• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2701-2717
• /
• 2023

In this paper, a hybrid fuzzy-based method is suggested for determining India's best system for power generation. This suggested approach was created using a fuzzy-based combination of the Giza Pyramids Construction (GPC) and Recalling-Enhanced Recurrent Neural Network (RERNN). GPC is a meta-heuristic algorithm that deals with solutions for many groups of problems, whereas RERNN has selective memory properties. The evaluation of the current load requirements and production profile information system is the main objective of the suggested method. The Central Electricity Authority database, the Indian National Load Dispatch Centre, regional load dispatching centers, and annual reports of India were some of the sources used to compile the data regarding profiles of electricity loads, capacity factors, power plant generation, and transmission limits. The RERNN approach makes advantage of the ability to analyze the ideal power generation from energy data, however the optimization of RERNN factor necessitates the employment of a GPC technique. The proposed method was tested using MATLAB, and the findings indicate that it is effective in terms of accuracy, feasibility, and computing efficiency. The suggested hybrid system outperformed conventional models, achieving the top result of 93% accuracy with a shorter computation time of 6814 seconds.

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.673-687
• /
• 2023

Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.

• ETRI Journal
• /
• v.46 no.2
• /
• pp.227-237
• /
• 2024

This study proposes a novel, conditionally applied neural network technique to reduce the overall peak-to-average power ratio (PAPR) of an orthogonal frequency division multiplexing (OFDM) system while maintaining an acceptable bit error rate (BER) level. The main purpose of the proposed scheme is to adjust only those subcarriers whose peaks exceed a given threshold. In this respect, the developed C-ANN algorithm suppresses only the peaks of the targeted subcarriers by slightly shifting the locations of their corresponding frequency samples without affecting their phase orientations. In turn, this achieves a reasonable system performance by sustaining a tolerable BER. For practical reasons and to cover a wide range of application scenarios, the threshold for the subcarrier peaks was chosen to be proportional to the saturation level of the nonlinear power amplifier used to pass the generated OFDM blocks. Consequently, the optimal values of the factor controlling the peak threshold were obtained that satisfy both reasonable PAPR reduction and acceptable BER levels. Furthermore, the proposed system does not require a recovery process at the receiver, thus making the computational process less complex. The simulation results show that the proposed system model performed satisfactorily, attaining both low PAPR and BER for specific application settings using comparatively fewer computations.

• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.73-79
• /
• 2023

Cyber threats are evolving and becoming more sophisticated with the development of new technologies, and consequently the number of service failures caused by DDoS attacks are continually increasing. Recently, DDoS attacks have numerous types of service failures by applying a large amount of traffic to the domain address of a specific service or server. In this paper, after generating the data of the Syn Flooding attack, which is the representative attack type of bandwidth exhaustion attack, the data were compared and analyzed using Random Forest, Decision Tree, Multi-Layer Perceptron, and KNN algorithms for the effective detection of attacks, and the optimal algorithm was derived. Based on this result, it will be useful to use as a technique for the detection policy of Syn Flooding attacks.

• Journal of Chest Surgery
• /
• v.57 no.2
• /
• pp.225-229
• /
• 2024

Venovenous (VV) extracorporeal membrane oxygenation (ECMO) is a lifesaving technique for patients experiencing respiratory failure. When VV ECMO fails to provide adequate support despite optimal settings, alternative strategies may be employed. One option is to add another venous cannula to increase venous drainage, while another is to insert an additional arterial return cannula to assist cardiac function. Alternatively, a separate ECMO circuit can be implemented to function in parallel with the existing circuit. We present a case in which the parallel ECMO method was used in a 63-year-old man with respiratory failure due to coronavirus disease 2019, combined with cardiac dysfunction. We installed an additional venoarterial ECMO circuit alongside the existing VV ECMO circuit and successfully weaned the patient from both types of ECMO. In this report, we share our experience and discuss this method.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.8
• /
• pp.375-382
• /
• 2006

This paper is about how to identify emotional information and how to detect a specific emotion from speech signals. For emotion identification and detection task. we use long-term acoustic feature parameters and select the optimal Parameters using the feature selection technique based on F-score. We transform the conventional SVM into probabilistic output SVM for our emotion identification and detection system. In this paper we propose three approximation methods for log-likelihoods in a hypothesis test and compare the performance of those three methods. Experimental results using the SUSAS database showed the effectiveness of both feature selection and Probabilistic output SVM in the emotion identification task. The proposed methods could detect anger emotion with 91.3% correctness.

• Korean Journal of Construction Engineering and Management
• /
• v.25 no.3
• /
• pp.68-82
• /
• 2024

The planning stage of laser scanning is crucial for acquiring high-quality 3D source data. It involves assessing the target space's environment and formulating an effective measurement strategy. However, existing practices often overlook on-site conditions, with decisions on scanner deployment and scanning locations relying heavily on the operators' experience. This approach has resulted in frequent modifications to scanning locations and diminished 3D data quality. Previous research has explored the selection of optimal scanner locations and conducted preliminary reviews through simulation, but these methods have significant drawbacks. They fail to consider scanner inaccuracies, do not support the use of multiple scanners, rely on less accurate 2D drawings, and require specialized knowledge in 3D modeling and programming. This study introduces an optimization technique for laser scanning planning using 3D simulation to address these issues. By evaluating the accuracy of scan data from various laser scanners and their positioning for scanning a retaining wall structure in a small-scale building, this method aids in refining the laser scanning plan. It enhances the decision-making process for end-users by ensuring data quality and reducing the need for plan adjustments during the planning phase.

• Transactions of Materials Processing
• /
• v.33 no.1
• /
• pp.36-42
• /
• 2024

Additive manufacturing with 3XX austenitic stainless steels has been widely investigated during a decade due to its high strength, good corrosion resistance, and fair weldability. However, in recently, Ni price drastically increased due to the high demand of secondary battery for electric mobilities. Thus, it is essential to substitute the Ni with Mn for reducing stainless steels price. Meanwhile, the chemical composition changes in stainless steels not only affect to its properties but also change the optimal processing parameters during additive manufacturing. Therefore, it is necessary to optimize the processing parameters of each alloy for obtaining high-quality product using additive manufacturing. After processing optimization, mechanical properties and microstructure of the laser-powder bed fusion processed Fe-15Cr-7Ni-3Mn alloy were investigated in both room (298 K) and cryogenic (77 K) temperatures. Since the temperature reduction affects to the deformation mechanism transition, multi-scale microstructural characterization technique was conducted to reveal the deformation mechanism of each sample.

• Wind and Structures
• /
• v.38 no.2
• /
• pp.119-128
• /
• 2024

The aerodynamic damping is an essential factor that can considerably affect the dynamic response of the cable-stayed bridge induced by crosswind load. However, developing an accurate and efficient aerodynamic damping model is crucial for evaluating the crosswind load-induced response on cable-stayed bridges. Therefore, this study proposes a new method for identifying aerodynamic damping of the bridge structures under crosswind load using an extended Kalman filter (EKF) and the particle filter (PF) algorithm. The EKF algorithm is introduced to capture the aerodynamic damping ratio. PF technique is used to select the optimal spectral representation of the noise. The effectiveness and accuracy of the proposed solution were investigated through full-scale vibration measurement data of the crosswind-induced on the bridge's girder. The results show that the proposed solution can generate an efficient and robust estimation. The errors between the target and extracted values are around 0.01mm and 0.003^o, respectively, for the vertical and torsional motion. The relationship between the amplitude and the aerodynamic damping ratio is linear for small reduced wind velocity and nonlinear with the increasing value of the reduced wind velocity. Finally, the results show the influence of the level of noise.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.1
• /
• pp.151-160
• /
• 2024

Artificial Neural Networks that enabled Artificial Intelligence are being used in many fields. However, the application to mechanical structures has several problems and research is incomplete. One of the problems is that it is difficult to secure a large amount of data necessary for learning Artificial Neural Networks. In particular, it is important to detect and recognize external forces and forces for safety working and accident prevention of mechanical structures. This study examined the possibility by applying the Current Neural Network of Artificial Neural Networks to detect and recognize the load on the machine. Tens of thousands of data are required for general learning of Recurrent Neural Networks, and to secure large amounts of data, this paper derives load data from ANSYS structural analysis results and applies a stacked auto-encoder technique to secure the amount of data that can be learned. The usefulness of Stacked Auto-Encoder data was examined by comparing Stacked Auto-Encoder data and ANSYS data. In addition, in order to improve the accuracy of detection and recognition of load data with a Recurrent Neural Network, the optimal conditions are proposed by investigating the effects of related functions.