• Korean Journal of Ecology and Environment
• /
• v.56 no.3
• /
• pp.268-279
• /
• 2023

Nowadays, artificial intelligence model approaches such as machine and deep learning have been widely used to predict variations of water quality in various freshwater bodies. In particular, many researchers have tried to predict the occurrence of cyanobacterial blooms in inland water, which pose a threat to human health and aquatic ecosystems. Therefore, the objective of this study were to: 1) review studies on the application of machine learning models for predicting the occurrence of cyanobacterial blooms and its metabolites and 2) prospect for future study on the prediction of cyanobacteria by machine learning models including deep learning. In this study, a systematic literature search and review were conducted using SCOPUS, which is Elsevier's abstract and citation database. The key results showed that deep learning models were usually used to predict cyanobacterial cells, while machine learning models focused on predicting cyanobacterial metabolites such as concentrations of microcystin, geosmin, and 2-methylisoborneol (2-MIB) in reservoirs. There was a distinct difference in the use of input variables to predict cyanobacterial cells and metabolites. The application of deep learning models through the construction of big data may be encouraged to build accurate models to predict cyanobacterial metabolites.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.119-128
• /
• 2022

Recently, due to the development of related technologies for autonomous vehicles, driving work is changing more safely. However, the development of support technologies for level 5 full autonomous driving is still insufficient. That is, even in the case of an autonomous vehicle, the driver needs to drive through forward attention while driving. In this paper, we propose a method to monitor driving tasks by recognizing driver behavior. The proposed method uses pre-trained deep convolutional neural network models to recognize whether the driver's face or body has unnecessary movement. The use of pre-trained Deep Convolitional Neural Network (DCNN) models enables high accuracy in relatively short time, and has the advantage of overcoming limitations in collecting a small number of driver behavior learning data. The proposed method can be applied to an intelligent vehicle safety driving support system, such as driver drowsy driving detection and abnormal driving detection.

• Korea Real Estate Review
• /
• v.27 no.3
• /
• pp.71-86
• /
• 2017

The purpose of this study was to apply the deep running method to real estate price index predicting and to compare it with the time series analysis method to test the possibility of its application to real estate market forecasting. Various real estate price indices were predicted using the DNN (deep neural networks) and LSTM (long short term memory networks) models, both of which draw on the deep learning method, and the ARIMA (autoregressive integrated moving average) model, which is based on the time seies analysis method. The results of the study showed the following. First, the predictive power of the deep learning method is superior to that of the time series analysis method. Second, among the deep learning models, the predictability of the DNN model is slightly superior to that of the LSTM model. Third, the deep learning method and the ARIMA model are the least reliable tools for predicting the housing sales prices index among the real estate price indices. Drawing on the deep learning method, it is hoped that this study will help enhance the accuracy in predicting the real estate market dynamics.

• Journal of Environmental Health Sciences
• /
• v.47 no.5
• /
• pp.462-471
• /
• 2021

Background: The number of synthesized chemicals has rapidly increased over the past decade. For many chemicals, there is a lack of information on toxicity. With the current movement toward reducing animal testing, the use of toxicity big data and deep learning could be a promising tool to screen potential toxicants. Objectives: This study identified potential chemicals related to reproductive and estrogen receptor (ER)-mediated toxicities for 1135 cleaning products and 886 laundry products. Methods: We listed chemicals contained in cleaning and laundry products from a publicly available database. Then, chemicals that potentially exhibited reproductive and ER-mediated toxicities were identified using the European Union Classification, Labeling and Packaging classification and ToxCast database, respectively. For chemicals absent from the ToxCast database, ER activity was predicted using deep learning models. Results: Among the 783 listed chemicals, there were 53 with potential reproductive toxicity and 310 with potential ER-mediated toxicity. Among the 473 chemicals not tested with ToxCast assays, deep learning models indicated that 42 chemicals exhibited ER-mediated toxicity. A total of 13 chemicals were identified as causing reproductive toxicity by reacting with the ER. Conclusions: We demonstrated a screening method to identify potential chemicals related to reproductive and ER-mediated toxicities utilizing chemical toxicity big data and deep learning. Integrating toxicity data from in vivo, in vitro, and deep learning models may contribute to screening chemicals in consumer products.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.319-325
• /
• 2023

In this study, we proposed a method for hyperparameter optimization in the building and training of a deep learning model designed to process point cloud data collected by a millimeter-wave radar system. The primary aim of this study is to facilitate the deployment of a baseline model in resource-constrained IoT devices. We evaluated a RadHAR baseline deep learning model trained on a public dataset composed of point clouds representing five distinct human activities. Additionally, we introduced a coarse-to-fine hyperparameter optimization procedure, showing substantial potential to enhance model efficiency without compromising predictive performance. Experimental results show the feasibility of significantly reducing model size without adversely impacting performance. Specifically, the optimized model demonstrated a 3.3% improvement in classification accuracy despite a 16.8% reduction in number of parameters compared th the baseline model. In conclusion, this research offers valuable insights for the development of deep learning models for resource-constrained IoT devices, underscoring the potential of hyperparameter optimization and model size reduction strategies. This work contributes to enhancing the practicality and usability of deep learning models in real-world environments, where high levels of accuracy and efficiency in data processing and classification tasks are required.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.31-41
• /
• 2024

Deep learning models show excellent performance in tasks such as image classification and object detection in the field of computer vision, and are used in various ways in actual industrial sites. Recently, research on improving robustness has been actively conducted, along with pointing out that this deep learning model is vulnerable to hostile examples. A hostile example is an image in which small noise is added to induce misclassification, and can pose a significant threat when applying a deep learning model to a real environment. In this paper, we tried to confirm the robustness of the edge-learning classification model and the performance of the adversarial example detection model using it for adversarial examples of various algorithms. As a result of robustness experiments, the basic classification model showed about 17% accuracy for the FGSM algorithm, while the edge-learning models maintained accuracy in the 60-70% range, and the basic classification model showed accuracy in the 0-1% range for the PGD/DeepFool/CW algorithm, while the edge-learning models maintained accuracy in 80-90%. As a result of the adversarial example detection experiment, a high detection rate of 91-95% was confirmed for all algorithms of FGSM/PGD/DeepFool/CW. By presenting the possibility of defending against various hostile algorithms through this study, it is expected to improve the safety and reliability of deep learning models in various industries using computer vision.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.1-17
• /
• 2017

The deep learning framework is software designed to help develop deep learning models. Some of its important functions include "automatic differentiation" and "utilization of GPU". The list of popular deep learning framework includes Caffe (BVLC) and Theano (University of Montreal). And recently, Microsoft's deep learning framework, Microsoft Cognitive Toolkit, was released as open-source license, following Google's Tensorflow a year earlier. The early deep learning frameworks have been developed mainly for research at universities. Beginning with the inception of Tensorflow, however, it seems that companies such as Microsoft and Facebook have started to join the competition of framework development. Given the trend, Google and other companies are expected to continue investing in the deep learning framework to bring forward the initiative in the artificial intelligence business. From this point of view, we think it is a good time to compare some of deep learning frameworks. So we compare three deep learning frameworks which can be used as a Python library. Those are Google's Tensorflow, Microsoft's CNTK, and Theano which is sort of a predecessor of the preceding two. The most common and important function of deep learning frameworks is the ability to perform automatic differentiation. Basically all the mathematical expressions of deep learning models can be represented as computational graphs, which consist of nodes and edges. Partial derivatives on each edge of a computational graph can then be obtained. With the partial derivatives, we can let software compute differentiation of any node with respect to any variable by utilizing chain rule of Calculus. First of all, the convenience of coding is in the order of CNTK, Tensorflow, and Theano. The criterion is simply based on the lengths of the codes and the learning curve and the ease of coding are not the main concern. According to the criteria, Theano was the most difficult to implement with, and CNTK and Tensorflow were somewhat easier. With Tensorflow, we need to define weight variables and biases explicitly. The reason that CNTK and Tensorflow are easier to implement with is that those frameworks provide us with more abstraction than Theano. We, however, need to mention that low-level coding is not always bad. It gives us flexibility of coding. With the low-level coding such as in Theano, we can implement and test any new deep learning models or any new search methods that we can think of. The assessment of the execution speed of each framework is that there is not meaningful difference. According to the experiment, execution speeds of Theano and Tensorflow are very similar, although the experiment was limited to a CNN model. In the case of CNTK, the experimental environment was not maintained as the same. The code written in CNTK has to be run in PC environment without GPU where codes execute as much as 50 times slower than with GPU. But we concluded that the difference of execution speed was within the range of variation caused by the different hardware setup. In this study, we compared three types of deep learning framework: Theano, Tensorflow, and CNTK. According to Wikipedia, there are 12 available deep learning frameworks. And 15 different attributes differentiate each framework. Some of the important attributes would include interface language (Python, C ++, Java, etc.) and the availability of libraries on various deep learning models such as CNN, RNN, DBN, and etc. And if a user implements a large scale deep learning model, it will also be important to support multiple GPU or multiple servers. Also, if you are learning the deep learning model, it would also be important if there are enough examples and references.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.74-89
• /
• 2022

Due to the unique recipes and processes of each company, not only differences among the results of dyeing textile materials exist but they are also difficult to predict. This study attempted to develop a color prediction model based on deep learning to optimize color realization in the dyeing process. For this purpose, deep learning-based models such as multilayer perceptron, CNN and LSTM models were selected. Three forecasting models were trained by collecting a total of 376 data sets. The three predictive models were compared and analyzed using the cross-validation method. The mean of the CMC (2:1) color difference for the prediction results of the LSTM model was found to be the best.

• International journal of advanced smart convergence
• /
• v.11 no.4
• /
• pp.10-19
• /
• 2022

AI-based Network Intrusion Detection Systems (AI-NIDS) detect network attacks using machine learning and deep learning models. Recently, unsupervised AI-NIDS methods are getting more attention since there is no need for labeling, which is crucial for building practical NIDS systems. This paper aims to test the impact of designing autoencoder models that can be applied to unsupervised an AI-NIDS in real network systems. We collected security events of legacy network security system and carried out an experiment. We report the results and discuss the findings.

• Journal of Information Processing Systems
• /
• v.20 no.2
• /
• pp.149-158
• /
• 2024

Traditional manual identification of crop leaf diseases is challenging. Owing to the limitations in manpower and resources, it is challenging to explore crop diseases on a large scale. The emergence of artificial intelligence technologies, particularly the extensive application of deep learning technologies, is expected to overcome these challenges and greatly improve the accuracy and efficiency of crop disease identification. Crop leaf disease identification models have been designed and trained using large-scale training data, enabling them to predict different categories of diseases from unlabeled crop leaves. However, these models, which possess strong feature representation capabilities, require substantial training data, and there is often a shortage of such datasets in practical farming scenarios. To address this issue and improve the feature learning abilities of models, this study proposes a deep transfer learning adaptation strategy. The novel proposed method aims to transfer the weights and parameters from pre-trained models in similar large-scale training datasets, such as ImageNet. ImageNet pre-trained weights are adopted and fine-tuned with the features of crop leaf diseases to improve prediction ability. In this study, we collected 16,060 crop leaf disease images, spanning 12 categories, for training. The experimental results demonstrate that an impressive accuracy of 98% is achieved using the proposed method on the transferred ResNet-50 model, thereby confirming the effectiveness of our transfer learning approach.