• Journal of Convergence for Information Technology
• /
• v.11 no.7
• /
• pp.31-38
• /
• 2021

In this paper, in order to obtain the optimization of the RNN model used for sentiment analysis, the correlation of each model was studied by observing the trend of loss and accuracy according to hyperparameter tuning. As a research method, after configuring the hidden layer with LSTM and the embedding layer that are most optimized to process sequential data, the loss and accuracy of each model were measured by tuning the unit, batch-size, and embedding size of the LSTM. As a result of the measurement, the loss was 41.9% and the accuracy was 11.4%, and the trend of the optimization model showed a consistently stable graph, confirming that the tuning of the hyperparameter had a profound effect on the model. In addition, it was confirmed that the decision of the embedding size among the three hyperparameters had the greatest influence on the model. In the future, this research will be continued, and research on an algorithm that allows the model to directly find the optimal hyperparameter will continue.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.146-151
• /
• 2021

Currently, the demand for vehicles from one family is increasing in many countries at home and abroad, reducing the number of people on the vehicle and increasing the number of vehicles on the road. The multi-passenger lane system, which is available to solve the problem of traffic congestion, is being implemented. The system allows police to monitor fast-moving vehicles with their own eyes to crack down on illegal vehicles, which is less accurate and accompanied by the risk of accidents. To address these problems, applying deep learning object recognition techniques using images from road sites will solve the aforementioned problems. Therefore, in this paper, we compare and analyze the performance of existing deep learning models, select a deep learning model that can identify real-time vehicle occupants through video, and propose a vehicle occupancy detection algorithm that complements the object-ident model's problems.

• Journal of Radiation Protection and Research
• /
• v.45 no.4
• /
• pp.171-177
• /
• 2020

Background: This study aims to determine the effective atomic number (Zeff) from dual-energy image sets obtained using a conventional computed tomography (CT) simulator. The estimated Zeff can be used for deriving the stopping power and material decomposition of CT images, thereby improving dose calculations in radiation therapy. Materials and Methods: An electron-density phantom was scanned using Philips Brilliance CT Big Bore at 80 and 140 kVp. The estimated Zeff values were compared with those obtained using the calibration phantom by applying the Rutherford, Schneider, and Joshi methods. The fitting parameters were optimized using the nonlinear least squares regression algorithm. The fitting curve and mass attenuation data were obtained from the National Institute of Standards and Technology. The fitting parameters obtained from stopping power and material decomposition of CT images, were validated by estimating the residual errors between the reference and calculated Zeff values. Next, the calculation accuracy of Zeff was evaluated by comparing the calculated values with the reference Zeff values of insert plugs. The exposure levels of patients under additional CT scanning at 80, 120, and 140 kVp were evaluated by measuring the weighted CT dose index (CTDIw). Results and Discussion: The residual errors of the fitting parameters were lower than 2%. The best and worst Zeff values were obtained using the Schneider and Joshi methods, respectively. The maximum differences between the reference and calculated values were 11.3% (for lung during inhalation), 4.7% (for adipose tissue), and 9.8% (for lung during inhalation) when applying the Rutherford, Schneider, and Joshi methods, respectively. Under dual-energy scanning (80 and 140 kVp), the patient exposure level was approximately twice that in general single-energy scanning (120 kVp). Conclusion: Zeff was calculated from two image sets scanned by conventional single-energy CT simulator. The results obtained using three different methods were compared. The Zeff calculation based on single-energy exhibited appropriate feasibility.

• Journal of Microbiology and Biotechnology
• /
• v.32 no.2
• /
• pp.149-159
• /
• 2022

Cancers of the lung and liver are the top 10 leading causes of cancer death worldwide. Thus, it is essential to identify the genes specifically expressed in these two cancer types to develop new therapeutics. Although many messenger RNA (mRNA) sequencing data related to these cancer cells are available due to the advancement of next-generation sequencing (NGS) technologies, optimized data processing methods need to be developed to identify the novel cancer-specific genes. Here, we conducted an analytical comparison between Bowtie2, a Burrows-Wheeler transform-based alignment tool, and Kallisto, which adopts pseudo alignment based on a transcriptome de Bruijn graph using mRNA sequencing data on normal cells and lung/liver cancer tissues. Before using cancer data, simulated mRNA sequencing reads were generated, and the high Transcripts Per Million (TPM) values were compared. mRNA sequencing reads data on lung/liver cancer cells were also extracted and quantified. While Kallisto could directly give the output in TPM values, Bowtie2 provided the counts. Thus, TPM values were calculated by processing the Sequence Alignment Map (SAM) file in R using package Rsubread and subsequently in python. The analysis of the simulated sequencing data revealed that Kallisto could detect more transcripts and had a higher overlap over Bowtie2. The evaluation of these two data processing methods using the known lung cancer biomarkers concludes that in standard settings without any dedicated quality control, Kallisto is more effective at producing faster and more accurate results than Bowtie2. Such conclusions were also drawn and confirmed with the known biomarkers specific to liver cancer.

• Journal of information and communication convergence engineering
• /
• v.20 no.1
• /
• pp.22-30
• /
• 2022

The reinforcement learning algorithm has proven its potential in solving sequential decision-making problems under uncertainties, such as finding paths to route data packets in wireless sensor networks. With reinforcement learning, the computation of the optimum path requires careful definition of the so-called reward function, which is defined as a linear function that aggregates multiple objective functions into a single objective to compute a numerical value (reward) to be maximized. In a typical defined linear reward function, the multiple objectives to be optimized are integrated in the form of a weighted sum with fixed weighting factors for all learning agents. This study proposes a reinforcement learning -based routing protocol for wireless sensor network, where different learning agents prioritize different objective goals by assigning weighting factors to the aggregated objectives of the reward function. We assign appropriate weighting factors to the objectives in the reward function of a sensor node according to its hop-count distance to the sink node. We expect this approach to enhance the effectiveness of multi-objective reinforcement learning for wireless sensor networks with a balanced trade-off among competing parameters. Furthermore, we propose SDN (Software Defined Networks) architecture with multiple controllers for constant network monitoring to allow learning agents to adapt according to the dynamics of the network conditions. Simulation results show that our proposed scheme enhances the performance of wireless sensor network under varied conditions, such as the node density and traffic intensity, with a good trade-off among competing performance metrics.

• Mass Spectrometry Letters
• /
• v.13 no.1
• /
• pp.11-19
• /
• 2022

Although translational research is referred to clinical chemistry measures, correct weighting factors for linear and quadratic calibration curves with least-squares regression algorithm have not been carefully considered in bioanalytical assays yet. The objective of this study was to identify steroidogenic roles in preeclampsia and verify accuracy of quantitative results by comparing two different linear regression models with weighting factor of 1 and 1/x². A liquid chromatography-mass spectrometry (LC-MS)-based adrenal steroid assay was conducted to reveal metabolic signatures of preeclampsia in both serum and placenta samples obtained 15 preeclamptic patients and 17 age-matched control pregnant women (33.9 ± 4.2 vs. 32.8 ± 5.6 yr, respectively) at 34~36 gestational weeks. Percent biases in the unweighted model (w_i = 1) were inversely proportional to concentrations (-739.4 ~ 852.9%) while those of weighted regression (w_i = 1/x²) were < 18% for all variables. The optimized LC-MS combined with the weighted linear regression resulted in significantly increased maternal serum levels of pregnenolone, 21-deoxycortisol, and tetrahydrocortisone (P < 0.05 for all) in preeclampsia. Serum metabolic ratio of (tetrahydrocortisol + allo-tetrahydrocortisol) / tetrahydrocortisone indicating 11β-hydroxysteroid dehydrogenase type 2 was decreased (P < 0.005) in patients. In placenta, local concentrations of androstenedione were changed while its metabolic ratio to 17α-hydroxyprogesterone responsible for 17,20-lyase activity was significantly decreased in patients (P = 0.002). The current bioanalytical LC-MS assay with corrected weighting factor of 1/x² may provide reliable and accurate quantitative outcomes, suggesting altered steroidogenesis in preeclampsia patients at late gestational weeks in the third trimester.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.109-117
• /
• 2022

Most of real-world decision-making processes are used to optimize problems with many objectives of conflicting. Since the betterment of some objectives requires the sacrifice of other objectives, different objectives may not be optimized simultaneously. Consequently, Pareto solution can be considered as candidates of a solution with respect to a multi-objective optimization (MOP). Such problem involves two main procedures: finding Pareto solutions and choosing one solution among them. So-called multi-objective genetic algorithms have been proved to be effective for finding many Pareto solutions. In this study, we suggest a fitness evaluation method based on the achievement level up to the target value to improve the solution search performance by the multi-objective genetic algorithm. Using numerical examples and benchmark problems, we compare the proposed method, which considers the achievement level, with conventional Pareto ranking methods. Based on the comparison, it is verified that the proposed method can generate a highly convergent and diverse solution set. Most of the existing multi-objective genetic algorithms mainly focus on finding solutions, however the ultimate aim of MOP is not to find the entire set of Pareto solutions, but to choose one solution among many obtained solutions. We further propose an interactive decision-making process based on a visualized trade-off analysis that incorporates the satisfaction of the decision maker. The findings of the study will serve as a reference to build a multi-objective decision-making support system.

• International Journal of Computer Science & Network Security
• /
• v.22 no.12
• /
• pp.185-196
• /
• 2022

The Internet of Things (IoT) has become more and more widespread in recent years, thus attackers are placing greater emphasis on IoT environments. The IoT connects a large number of smart devices via wired and wireless networks that incorporate sensors or actuators in order to produce and share meaningful information. Attackers employed IoT devices as bots to assault the target server; however, because of their resource limitations, these devices are easily infected with IoT malware. The Distributed Denial of Service (DDoS) is one of the many security problems that might arise in an IoT context. DDOS attempt involves flooding a target server with irrelevant requests in an effort to disrupt it fully or partially. This worst practice blocks the legitimate user requests from being processed. We explored an intelligent intrusion detection system (IIDS) using a particular sort of machine learning, such as Artificial Neural Networks, (ANN) in order to handle and mitigate this type of cyber-attacks. In this research paper Feed-Forward Neural Network (FNN) is tested for detecting the DDOS attacks using a modified version of the KDD Cup 99 dataset. The aim of this paper is to determine the performance of the most effective and efficient Back-propagation algorithms among several algorithms and check the potential capability of ANN- based network model as a classifier to counteract the cyber-attacks in IoT environments. We have found that except Gradient Descent with Momentum Algorithm, the success rate obtained by the other three optimized and effective Back- Propagation algorithms is above 99.00%. The experimental findings showed that the accuracy rate of the proposed method using ANN is satisfactory.

• Journal of Information Technology Services
• /
• v.22 no.4
• /
• pp.97-110
• /
• 2023

In this study, we propose a technique to automatically generate transfer documents using sensor data from livestock manure transfer systems. The research involves analyzing sensor data and applying machine learning techniques to derive optimized outcomes for livestock manure transfer documents. By comparing and contrasting with existing documents, we present a method for automatic document generation. Specifically, we propose the utilization of Gradient Boosting, a machine learning algorithm. The objective of this research is to enhance the efficiency of livestock manure and liquid byproduct management. Currently, stakeholders including producers, transporters, and processors manually input data into the livestock manure transfer management system during the disposal of manure and liquid byproducts. This manual process consumes additional labor, leads to data inconsistency, and complicates the management of distribution and treatment. Therefore, the aim of this study is to leverage data to automatically generate transfer documents, thereby increasing the efficiency of livestock manure and liquid byproduct management. By utilizing sensor data from livestock manure and liquid byproduct transport vehicles and employing machine learning algorithms, we establish a system that automates the validation of transfer documents, reducing the burden on producers, transporters, and processors. This efficient management system is anticipated to create a transparent environment for the distribution and treatment of livestock manure and liquid byproducts.

• Journal of Advanced Navigation Technology
• /
• v.27 no.4
• /
• pp.365-373
• /
• 2023

Unmanned aerial vehicles are widely used in various fields, and real-time path replanning is a critical factor in enhancing the safety and efficiency of these devices. In this paper, we propose a real-time path replanning technique based on RRT* and LOSPO. The proposed technique first generates an initial path using the RRT* algorithm and then optimizes the path using LOSPO. Additionally, the optimized path can be converted into a trajectory that considers actual time and the dynamic limits of the aircraft. In this process, environmental changes and collision risks are detected in real-time, and the path is replanned as needed to maintain safe operation. This method has been verified through simulation-based experiments. The results of this paper make a significant contribution to the research on real-time path replanning for UAVs, and by applying this technique to various situations, the safety and efficiency of UAVs can be improved.