• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.77-90
• /
• 2023

Today, crops face many characteristics/diseases. Insect damage is one of the main characteristics/diseases. Insecticides are not always effective because they can be toxic to some birds. It will also disrupt the natural food chain for animals. A common practice of plant scientists is to visually assess plant damage (leaves, stems) due to disease based on the percentage of disease. Plants suffer from various diseases at any stage of their development. For farmers and agricultural professionals, disease management is a critical issue that requires immediate attention. It requires urgent diagnosis and preventive measures to maintain quality and minimize losses. Many researchers have provided plant disease detection techniques to support rapid disease diagnosis. In this review paper, we mainly focus on artificial intelligence (AI) technology, image processing technology (IP), deep learning technology (DL), vector machine (SVM) technology, the network Convergent neuronal (CNN) content Detailed description of the identification of different types of diseases in tomato and potato plants based on image retrieval technology (CBIR). It also includes the various types of diseases that typically exist in tomato and potato. Content-based Image Retrieval (CBIR) technologies should be used as a supplementary tool to enhance search accuracy by encouraging you to access collections of extra knowledge so that it can be useful. CBIR systems mainly use colour, form, and texture as core features, such that they work on the first level of the lowest level. This is the most sophisticated methods used to diagnose diseases of tomato plants.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.85-92
• /
• 2023

Deep learning applications are increasingly being leveraged for disease detection tasks in medical imaging modalities such as X-ray, Computed Tomography (CT), and Magnetic Resonance Imaging (MRI). Most data-centric deep learning challenges necessitate the use of supervised learning methodologies to attain high accuracy and to facilitate performance evaluation through comparison with the ground truth. Supervised learning mandates a substantial amount of image and label sets, however, procuring an adequate volume of medical imaging data for training is a formidable task. Various data augmentation strategies can mitigate the underfitting issue inherent in supervised learning-based models that are trained on limited medical image and label sets. This research investigates the enhancement of a deep learning-based rib fracture segmentation model and the efficacy of data augmentation techniques such as left-right flipping, rotation, and scaling. Augmented dataset with L/R flipping and rotations(30°, 60°) increased model performance, however, dataset with rotation(90°) and ⨯0.5 rescaling decreased model performance. This indicates the usage of appropriate data augmentation methods depending on datasets and tasks.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.4
• /
• pp.601-608
• /
• 2023

Mobile robots are widely used in industries because mobile robots perform tasks in various environments. In order to carry out tasks, determining the precise location of the robot in real-time is important due to the need for path generation and obstacle detection. In particular, when mobile robots autonomously navigate in indoor environments and carry out assigned tasks within pre-determined areas, highly precise positioning performance is required. However, mobile robots frequently experience data missing in wireless communication environments. The robots need to rely on predictive techniques to autonomously determine the mobile robot positions and continue performing mobile robot tasks. In this paper, we propose an extended Kalman filter-based algorithm to enhance the accuracy of mobile robot localization and address the issue of data missing. Trilateration algorithm relies on measurements taken at that moment, resulting in inaccurate localization performance. In contrast, the proposed algorithm uses residual values of predicted measurements in data missing environments, making precise mobile robot position estimation. We conducted simulations in terms of data missing to verify the superior performance of the proposed algorithm.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.87-93
• /
• 2023

In this paper, we propose a system that accurately and efficiently determines forward head posture based on network learning by analyzing the user's skeletal posture. Forward head posture syndrome is a condition in which the forward head posture is changed by keeping the neck in a bent forward position for a long time, causing pain in the back, shoulders, and lower back, and it is known that daily posture habits are more effective than surgery or drug treatment. Existing methods use convolutional neural networks using webcams, and these approaches are affected by the brightness, lighting, skin color, etc. of the image, so there is a problem that they are only performed for a specific person. To alleviate this problem, this paper extracts the skeleton from the image and learns the data corresponding to the side rather than the frontal view to find the forward head posture more efficiently and accurately than the previous method. The results show that the accuracy is improved in various experimental scenes compared to the previous method.

• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3140-3149
• /
• 2023

In theory, the sharp dose falloff at the distal end of a proton beam allows for high conformal dose to the target. However, conformity has not been fully achieved in practice, primarily due to beam range uncertainty, which is approximately 4% and varies slightly across institutions. To address this issue, we developed a new range verification system prototype: a multi-slit prompt-gamma camera (MSPGC). This system features high prompt-gamma detection sensitivity, an advanced range estimation algorithm, and a precise camera positioning system. We evaluated the range measurement precision of the prototype for single spot beams with varying energies, proton quantities, and positions, as well as for spot-scanning proton beams in a simulated SSPT treatment using a phantom. Our results demonstrated high accuracy (<0.4 mm) in range measurement for the tested beam energies and positions. Measurement precision increased significantly with the number of protons, achieving 1% precision with 5 × 10⁸ protons. For spot-scanning proton beams, the prototype ensured more than 5 × 10⁸ protons per spot with a 7 mm or larger spot aggregation, achieving 1% range measurement precision. Based on these findings, we anticipate that the clinical application of the new prototype will reduce range uncertainty (currently approximately 4%) to 1% or less.

• Journal of Sensor Science and Technology
• /
• v.32 no.2
• /
• pp.88-94
• /
• 2023

Recently, piezoelectric tactile sensors have garnered considerable attention in the field of texture recognition owing to their high sensitivity and high-frequency detection capability. Despite their remarkable potential, improving their mechanical flexibility to attach to complex surfaces remains challenging. In this study, we present a flexible piezoelectric sensor that can be bent to an extremely small radius of up to 2.5 mm and still maintain good electrical performance. The proposed sensor was fabricated by controlling the thickness that induces internal stress under external deformation. The fabricated piezoelectric sensor exhibited a high sensitivity of 9.3 nA/kPa ranging from 0 to 10 kPa and a wide frequency range of up to 1 kHz. To demonstrate real-time texture recognition by rubbing the surface of an object with our sensor, nine sets of fabric plates were prepared to reflect their material properties and surface roughness. To extract features of the objects from the detected sensing data, we converted the analog dataset to short-term Fourier transform images. Subsequently, texture recognition was performed using a convolutional neural network with a classification accuracy of 97%.

• Journal of the Korean Geosynthetics Society
• /
• v.22 no.1
• /
• pp.67-74
• /
• 2023

In order to monitor the stability of slopes, research on data-based slope failure prediction and early warning is increasing. However, most papers overlook the quality of data. Poor data quality can cause problems such as false alarms. Therefore, this paper proposes a two-step hybrid approach consisting of rules and machine learning models for quality control of data collected from slopes. The rule-based has the advantage of high accuracy and intuitive interpretation, and the machine learning model has the advantage of being able to derive patterns that cannot be explicitly expressed. The hybrid approach was able to take both of these advantages. Through a case study, the performance of using the two methods alone and the case of using the hybrid approach was compared, and the hybrid method was judged to have high performance. Therefore, it is judged that using a hybrid method is more appropriate than using the two methods alone for data quality control.

• Convergence Security Journal
• /
• v.23 no.1
• /
• pp.117-123
• /
• 2023

To detect advanced ransomware attacks with machine learning-based models, the classification model must train learning data with high-dimensional feature space. And in this case, a 'curse of dimension' phenomenon is likely to occur. Therefore, dimensionality reduction of features must be preceded in order to increase the accuracy of the learning model and improve the execution speed while avoiding the 'curse of dimension' phenomenon. In this paper, we conducted classification of ransomware by applying three machine learning models and two feature extraction techniques to two datasets with extremely different dimensions of feature space. As a result of the experiment, the feature dimensionality reduction techniques did not significantly affect the performance improvement in binary classification, and it was the same even when the dimension of featurespace was small in multi-class clasification. However, when the dataset had high-dimensional feature space, LDA(Linear Discriminant Analysis) showed quite excellent performance.

• Korean Journal of Agricultural Science
• /
• v.48 no.4
• /
• pp.1015-1026
• /
• 2021

The objective of this study was to determine amino acid and protein contents of brown and milled non-glutinous rice of 13 cultivars in Korea. Protein contents of MRs (milled rices) were in order of Haepum (7.27%) > Hanareum No. 4 (7.14%) > Odae (6.84%). Protein contents of BRs (brown rices) were in order of Haepum (7.68%) > Odae (7.63%) > Hanareum No. 4 (7.60%). The amino acid content was the highest in Haepum (MR 5.76%, BR 6.49%), followed by Haedeul (MR 5.71%, BR 6.30%), and Odae (MR 5.63%, BR 6.29%). The essential amino acid contents of non-glutinous rices were in order of Haepum (MR 2.34%, BR 2.57%) > Haedeul (MR 2.31%, BR 2.48%) > Odae (MR 2.20%, BR 2.56%). The contents of amino acid and protein in BRs were considerably higher than those in MRs. Protein and most of amino acid contents were higher in Haepum than the other cultivars. The certificated reference material (CRM) 1849a (infant/adults nutritional formular) from National Institute of Standard and Technology (NIST) was used as the test sample to determine the precision and accuracy of the analytical method. The regression analyses revealed good correlations (correlation coefficient), greater than 0.99. The recovery values of the amino acids ranged from 93.17 to 99.59%. The limit of detection (LODs) ranged from 0.01 - 0.07 mg·100 g^-1 and the limit of quantitation (LOQs) ranged from 0.03 - 0.21 mg·100 g^-1 for all analytes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1377-1393
• /
• 2023

Social media is used for various purposes including entertainment, communication, information search, and voicing their thoughts and concerns about a service, product, or issue. The social media data can be used for information mining and getting insights from it. The World Health Organization has listed COVID-19 as a global epidemic since 2020. People from every aspect of life as well as the entire health system have been severely impacted by this pandemic. Even now, after almost three years of the pandemic declaration, the fear caused by the COVID-19 virus leading to higher depression, stress, and anxiety levels has not been fully overcome. This has also triggered numerous kinds of discussions covering various aspects of the pandemic on the social media platforms. Among these aspects is the part focused on vaccines developed by different countries, their features and the advantages and disadvantages associated with each vaccine. Social media users often share their thoughts about vaccinations and vaccines. This data can be used to determine the popularity levels of vaccines, which can provide the producers with some insight for future decision making about their product. In this article, we used Twitter data for the vaccine popularity detection. We gathered data by scraping tweets about various vaccines from different countries. After that, various machine learning and deep learning models, i.e., naive bayes, decision tree, support vector machines, k-nearest neighbor, and deep neural network are used for sentiment analysis to determine the popularity of each vaccine. The results of experiments show that the proposed deep neural network model outperforms the other models by achieving 97.87% accuracy.