http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Love Allen Chijioke Ahakonye,Cosmas Ifeanyi Nwakanma,Jae Min Lee,Dong-Seong Kim 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.11
A dependable Smart Factory (SF) Supervisory Control and Data Acquisition (SCADA) network consolidates the security features of Artificial Intelligence (AI) and Information Technology (IT) trustworthiness by exploiting Machine Learning (ML) capabilities in attack detection. This study proposes to improve the efficiency of the SF SCADA network through a reliable ML detection technique. Specifically, Hyperparameter optimization of trees was lead for various optimizers for improving ML reliability. The Grid Search Optimizer improved the model by the combined advantage of training time and prediction speed. Hence, reliable for the improvement of ML in SF SCADA attack detection.
Love Allen Chijioke Ahakonye,Cosmas Ifeanyi Nwakanma,이재민,김동성 한국통신학회 2024 韓國通信學會論文誌 Vol.49 No.2
In Industrial Internet of Things (IIoT) environments, the reliability and adaptability of machine learning models are crucial for accurate decision-making. This paper introduces the Characteristic Stability Index (CSI) to monitor and ensure the stability of models in the context of heterogeneous IIoT sensor data. The CSI quantifies the variations in feature importance rankings, enabling the early detection of data drift and shifts. The experimentation results validate the performance of the decision tree algorithm to provide actionable insights, facilitating domain experts’ adaptability and enhancing decision-making while minimizing operational risks and costs in the choice of intrusion detection systems model.
Anomaly Detection of Malicious Energy Usage in Smart Factories using Deep Neural Network
Love Allen Chijioke Ahakonye,Cosmas Ifeanyi Nwakanma,Jae Min Lee,Dong-Seong Kim 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.6
In Smart Factory, an extensive volume of data is generated daily by Advanced Metering Infrastructures (AMI) and Smart Sensors. One such data is the amount of energy usage and the need to keep track of normal and abnormal energy usage in the smart factory. This allows energy producers to uncover abnormal power consumption as well as realizing distinct malicious energy usage. Recognition of abnormal conducts is essential to predict the unusual occurrence and to enhance energy productivity. This work proposes the Long Short-Term Memory (LSTM) Network to accurately recognize malicious energy usage in a smart factory. The proposed system is implemented using Python on Google collaborate with Tanh activation function. The performance of the proposed scheme showed 99.92%, 99.98%, 99.92%, and 99.85% for accuracy, precision, F1-Score, and recall respectively.
Deep Learning Anomaly Detection in Additive Manufacturing Process of a Smart Factory
Love Allen Chijioke Ahakonye,Cosmas Ifeanyi Nwakanma,Made Adi Paramartha Putra,Mark Verana,Khurboev Shakhzodbek,Jae Min Lee,Dong-Seong Kim 한국통신학회 2022 한국통신학회 학술대회논문집 Vol.2022 No.2
Efficient monitoring of production process is vital in the Smart Factory to forestall wastage. This study presents a deep learning technique for real-time detection of anomaly in the additive production process. You Look Only Once version 5 (YOLOv5) scheme is used in the monitoring of the 3D Printing process. The evaluation shows that the technique can identify and analyze anomaly with high prediction accuracy in real-time.