• Smart Structures and Systems
• /
• 제33권1호
• /
• pp.65-91
• /
• 2024

The use of five optimization techniques for the prediction of a strength-based concrete mixture's best-fit model is examined in this work. Five optimization techniques are utilized for this purpose: Slime Mold Algorithm (SMA), Black Hole Algorithm (BHA), Multi-Verse Optimizer (MVO), Vortex Search (VS), and Whale Optimization Algorithm (WOA). MATLAB employs a hybrid learning strategy to train an artificial neural network that combines least square estimation with backpropagation. Thus, 72 samples are utilized as training datasets and 31 as testing datasets, totaling 103. The multi-layer perceptron (MLP) is used to analyze all data, and results are verified by comparison. For training datasets in the best-fit models of SMA-MLP, BHA-MLP, MVO-MLP, VS-MLP, and WOA-MLP, the statistical indices of coefficient of determination (R²) in training phase are 0.9603, 0.9679, 0.9827, 0.9841 and 0.9770, and in testing phase are 0.9567, 0.9552, 0.9594, 0.9888 and 0.9695 respectively. In addition, the best-fit structures for training for SMA, BHA, MVO, VS, and WOA (all combined with multilayer perceptron, MLP) are achieved when the term population size was modified to 450, 500, 250, 150, and 500, respectively. Among all the suggested options, VS could offer a stronger prediction network for training MLP.

• 한국산업융합학회 논문집
• /
• 제27권3호
• /
• pp.701-707
• /
• 2024

Industry 4.0 has brought about significant changes in the roles of workers through the introduction of innovative technologies. In smart factory environments, workers are required to interact seamlessly with robots and automated systems, often utilizing equipment enhanced by Virtual Reality (VR) and Augmented Reality (AR) technologies. This study aims to systematically analyze recent research literature on monitoring the physical and mental states of workers in Industry 4.0 environments. Relevant literature was collected using the Web of Science database, employing a comprehensive keyword search strategy involving terms related to Industry 4.0 and health monitoring. The initial search yielded 1,708 documents, which were refined to 923 journal articles. The analysis was conducted using VOSviewer, a tool for visualizing bibliometric data. The study identified general trends in the publication years, countries of authors, and research fields. Keywords were clustered into four main areas: 'Industry 4.0', 'Internet of Things', 'Machine Learning', and 'Monitoring'. The findings highlight that research on health monitoring of workers in Industry 4.0 is still emerging, with most studies focusing on using wearable devices to monitor mental and physical stress and risks. This study provides a foundational overview of the current state of research on health monitoring in Industry 4.0, emphasizing the need for continued exploration in this critical area to enhance worker well-being and productivity.

• International journal of advanced smart convergence
• /
• 제13권2호
• /
• pp.205-213
• /
• 2024

This study uses a large language model (LLM) to identify Aristotle's rhetorical principles (ethos, pathos, and logos) in COVID-19 information on Naver Knowledge-iN, South Korea's leading question-and-answer community. The research analyzed the differences of these rhetorical elements in the most upvoted answers with random answers. A total of 193 answer pairs were randomly selected, with 135 pairs for training and 58 for testing. These answers were then coded in line with the rhetorical principles to refine GPT 3.5-based models. The models achieved F1 scores of .88 (ethos), .81 (pathos), and .69 (logos). Subsequent analysis of 128 new answer pairs revealed that logos, particularly factual information and logical reasoning, was more frequently used in the most upvoted answers than the random answers, whereas there were no differences in ethos and pathos between the answer groups. The results suggest that health information consumers value information including logos while ethos and pathos were not associated with consumers' preference for health information. By utilizing an LLM for the analysis of persuasive content, which has been typically conducted manually with much labor and time, this study not only demonstrates the feasibility of using an LLM for latent content but also contributes to expanding the horizon in the field of AI text extraction.

• International Journal of Computer Science & Network Security
• /
• 제23권12호
• /
• pp.199-203
• /
• 2023

In recent decades, the growth of communication technology has resulted in an explosion of data-related information. Ontology perception is being used as a growing requirement to integrate data and unique functionalities. Ontologies are not only critical for transforming the traditional web into the semantic web but also for the development of intelligent applications that use semantic enrichment and machine learning to transform data into smart data. To address these unclear facts, several researchers have been focused on expanding ontologies and semantic web technologies. Due to the lack of clear-cut limitations, ontologies would not suffice to deliver uncertain information among domain ideas, conceptual formalism supplied by traditional. To deal with this ambiguity, it is suggested that fuzzy ontologies should be used. It employs Ontology to introduce fuzzy logical policies for ambiguous area concepts such as darkness, heat, thickness, creaminess, and so on in a device-readable and compatible format. This survey efforts to provide a brief and conveniently understandable study of the research directions taken in the domain of ontology to deal with fuzzy information; reconcile various definitions observed in scientific literature, and identify some of the domain's future research-challenging scenarios. This work is hoping that this evaluation can be treasured by fuzzy ontology scholars. This paper concludes by the way of reviewing present research and stating research gaps for buddy researchers.

• 한국인터넷방송통신학회논문지
• /
• 제24권3호
• /
• pp.63-67
• /
• 2024

최근 스마트 물류, 핀테크, 엔터테인먼트 등 다양한 산업 분야의 인공지능 워크로드들이 클라우드 상에서 실행되고 있다. 본 논문은 이기종 GPU 클러스터로 구성된 다중 테넌트 클라우드 시스템에서 다양한 인공지능 워크로드가 실행될 때 발생하는 스케줄링 문제를 다룬다. 전통적인 스케줄링은 이러한 환경에서 GPU 이용률을 크게 저하시켜 시스템의 성능을 떨어뜨린다. 이러한 문제를 해결하기 위해, 본 논문에서는 유전 알고리즘 기반의 최적화 기법을 사용하는 새로운 스케줄링 접근 방식을 제안하고, 이를 프로세스 기반 이벤트 시뮬레이션 프레임워크에 구현하였다. 알리바바의 MLaaS 클러스터에서 수집한 광범위한 인공지능 작업들의 트레이스를 재현하는 실험을 통해 제안하는 스케줄링이 기존 스케줄링에 비해 GPU 이용률을 크게 개선함을 확인하였다.

• 문화기술의 융합
• /
• 제10권1호
• /
• pp.617-623
• /
• 2024

언어와 감정 사이의 복잡한 관계의 특징을 보이며, 우리의 말을 통해 감정을 식별하는 것은 중요한 과제로 인식된다. 이 연구는 음성 및 텍스트 데이터를 모두 포함하는 다중 모드 분류 작업을 통해 음성 언어의 감정을 식별하기 위해 속성 엔지니어링을 사용하여 이러한 과제를 해결하는 것을 목표로 한다. CNN(Convolutional Neural Networks)과 LSTM(Long Short-Term Memory)이라는 두 가지 분류기를 BERT 기반 사전 훈련된 모델과 통합하여 평가하였다. 논문에서 평가는 다양한 실험 설정 전반에 걸쳐 다양한 성능 지표(정확도, F-점수, 정밀도 및 재현율)를 다룬다. 이번 연구 결과는 텍스트와 음성 데이터 모두에서 감정을 정확하게 식별하는 두 모델의 뛰어난 능력을 보인다.

• 한국인공지능학회지
• /
• 제12권3호
• /
• pp.1-7
• /
• 2024

In this paper, we propose an innovative super-resolution technique to address the issue of reduced accuracy in license plate recognition caused by low-resolution images. Conventional vehicle license plate recognition systems have relied on images obtained from fixed surveillance cameras for traffic detection to perform vehicle detection, tracking, and license plate recognition. However, during this process, image quality degradation occurred due to the physical distance between the camera and the vehicle, vehicle movement, and external environmental factors such as weather and lighting conditions. In particular, the acquisition of low-resolution images due to camera performance limitations has been a major cause of significantly reduced accuracy in license plate recognition. To solve this problem, we propose a Single Image Super-Resolution (SISR) model with a parallel structure that combines Multi-Scale and Attention Mechanism. This model is capable of effectively extracting features at various scales and focusing on important areas. Specifically, it generates feature maps of various sizes through a multi-branch structure and emphasizes the key features of license plates using an Attention Mechanism. Experimental results show that the proposed model demonstrates significantly improved recognition accuracy compared to existing vehicle license plate super-resolution methods using Bicubic Interpolation.

• Smart Structures and Systems
• /
• 제33권5호
• /
• pp.325-332
• /
• 2024

This study proposes a novel long short-term memory (LSTM)-based approach for predicting carbonation depth, with the aim of enhancing the durability evaluation of concrete structures. Conventional carbonation depth prediction relies on statistical methodologies using carbonation influencing factors and in-situ carbonation depth data. However, applying in-situ data for predictive modeling faces challenges due to the lack of time-series data. To address this limitation, an LSTM-based carbonation depth prediction technique is proposed. First, training data are generated through random sampling from the distribution of carbonation velocity coefficients, which are calculated from in-situ carbonation depth data. Subsequently, a Bayesian theorem is applied to tailor the training data for each target bridge, which are depending on surrounding environmental conditions. Ultimately, the LSTM model predicts the time-dependent carbonation depth data for the target bridge. To examine the feasibility of this technique, a carbonation depth dataset from 3,960 in-situ bridges was used for training, and untrained time-series data from the Miho River bridge in the Republic of Korea were used for experimental validation. The results of the experimental validation demonstrate a significant reduction in prediction error from 8.19% to 1.75% compared with the conventional statistical method. Furthermore, the LSTM prediction result can be enhanced by sequentially updating the LSTM model using actual time-series measurement data.

• Smart Structures and Systems
• /
• 제34권1호
• /
• pp.9-15
• /
• 2024

Oversampling algorithms are methods employed in the field of machine learning to address the constraints associated with data quantity. This study aimed to explore the variations in reliability as data volume is progressively increased through the use of oversampling algorithms. For this purpose, the synthetic minority oversampling technique (SMOTE) and the borderline synthetic minority oversampling technique (BSMOTE) are chosen. The data inputs, which included air temperature, humidity, and wind speed, are parameters used in the Fosberg Fire-Weather Index (FFWI). Starting with a base of 52 entries, new data sets are generated by incrementally increasing the data volume by 10% up to a total increase of 100%. This augmented data is then utilized to predict FFWI using a deep neural network. The coefficient of determination (R²) is calculated for predictions made with both the original and the augmented datasets. Suggesting that increasing data volume by more than 50% of the original dataset quantity yields more reliable outcomes. This study introduces a methodology to alleviate the challenge of establishing a standard for data augmentation when employing oversampling algorithms, as well as a means to assess reliability.

• International journal of advanced smart convergence
• /
• 제13권3호
• /
• pp.41-47
• /
• 2024

In this paper, we deal with a game theoretic problem to explore interactions between evasive Artificial Intelligence (AI) malware and detectors in Internet of Things (IoT). Evasive AI malware is defined as malware having capability of eluding detection by exploiting artificial intelligence such as machine learning and deep leaning. Detectors are defined as IoT devices participating in detection of evasive AI malware in IoT. They can be separated into two groups such that one group of detectors can be armed with detection capability powered by AI, the other group cannot be armed with it. Evasive AI malware can take three strategies of Non-attack, Non-AI attack, AI attack. To cope with these strategies of evasive AI malware, detector can adopt three strategies of Non-defense, Non-AI defense, AI defense. We formulate a Bayesian game theoretic model with these strategies employed by evasive AI malware and detector. We derive pure strategy Bayesian Nash Equilibria in a single stage game from the formulated Bayesian game theoretic model. Our devised work is useful in the sense that it can be used as a basic game theoretic model for developing AI malware detection schemes.