In this study, multiple trade-off operating scenarios were selected by applying a multi-objective optimization algorithm that aims at maximizing the recovery factor and minimizing the cumulative steam-oil ratio for efficiently addressing volatile market conditions. Thus, the proposed method can overcome the limitations of conventional optimization methods that not only yield a single solution based on a particular objective function but also are hard to adapt to fluctuating oil prices. Furthermore, the proposed method can provide optimum trade-off operating scenarios, and hence can aid in planning operating (i.e., marketing) strategies according to the variation in oil prices and operating costs, without the need for an additional optimization process.

에어컴프레서는 다양한 제조공장에서 널리 사용되고 있는 원동기이며, 공기역학을 기반으로 하는 다수의 제조 장비 에 동력을 제공하고 있어, 예기치 못한 고장이 발생할 경우 전체 제조라인의 가동이 중단될 수 있다. 본 연구에서는 컴프레서에 통신이 가능한 진동센서를 부착하여 컴프레서 가동 시 발생되는 진동 데이터를 클라우드 상에 축적하고 수집된 데이터로부터 컴프레서의 운영 상태 진단을 위한 특징들을 추출하였다. ‘합성곱신경망(Convolutionl Neural Networks)’을 활용하여 수집된 데이터와 추출된 특징들을 학습시켜 컴프레서의 상태 건전성을 자동으로 예측할 수 있도록 인공지능 알고리즘을 고안하였다. 이후 합성곱신경망의 최적화 파라미터별로 컴프레서의 건전성 예측 정확도에 어떠한 영향을 미치는지 실험하였다. 실험결과, 합성곱신경망을 통한 컴프레서의 진동 데이터 분석에 서는 ‘모멘텀’ 최적화 기법의 판정 정확도가 가장 우수하였다. 데이터 셋의 특성에 따라 적절한 신경망 최적화 기법 이 합성곱신경망 학습 효율과 예측 정확도를 결정짓는 매우 중요한 요소임을 확인할 수 있었다.

The air compressor is a common rotating machine that is widely used in various manufacturing plants, and provides power to a number of manufacturing devices based on aerodynamics in the plant, so if an unexpected failure occurs, the entire manufacturing line can be shut down. In this study, a vibration sensor capable of communication was attached to the compressor, the vibration data generated during compressor operation was accumulated on the cloud, and features for diagnosing the operating status of the compressor were extracted from the collected data. An artificial intelligence algorithm was designed to automatically predict the health-condition of the air- compressor by learning the collected data and extracted features using ‘Convolutional Neural Network (CNN). And then we tested how each CNN optimization parameter affected the compressor's health prediction accuracy. As a result of the experiment, in analyzing compressor vibration data through CNN, the ‘momentum’ optimization algorithm had the best accuracy, and depending on the characteristics of the data set. We found that appropriate neural network optimization techniques are a very important factor in determining CNN learning efficiency and prediction accuracy.