• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.21-31
• /
• 2023

In this paper, we focused on the problem of evaluating multi-class classification accuracy and simulation of multiple classifier performance metrics. Multi-class classifiers for sentiment analysis involved many challenges, whereas previous research narrowed to the binary classification model since it provides higher accuracy when dealing with text data. Thus, we take inspiration from the non-linear Support Vector Machine to modify the algorithm by embedding dynamic hyperplanes representing multiple class labels. Then we analyzed the performance of multi-class classifiers using macro-accuracy, micro-accuracy and several other metrics to justify the significance of our algorithm enhancement. Furthermore, we hybridized Enhanced Convolution Neural Network (ECNN) with Dynamic Support Vector Machine (DSVM) to demonstrate the effectiveness and efficiency of the classifier towards multi-class text data. We performed experiments on three hybrid classifiers, which are ECNN with Binary SVM (ECNN-BSVM), and ECNN with linear Multi-Class SVM (ECNN-MCSVM) and our proposed algorithm (ECNNDSVM). Comparative experiments of hybrid algorithms yielded 85.12 % for single metric accuracy; 86.95 % for multiple metrics on average. As for our modified algorithm of the ECNN-DSVM classifier, we reached 98.29 % micro-accuracy results with an f-score value of 98 % at most. For the future direction of this research, we are aiming for hyperplane optimization analysis.

• Journal of Biosystems Engineering
• /
• v.13 no.4
• /
• pp.46-55
• /
• 1988

The objective of this study was to develop a computer measurement and control system which enable it possible to manage the natural air rough rice drying and storage properly and safely. The following contents of work were taken in this study in order to fulfill the above goal: 1) Design and construction of measurement system which can measure the rough rice drying conditions automatically and transfer them to computer system for data processing. 2) Development of a management software which can determine the need of fan operation by the analysis of drying and/or storage conditions. 3) Design and construction of a control system which deliver the computer decision of fan operation and make it on and off. 4) Technical and economical analysis of the computer measurement and control system development by the comparison experiments of the computer management and of the manual.

• Journal of Biosystems Engineering
• /
• v.24 no.3
• /
• pp.195-208
• /
• 1999

A computer simulation was carried out to investigate draft characteristics of Korean paddy field for obtaining the basic reference to the selection of optimum moldboard type suitable for Korean paddy field conditions. Cylindrical, cylindroidal, semihelical moldboard plows, and one type of oriental Janggi were used for simulation. A series of soil bin experiments was conducted to compare the experimental results with the predicted drafts from computer simulation using the cylindroidal moldboard plow. The computer model predicted draft force with 1~12% error at 12~16cm plowing depth which is the most conventional plowing depth in the rural area in Korea. Thus, the computer model was considered to be good enough for simulation. Due to the different plowing width of experimental plows, specific draft was selected for comparison by computer simulations. Specific draft of cylindrical moldboard plow was ranged from 3 to 6 N/$\textrm{cm}^2$ according to the soil conditions, plowing speed and plowing depth, 2.5~3.0 N/$\textrm{cm}^2$ for semihelical moldboard plow.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.101-106
• /
• 2021

Breast cancer is the number one cause of deaths from cancer in women, knowing the type of breast cancer in the early stages can help us to prevent the dangers of the next stage. The performance of the deep learning depends on large number of labeled data, this paper presented convolutional neural network for classification breast cancer from images to benign or malignant. our network contains 11 layers and ends with softmax for the output, the experiments result using public BreakHis dataset, and the proposed methods outperformed the state-of-the-art methods.

• Journal of Advanced Navigation Technology
• /
• v.16 no.1
• /
• pp.1-7
• /
• 2012

In this research, a single-axis attitude control test bed is developed, and simulation and tests experiments are performed, as a preliminary research of a quad-rotor aerial vehicle development. A single-axis test bed with seesaw configuration is manufactured using two motors and propellers, and the aerodynamic parameters are derived by thrust tests. The response of the system is estimated with Matlab/Simulink, and experiments are performed with attitude control computer and an attitude sensor onboard the test bed. Comparing the results of simulated and tested data, factors of steady-state errors during experiments are found, and performances of used attitude control algorithm and the control computer were verified. In these process, essential preliminary data for attitude control of a quad-rotor unmanned aerial vehicle were acquired.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.374-388
• /
• 2022

Cloud computing has been one of the most critical technology in the last few decades. It has been invented for several purposes as an example meeting the user requirements and is to satisfy the needs of the user in simple ways. Since cloud computing has been invented, it had followed the traditional approaches in elasticity, which is the key characteristic of cloud computing. Elasticity is that feature in cloud computing which is seeking to meet the needs of the user's with no interruption at run time. There are traditional approaches to do elasticity which have been conducted for several years and have been done with different modelling of mathematical. Even though mathematical modellings have done a forward step in meeting the user's needs, there is still a lack in the optimisation of elasticity. To optimise the elasticity in the cloud, it could be better to benefit of Machine Learning algorithms to predict upcoming workloads and assign them to the scheduling algorithm which would achieve an excellent provision of the cloud services and would improve the Quality of Service (QoS) and save power consumption. Therefore, this paper aims to investigate the use of machine learning techniques in order to predict the workload of Physical Hosts (PH) on the cloud and their energy consumption. The environment of the cloud will be the school of computing cloud testbed (SoC) which will host the experiments. The experiments will take on real applications with different behaviours, by changing workloads over time. The results of the experiments demonstrate that our machine learning techniques used in scheduling algorithm is able to predict the workload of physical hosts (CPU utilisation) and that would contribute to reducing power consumption by scheduling the upcoming virtual machines to the lowest CPU utilisation in the environment of physical hosts. Additionally, there are a number of tools, which are used and explored in this paper, such as the WEKA tool to train the real data to explore Machine learning algorithms and the Zabbix tool to monitor the power consumption before and after scheduling the virtual machines to physical hosts. Moreover, the methodology of the paper is the agile approach that helps us in achieving our solution and managing our paper effectively.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.3
• /
• pp.121-133
• /
• 2012

In this paper, we propose a novel data analysis approach that extracts granules suitable for various perspectives by introducing scaling level into formal concept analysis in order to control the level of granularity. Based on our approach, we can extract various granules from the given data set and constructs granular concept hierarchies based on the relations between the granules. Therefore, we can classify the given data with respect to the purpose or the intention of user's viewpoints. And, we developed G-Tool that supports our approach. In order to verify the usefulness of our proposed approach and G-Tool, we have done some experiments for real data set and reported about results of our experiments. From the experiments' results, we can verify our approach with G-Tool can be useful and suitable for classifying the given data with various scaling levels. The traditional formal concept analysis cannot control the level of granularity and can only classify for a particular perspective. However, our proposed approach can classify the given data with respect to user's purpose or intention by combining of diverse scale information and scaling levels.

• Journal of Digital Convergence
• /
• v.15 no.7
• /
• pp.213-222
• /
• 2017

This paper proposes a new service design which is deep learning-based image retrieval system for product search on O2O shopping mall platform. We have implemented deep learning technology that provides more convenient retrieval service for diverse images of many products that are sold in the internet shopping malls. In order to implement this retrieval system, real data used by shopping mall companies were used as experimental data. However, result from several experiments have confirmed deterioration of retrieval performance due to data components. In order to improve the performance, the learning data that interferes with the retrieval is revised several times, and then the values of experimental result are quantified with the verification data. Using the numerical values of these experiments, we have applied them to the new service design in this system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1814-1828
• /
• 2021

Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from low-resolution. To reduce the noise of the enhanced image and improve the image quality, a super-resolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1310-1338
• /
• 2023

As Internet of Things (IoT) applications and devices rapidly grow, cyber-attacks on IoT networks/systems also have an increasing trend, thus increasing the threat to security and privacy. Botnet is one of the threats that dominate the attacks as it can easily compromise devices attached to an IoT networks/systems. The compromised devices will behave like the normal ones, thus it is difficult to recognize them. Several intelligent approaches have been introduced to improve the detection accuracy of this type of cyber-attack, including deep learning and machine learning techniques. Moreover, dimensionality reduction methods are implemented during the preprocessing stage. This research work proposes deep Autoencoder dimensionality reduction method combined with Artificial Neural Network (ANN) classifier as botnet detection system for IoT networks/systems. Experiments were carried out using 3- layer, 4-layer and 5-layer pre-processing data from the MedBIoT dataset. Experimental results show that using a 5-layer Autoencoder has better results, with details of accuracy value of 99.72%, Precision of 99.82%, Sensitivity of 99.82%, Specificity of 99.31%, and F1-score value of 99.82%. On the other hand, the 5-layer Autoencoder model succeeded in reducing the dataset size from 152 MB to 12.6 MB (equivalent to a reduction of 91.2%). Besides that, experiments on the N_BaIoT dataset also have a very high level of accuracy, up to 99.99%.