• Journal of Veterinary Science
• /
• v.23 no.4
• /
• pp.60.1-60.6
• /
• 2022

Background: A definite diagnosis should be made in the bovine practice field, however, it was difficult to perform laboratory analysis immediately. Currently, three types of portable blood gas analyzers are available in Korea. Objectives: This study aimed to evaluate the correlations among these three analyzers. Methods: Seventy-two plasma samples from Holstein-Friesian cows were used for blood gas analysis, and three instruments (EDAN i15 Vet, VETSCAN i-STAT, and EPOC) were operated simultaneously. Moreover, plasma calcium levels were compared between these portable analyzers and blood chemistry device, which is usually used in a laboratory environment. Pearson analysis was performed to confirm the correlation of each parameter produced with the three instruments and blood chemistry analyzer. Results: As results, high correlation was observed in parameters of pH, pO₂, potassium ion, ionized calcium, and glucose (p < 0.001, r > 0.7). In addition, pCO₂ showed a moderate correlation among the three analyzers (p < 0.001, r > 0.5), and there was no correlation among all instruments for sodium ions. There was also a high correlation between ionized calcium from the three portable devices and total calcium from the biochemistry analyzer (p < 0.001, r > 0.9). Conclusions: In conclusion, there was a high correlation between results from the three different blood gas analyzers used in the bovine clinical field in Korea. Thus, a consistent diagnosis can be made even with different equipment if the operator is aware of the strengths and weaknesses of each piece of equipment and operates it properly.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.5
• /
• pp.395-401
• /
• 2023

Sound Event Detection (SED) aims to identify not only sound category but also time interval for target sounds in an audio waveform. It is a critical technique in field of acoustic surveillance system and monitoring system. Recently, various models have introduced through Detection and Classification of Acoustic Scenes and Events (DCASE) Task 4. This paper explored how to design optimal parameters of DenseNet based model, which has led to outstanding performance in other recognition system. In experiment, DenseRNN as an SED model consists of DensNet-BC and bi-directional Gated Recurrent Units (GRU). This model is trained with Mean teacher model. With an event-based f-score, evaluation is performed depending on parameters, related to model architecture as well as model training, under the assessment protocol of DCASE task4. Experimental result shows that the performance goes up and has been saturated to near the best. Also, DenseRNN would be trained more effectively without dropout technique.

• Journal of radiological science and technology
• /
• v.46 no.4
• /
• pp.277-285
• /
• 2023

In this study, pneumonia identification networks with the small number of layers were constructed by using chest X-ray images. The networks had similar trainable-parameters, and the performance of the trained models was quantitatively evaluated with the modification of the network architectures. A total of 6 networks were constructed: convolutional neural network (CNN), VGGNet, GoogleNet, residual network with identity blocks, ResNet with bottleneck blocks and ResNet with identity and bottleneck blocks. Trainable parameters for the 6 networks were set in a range of 273,921-294,817 by adjusting the output channels of convolution layers. The network training was implemented with binary cross entropy (BCE) loss function, sigmoid activation function, adaptive moment estimation (Adam) optimizer and 100 epochs. The performance of the trained models was evaluated in terms of training time, accuracy, precision, recall, specificity and F1-score. The results showed that the trained models with the small number of layers precisely detect pneumonia from chest X-ray images. In particular, the overall quantitative performance of the trained models based on the ResNets was above 0.9, and the performance levels were similar or superior to those based on the CNN, VGGNet and GoogleNet. Also, the residual blocks affected the performance of the trained models based on the ResNets. Therefore, in this study, we demonstrated that the object detection networks with the small number of layers are suitable for detecting pneumonia using chest X-ray images. And, the trained models based on the ResNets can be optimized by applying appropriate residual-blocks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1433-1449
• /
• 2023

In recent years, the rapid development of social networks has led to a rapid increase in the amount of information available on the Internet, which contains a large amount of sensitive information related to pornography, politics, and terrorism. In the aspect of sensitive image detection, the existing machine learning algorithms are confronted with problems such as large model size, long training time, and slow detection speed when auditing and supervising. In order to detect sensitive images more accurately and quickly, this paper proposes a multiclassification sensitive image detection method based on lightweight Convolutional Neural Network. On the basis of the EfficientNet model, this method combines the Ghost Module idea of the GhostNet model and adds the SE channel attention mechanism in the Ghost Module for feature extraction training. The experimental results on the sensitive image data set constructed in this paper show that the accuracy of the proposed method in sensitive information detection is 94.46% higher than that of the similar methods. Then, the model is pruned through an ablation experiment, and the activation function is replaced by Hard-Swish, which reduces the parameters of the original model by 54.67%. Under the condition of ensuring accuracy, the detection time of a single image is reduced from 8.88ms to 6.37ms. The results of the experiment demonstrate that the method put forward has successfully enhanced the precision of identifying multi-class sensitive images, significantly decreased the number of parameters in the model, and achieved higher accuracy than comparable algorithms while using a more lightweight model design.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.8
• /
• pp.85-92
• /
• 2024

In this paper presents a comparative analysis of the performance between the latest object detection model, YOLOv10, and its previous versions. YOLOv10 introduces NMS-Free training, an enhanced model architecture, and an efficiency-centric design, resulting in outstanding performance. Experimental results using the COCO dataset demonstrate that YOLOv10-N maintains high accuracy of 39.5% and low latency of 1.84ms, despite having only 2.3M parameters and 6.7G floating-point operations (FLOPs). The key performance metrics used include the number of model parameters, FLOPs, average precision (AP), and latency. The analysis confirms the effectiveness of YOLOv10 as a real-time object detection model across various applications. Future research directions include testing on diverse datasets, further model optimization, and expanding application scenarios. These efforts aim to further enhance YOLOv10's versatility and efficiency.

• Journal of Biomedical Engineering Research
• /
• v.24 no.5
• /
• pp.465-471
• /
• 2003

The purpose of this research was to evaluate chronic stress using physiological parameters. Wistar rats were exposed to the sound stress for 14 days. Biosignals were acquired hourly. To develop a fuzzy inference system which can integrate physiological parameters. the parameters of the system were adjusted by the adaptive neuro-fuzzy inference system. Of the training dataset, input dataset was the physiological parameters from the biosignals and output dataset was the target values from the cortisol production. Physiological parameters were integrated using the fuzzy inference system. then 24-hour results were analyzed by the Cosinor method. Chronic stress was evaluated from the degree of circadian rhythm disturbance. Suppose that the degree of stress for initial rest period is 1. Then. the degree of stress after 14-day sound stress increased to 1.37, and increased to 1.47 after the 7-day recovery period. That is, the rat was exposed to 37%-increased amount of stress by the 14-day sound and did not recover after the 7-day recovery period.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.29 no.3
• /
• pp.177-182
• /
• 1993

In order to estimate the mesh selectivity master curves and the optimum mesh size, experiments were made by the cover net method with the cod-ends of the five different the opening mesh sizes(51.2mm, 70.2mm, 77.6mm, 88.0mm and 111.3mm). After that 163 hauling were performed and there by investigated, on the training vessel Saebada in the Southern Korean Sea and East China Sea from June 1991 to August 1992. In this report, the mesh selectivity master curves were fitted by using logistic function(S=1/(1+exp super(-(aR+b))), R=(L-L sub(0))/(M-M sub(0)) and the optimum mesh sizes were estimated from each master curve. In this case, a and b are the selection parameters, M is the mesh size of each experimental cod-end. L is body length, L sub(0) and M sub(0) is the distance from the coordinate origine to intersection of linear regression between 25% and 50% selection length. The results obtained are summarized as follows; 1. Trachurus japonicus: Mesh selectivity master curve parameters: a and b were 2. 25, -4.73 respectively and optimum mesh size was estimated to be 79.3mm. 2. Trichiurus lepturus: Mesh selectivity master curve parameters: a and b were 0.81, -3.17 respectively and optimum mesh size was estimated to be 64.5mm. 3. Photololigo edulis: Mesh selectivity master curve parameters: a and b were 1.30m, -4.10 respectively and optimum mesh size was estimated to be 89.9mm. 4. Todarodes pacificus: Mesh selectivity master curve parameters: a and b were 1. 35, -3.45 respectively and optimum mesh size was estimated to be 89.4mm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.9 no.5
• /
• pp.555-565
• /
• 1999

The optimal identification algorithm of fuzzy systems is presented for rule-based fuzzy modeling of nonlinear complex systems. Nonlinear systems are expressed using the identification of structure such as input variables and fuzzy input subspaces, and parameters of a fuzzy model. In this paper, the rule-based fuzzy modeling implements system structure and parameter identification using the fuzzy inference methods and hybrid structure combined with two types of optimization theories for nonlinear systems. Two types of inference methods of a fuzzy model are the simplified inference and linear inference. The proposed hybrid optimal identification algorithm is carried out using both a genetic algorithm and the improved complex method. Here, a genetic algorithm is utilized for determining initial parameters of membership function of premise fuzzy rules, and the improved complex method which is a powerful auto-tuning algorithm is carried out to obtain fine parameters of membership function. Accordingly, in order to optimize fuzzy model, we use the optimal algorithm with a hybrid type for the identification of premise parameters and standard least square method for the identification of consequence parameters of a fuzzy model. Also, an aggregate performance index with weighting factor is proposed to achieve a balance between performance results of fuzzy model produced for the training and testing data. Two numerical examples are used to evaluate the performance of the proposed model.

• Structural Engineering and Mechanics
• /
• v.83 no.3
• /
• pp.327-340
• /
• 2022

The Collapse Margin Ratio (CMR) is a notable index used for seismic assessment of the structures. As proposed by FEMA P695, a set of analyses including the Nonlinear Static Analysis (NSA), Incremental Dynamic Analysis (IDA), together with Fragility Analysis, which are typically time-taking and computationally unaffordable, need to be conducted, so that the CMR could be obtained. To address this issue and to achieve a quick and efficient method to estimate the CMR, the Artificial Neural Network (ANN), Response Surface Method (RSM), and Adaptive Neuro-Fuzzy Inference System (ANFIS) will be introduced in the current research. Accordingly, using the NSA results, an attempt was made to find a fast and efficient approach to derive the CMR. To this end, 5016 IDA analyses based on FEMA P695 methodology on 114 various Reinforced Concrete (RC) frames with 1 to 12 stories have been carried out. In this respect, five parameters have been used as the independent and desired inputs of the systems. On the other hand, the CMR is regarded as the output of the systems. Accordingly, a double hidden layer neural network with Levenberg-Marquardt training and learning algorithm was taken into account. Moreover, in the RSM approach, the quadratic system incorporating 20 parameters was implemented. Correspondingly, the Analysis of Variance (ANOVA) has been employed to discuss the results taken from the developed model. Additionally, the essential parameters and interactions are extracted, and input parameters are sorted according to their importance. Moreover, the ANFIS using Takagi-Sugeno fuzzy system was employed. Finally, all methods were compared, and the effective parameters and associated relationships were extracted. In contrast to the other approaches, the ANFIS provided the best efficiency and high accuracy with the minimum desired errors. Comparatively, it was obtained that the ANN method is more effective than the RSM and has a higher regression coefficient and lower statistical errors.

• Journal of Korea Water Resources Association
• /
• v.33 no.5
• /
• pp.537-550
• /
• 2000

In this study, Neural Networks models were used to forecast daily streamflow at Jindong station of the Nakdong River basin. Neural Networks models consist of CASE 1(5-5-1) and CASE 2(5-5-5-1). The criteria which separates two models is the number of hidden layers. Each model has Fletcher-Reeves Conjugate Gradient BackPropagation(FR-CGBP) and Scaled Conjugate Gradient BackPropagation(SCGBP) algorithms, which are better than original BackPropagation(BP) in convergence of global error and training tolerance. The data which are available for model training and validation were composed of wet, average, dry, wet+average, wet+dry, average+dry and wet+average+dry year respectively. During model training, the optimal connection weights and biases were determined using each data set and the daily streamflow was calculated at the same time. Except for wet+dry year, the results of training were good conditions by statistical analysis of forecast errors. And, model validation was carried out using the connection weights and biases which were calculated from model training. The results of validation were satisfactory like those of training. Daily streamflow forecasting using Neural Networks models were compared with those forecasted by Multiple Regression Analysis Mode(MRAM). Neural Networks models were displayed slightly better results than MRAM in this study. Thus, Neural Networks models have much advantage to provide a more sysmatic approach, reduce model parameters, and shorten the time spent in the model development.