• Journal of Internet Computing and Services
• /
• v.20 no.1
• /
• pp.1-10
• /
• 2019

Since big-data text mining extracts many features and data, clustering and classification can result in high computational complexity and low reliability of the analysis results. In particular, a term document matrix obtained through text mining represents term-document features, but produces a sparse matrix. We designed an advanced genetic algorithm (GA) to extract features in text mining for detection model. Term frequency inverse document frequency (TF-IDF) is used to reflect the document-term relationships in feature extraction. Through a repetitive process, a predetermined number of features are selected. And, we used the sparsity score to improve the performance of detection model. If a spam mail data set has the high sparsity, detection model have low performance and is difficult to search the optimization detection model. In addition, we find a low sparsity model that have also high TF-IDF score by using s(F) where the numerator in fitness function. We also verified its performance by applying the proposed algorithm to text classification. As a result, we have found that our algorithm shows higher performance (speed and accuracy) in attack mail classification.

• Food Science of Animal Resources
• /
• v.43 no.1
• /
• pp.73-84
• /
• 2023

Campylobacteriosis is a common cause of gastrointestinal disease. In this study, we suggest a general strategy of applying gold nanoparticles (AuNPs) in colorimetric biosensors to detect Campylobacter in chicken carcass. Polymerase chain reaction (PCR) was utilized for the amplification of the target genes, and the thiolated PCR products were collected. Following the blending of colloid AuNPs with PCR products, the thiol bound to the surface of AuNPs, forming AuNP-PCR products. The PCR products had a sufficient negative charge, which enabled AuNPs to maintain a dispersed formation under electrostatic repulsion. This platform presented a color change as AuNPs aggregate. It did not need additional time and optimization of pH for PCR amplicons to adhere to the AuNPs. The specificity of AuNPs of modified primer pairs for mapA from Campylobacter jejuni and ceuE from Campylobacter coli was activated perfectly (C. jejuni, p-value: 0.0085; C. coli, p-value: 0.0239) when compared to Salmonella Enteritidis and Escherichia coli as non-Campylobacter species. Likewise, C. jejuni was successfully detected from artificially contaminated chicken carcass samples. According to the sensitivity test, at least 15 ng/μL of Campylobacter PCR products or 1×10³ CFU/mL of cells in the broth was needed for the detection using the optical method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.5 no.4
• /
• pp.41-55
• /
• 1995

In this paper, an optimal idenfication method using fuzzy-neural networks is proposed for modeling of nonlinear complex systems. The proposed fuzzy-neural modeling implements system structure and parameter identification using the intelligent schemes together wlth optimization theory, linguistic fuzzy implication rules, and neural networks(NNs) from input and output data of processes. Inference type for this fuzzy-neural modeling is presented as simplified inference. To obtain optimal model, the learning rates and momentum coefficients of fuzzy-neural networks(FNNs) are tuned automatically using improved modified complex method and modified learning algorithm. For the purpose of its application to nonlinear processes, data for route choice of traffic problems and those for activateti sluge process of sewage treatment system are used for the purpose of evaluating the performance of the proposed fuzzy-neural network modeling. The results show that the proposed method can produce the intelligence model with higher accuracy than other works achieved previously.

• Journal of Digital Convergence
• /
• v.13 no.2
• /
• pp.127-133
• /
• 2015

In order for location information to deliver the collected information, it needs Sensor Nodes in an environment of Sensor Network. Each sensor sends data to a base station through the process of routing in a wireless sensor network environment. Therefore, Offering accurate location information is very important in a wireless sensor network environment. Most of existed routing methods save all the informations of nodes at the area of 1-hop. In order to save these informations, unnecessary wasted energy and traffics are generated. Routing Protocol proposed in this paper doesn't save node's location information, and doesn't exchange any periodic location information to reduce wasted energy. It includes transmission range of source nodes and nodes with the location information, however it doesn't include any nodes' routing near 1-hope distance.

• Earthquakes and Structures
• /
• v.17 no.5
• /
• pp.511-519
• /
• 2019

The concrete gravity dam is one of the most important parts of the nation's infrastructure. Besides the benefits, the dam also has some potentially catastrophic disasters related to the life of citizens directly. During the lifetime of service, some degradations in a dam may occur as consequences of operating conditions, environmental aspects and deterioration in materials from natural causes, especially from dynamic loads. Cumulative Absolute Velocity (CAV) plays a key role to assess the operational condition of a structure under seismic hazard. In previous researches, CAV is normally used in Nuclear Power Plant (NPP) fields, but there are no particular criteria or studies that have been made on dam structure. This paper presents a method to calculate the limitation of CAV for the Bohyeonsan Dam in Korea, where the critical Peak Ground Acceleration (PGA) is estimated from twelve sets of selected earthquakes based on High Confidence of Low Probability of Failure (HCLPF). HCLPF point denotes 5% damage probability with 95% confidence level in the fragility curve, and the corresponding PGA expresses the crucial acceleration of this dam. For determining the status of the dam, a 2D finite element model is simulated by ABAQUS. At first, the dam's parameters are optimized by the Minitab tool using the method of Central Composite Design (CCD) for increasing model reliability. Then the Response Surface Methodology (RSM) is used for updating the model and the optimization is implemented from the selected model parameters. Finally, the recorded response of the concrete gravity dam is compared against the results obtained from solving the numerical model for identifying the physical condition of the structure.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.28 no.4
• /
• pp.401-408
• /
• 2015

Conventional model updating methods for the structures have used global structural responses which are modal parameters obtained through vibration measurements. Although models updated by modal parameters estimate global structural responses accurately, they have difficulties to predict local responses for safety assesment of structural members. The safety of structural members in the structures has been evaluated through the stress estimation based on strain measurements. Thus, this study additionally uses measured strain responses of structural members to perform model updating besides modal parameters. In the proposed method, the objective functions are set to the differences of the global and local responses obtained from updated model and measurement and those functions are minimized by NSGA-II, one of the multi-objective optimization techniques. The strain responses predicted from updated model are used for safety assessment of the steel frame structures. The proposed method are verified by numerical and experimental studies through the impact hammer tests for a steel frame specimen.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.6
• /
• pp.98-105
• /
• 2003

We propose a new technique of deinterleaving multiple radar pulse sequences by means of genetic algorithm for threat identification in electronic warfare(EW) system. The conventional approaches based on histogram or continuous wavelet transform are so deterministic that they are subject to failing in detection of individual signal characteristics under real EW signal environment that suffers frequent signal missing, noise, and counter-EW signal. The proposed algorithm utilizes the probabilistic optimization procedure of genetic algorithm. This method, a time-of-arrival(TOA) only strategy, constructs an initial chromosome set using the difference of TOA. To evaluate the fitness of each gene, the defined pulse phase is considered. Since it is rare to meet with a single radar at a moment in EW field of combat, multiple solutions are to be derived in the final stage. Therefore it is designed to terminate genetic process at the prematured generation followed by a chromosome grouping. Experimental results for simulated and real radar signals show the improved performance in estimating both the number of radar and the pulse repetition interval.

• Korean journal of applied entomology
• /
• v.41 no.1
• /
• pp.49-53
• /
• 2002

Paenibacillus larvae is a gram-positive, spore-forming bacterium that is etiological agent for american foulbrood disease (AFB), which is the most severe disease in honey bee. To detect P. larvae from infected honeybee-comb or larvae, polyclonal antibody against whole bacterium was produced from guineapig and its specificity was evaluated. After optimization of ELISA-based detection system using these antibodies, a number of different P. larvae strains were analysed. Polyclonal antibody against P. larvae ATCC 25747 showed high affinity to most strains of P. larvae including P. larvae. strain ATCC 9545 (type strain), ATCC 25747 and other korean strain, SJl5 but exhibited no cross-reaction with other bacterial species. Additionally, this type of ELISA system was used for the detection of AFB in field-application The results have shown that this antibody could be useful for the rapid identification and monitoring of P. larvae in honeybee-comb.

• The Journal of the Korea Contents Association
• /
• v.21 no.8
• /
• pp.1-9
• /
• 2021

Deep learning in computer vision has made accelerated improvement over a short period but large-scale learning data and computing power are still essential that required time-consuming trial and error tasks are involved to derive an optimal network model. In this study, we propose a similar image classification performance improvement method based on CR (Confusion Rate) that considers only the characteristics of the data itself regardless of network optimization or data reinforcement. The proposed method is a technique that improves the performance of the deep learning model by calculating the CRs for images in a dataset with similar characteristics and reflecting it in the weight of the Loss Function. Also, the CR-based recognition method is advantageous for image identification with high similarity because it enables image recognition in consideration of similarity between classes. As a result of applying the proposed method to the Resnet18 model, it showed a performance improvement of 0.22% in HanDB and 3.38% in Animal-10N. The proposed method is expected to be the basis for artificial intelligence research using noisy labeled data accompanying large-scale learning data.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.3
• /
• pp.130-139
• /
• 2024

Artificial intelligence models are being used to detect facility anomalies using physics data such as vibration, current, and temperature for predictive maintenance in the manufacturing industry. Since the types of facility anomalies, such as facility defects and failures, anomaly detection methods using autoencoder-based unsupervised learning models have been mainly applied. Normal or abnormal facility conditions can be effectively classified using the reconstruction error of the autoencoder, but there is a limit to identifying facility anomalies specifically. When facility anomalies such as unbalance, misalignment, and looseness occur, the facility vibration frequency shows a pattern different from the normal state in a specific frequency range. This paper presents an N-segmentation anomaly detection method that performs anomaly detection by dividing the entire vibration frequency range into N regions. Experiments on nine kinds of anomaly data with different frequencies and amplitudes using vibration data from a compressor showed better performance when N-segmentation was applied. The proposed method helps materialize them after detecting facility anomalies.