• Journal of Korea Water Resources Association
• /
• v.55 no.spc1
• /
• pp.1283-1293
• /
• 2022

The purpose of this study is to predict residual chlorine in order to maintain stable residual chlorine concentration in sedimentation basin by using artificial intelligence algorithms in water treatment process employing pre-chlorination. Available water quantity and quality data are collected and analyzed statistically to apply into mathematical multiple regression and artificial intelligence models including multi-layer perceptron neural network, random forest, long short term memory (LSTM) algorithms. Water temperature, turbidity, pH, conductivity, flow rate, alkalinity and pre-chlorination dosage data are used as the input parameters to develop prediction models. As results, it is presented that the random forest algorithm shows the most moderate prediction result among four cases, which are long short term memory, multi-layer perceptron, multiple regression including random forest. Especially, it is result that the multiple regression model can not represent the residual chlorine with the input parameters which varies independently with seasonal change, numerical scale and dimension difference between quantity and quality. For this reason, random forest model is more appropriate for predict water qualities than other algorithms, which is classified into decision tree type algorithm. Also, it is expected that real time prediction by artificial intelligence models can play role of the stable operation of residual chlorine in water treatment plant including pre-chlorination process.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.5
• /
• pp.163-171
• /
• 2024

This study applies neural network analysis techniques to examine the factors influencing the purchasing decisions of fashion eyewear among women in their 30s and 40s, comparing these findings with traditional parametric analysis methods. In the fashion area, machine learning techniques are utilized for personalized fashion recommendation systems. However, research on such applications in Korea remains insufficient. By reanalyzing a study conducted in 2017 using traditional quantitative methods with these new techniques, this study aims to confirm the utility of neural network methods. Notably, the study finds that the classification accuracy of preferred sunglasses design is highest, at 86.2%, when the L-BFGS-B neural network is activated using the hyperbolic tangent function. The most critical factors influencing purchasing decisions were consumers' occupations and their pursuit of new styles. It is interpreted that Korean sunglasses consumers prefer "safe changes." These findings are consistent for selecting both the frames and lenses of sunglasses. Traditional quantitative analysis suggests that the type of sunglasses preferred varies according to the group to which a consumer belongs. In contrast, neural network analysis predicts the preferred sunglasses for each individual, thereby facilitating the development of personalized sunglasses recommendation systems.

• Structural Monitoring and Maintenance
• /
• v.1 no.3
• /
• pp.249-271
• /
• 2014

This paper presents a unique study of Structural Health Monitoring (SHM) for the maintenance decision making about a real life movable bridge. The mechanical components of movable bridges are maintained on a scheduled basis. However, it is desired to have a condition-based maintenance by taking advantage of SHM. The main objective is to track the operation of a gearbox and a rack-pinion/open gear assembly, which are critical parts of bascule type movable bridges. Maintenance needs that may lead to major damage to these components needs to be identified and diagnosed timely since an early detection of faults may help avoid unexpected bridge closures or costly repairs. The fault prediction of the gearbox and rack-pinion/open gear is carried out using two types of Artificial Neural Networks (ANNs): 1) Multi-Layer Perceptron Neural Networks (MLP-NNs) and 2) Fuzzy Neural Networks (FNNs). Monitoring data is collected during regular opening and closing of the bridge as well as during artificially induced reversible damage conditions. Several statistical parameters are extracted from the time-domain vibration signals as characteristic features to be fed to the ANNs for constructing the MLP-NNs and FNNs independently. The required training and testing sets are obtained by processing the acceleration data for both damaged and undamaged condition of the aforementioned mechanical components. The performances of the developed ANNs are first evaluated using unseen test sets. Second, the selected networks are used for long-term condition evaluation of the rack-pinion/open gear of the movable bridge. It is shown that the vibration monitoring data with selected statistical parameters and particular network architectures give successful results to predict the undamaged and damaged condition of the bridge. It is also observed that the MLP-NNs performed better than the FNNs in the presented case. The successful results indicate that ANNs are promising tools for maintenance monitoring of movable bridge components and it is also shown that the ANN results can be employed in simple approach for day-to-day operation and maintenance of movable bridges.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.4
• /
• pp.60-68
• /
• 1994

In this paper we propose a new Hybrid learning rule applied to multilayer feedforward neural networks, which is constructed by combining Hebbian learning rule that is a good feature extractor and Back-Propagation(BP) learning rule that is an excellent classifier. Unlike the BP rule used in multi-layer perceptron(MLP), the proposed Hybrid learning rule is used for uptate of all connection weights except for output connection weigths becase the Hebbian learning in output layer does not guarantee learning convergence. To evaluate the performance, the proposed hybrid rule is applied to classifier problems in two dimensional space and shows better performance than the one applied only by the BP rule. In terms of learning speed the proposed rule converges faster than the conventional BP. For example, the learning of the proposed Hybrid can be done in 2/10 of the iterations that are required for BP, while the recognition rate of the proposed Hybrid is improved by about $0.778\%$ at the peak.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.527-536
• /
• 2020

It has been found that an attacker can extract the secret key embedded in a security device and recover the operation instruction using power consumption traces which are some kind of side channel information. Many profiling-based side channel attacks based on a deep learning model such as MLP(Multi-Layer Perceptron) method are recently researched. In this paper, we implemented a disassembler for operation instruction set used in the micro-controller AVR XMEGA128-D4. After measuring the template traces on each instruction, we automatically made the pre-processing process and classified the operation instruction set using a deep learning model CNN. As an experimental result, we showed that all instructions are classified with 87.5% accuracy and some core instructions used frequently in device operation are with 99.6% respectively.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.5
• /
• pp.338-342
• /
• 2007

In this paper we propose a user adaptive post-processing method to improve the accuracy of speaker dependent, isolated word speech recognition, particularly for mobile devices. Our method considers the recognition result of the basic recognizer simply as a high-level speech feature and processes it further for correct recognition result. Our method learns correlation between the output of the basic recognizer and the correct final results and uses it to correct the erroneous output of the basic recognizer. A multi-layer perceptron model is built for each incorrectly recognized word with high frequency. As the result of experiments, we achieved a significant improvement of 41% in recognition accuracy (41% error correction rate).

• Proceedings of the KOSOMBE Conference
• /
• v.1990 no.05
• /
• pp.33-37
• /
• 1990

In this paper, a new method for lung area segmentation in chest radiographs has been presented. The movivation of this study is to include fuzzy informations about the relation between the image date structure and the area to be segmented in the segmentation process efficiently. The proposed method approached the segmentation problem in the perspective of pattern classification, using trainable pattern classifier, multi-layer perceptron. Having been trained with 10 samples, this method gives acceptable segmentation results, and also demonstrated the desirable property of giving better results as the training continues with more training samples.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.3
• /
• pp.163-171
• /
• 2016

Lane detection is a widely researched topic. Although simple road detection is easily achieved by previous methods, lane detection becomes very difficult in several complex cases involving noisy edges. To address this, we use a Convolution neural network (CNN) for image enhancement. CNN is a deep learning method that has been very successfully applied in object detection and recognition. In this paper, we introduce a robust lane detection method based on a CNN combined with random sample consensus (RANSAC) algorithm. Initially, we calculate edges in an image using a hat shaped kernel, then we detect lanes using the CNN combined with the RANSAC. In the training process of the CNN, input data consists of edge images and target data is images that have real white color lanes on an otherwise black background. The CNN structure consists of 8 layers with 3 convolutional layers, 2 subsampling layers and multi-layer perceptron (MLP) of 3 fully-connected layers. Convolutional and subsampling layers are hierarchically arranged to form a deep structure. Our proposed lane detection algorithm successfully eliminates noise lines and was found to perform better than other formal line detection algorithms such as RANSAC

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2002.11a
• /
• pp.445-453
• /
• 2002

Past and current customer behavior is the best predicator of future customer behavior. This paper introduces a procedure on personalized defection detection and prevention for an online game site. The basic idea for our defection detection and prevention is adopted from the observation that potential defectors have a tendency to take a couple of months or weeks to gradually change their behavior (i.e. trim-out their usage volume) before their eventual withdrawal. For this purpose, we suggest a SOM (Self-Organizing Map) based procedure to determine the possible states of customer behavior from past behavior data. Based on this representation of the state of behavior, potential defectors are detected by comparing their monitored trajectories of behavior states with frequent and confident trajectories of past defectors. The key feature of this study includes a defection prevention procedure which recommends the desirable behavior state for the ext period so as to lower the likelihood of defection. The defection prevention procedure can be used to design a marketing campaign on an individual basis because it provides desirable behavior patterns for the next period. The experiments demonstrate that our approach is effective for defection prevention and efficient for defection detection because it predicts potential defectors without deterioration of prediction accuracy compared to that of the MLP (Multi-Layer Perceptron) neural network.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.2948-2963
• /
• 2015

In the field of computer vision, visual surveillance systems have recently become an important research topic. Growth in this area is being driven by both the increase in the availability of inexpensive computing devices and image sensors as well as the general inefficiency of manual surveillance and monitoring. In particular, the ultimate goal for many visual surveillance systems is to provide automatic activity recognition for events at a given site. A higher level of understanding of these activities requires certain lower-level computer vision tasks to be performed. So in this paper, we propose an intelligent activity recognition model that uses a structure learning method and a classification method. The structure learning method is provided as a K2-learning algorithm that generates Bayesian networks of causal relationships between sensors for a given activity. The statistical characteristics of the sensor values and the topological characteristics of the generated graphs are learned for each activity, and then a neural network is designed to classify the current activity according to the features extracted from the multiple sensor values that have been collected. Finally, the proposed method is implemented and tested by using PETS2013 benchmark data.