• Journal of Biomedical Engineering Research
• /
• v.27 no.5
• /
• pp.291-299
• /
• 2006

A Computer-Aided Diagnosis system has been examined to reduce the effort of radiologist. In this paper, we propose the algorithm using Support Vector Machine(SVM) classifier to discriminate whether microcalcifications are malignant or benign tumors. The proposed method to detect microcalcifications is composed of two detection steps each of which uses SVM classifier. The coarse detection step finds out pixels considered high contrasts comparing with neighboring pixels. Then, Region of Interest(ROI) is generated based on microcalcification characteristics. The fine detection step determines whether the found ROIs are microcalcifications or not by merging potential regions using obtained ROIs and SVM classifier. The proposed method is specified on Korean mammogram database. The experimental result of the proposed algorithm presents robustness in detecting microcalcifications than the previous method using Artificial Neural Network as classifier even when using small training data.

• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.369-376
• /
• 2021

One of the most active areas of research in the field of affective computing and signal processing is emotion recognition. This paper proposes emotion recognition of low-resource (Sindhi) language. This work's uniqueness is that it examines the emotions of languages for which there is currently no publicly accessible dataset. The proposed effort has provided a dataset named MAVDESS (Mehran Audio-Visual Dataset Mehran Audio-Visual Database of Emotional Speech in Sindhi) for the academic community of a significant Sindhi language that is mainly spoken in Pakistan; however, no generic data for such languages is accessible in machine learning except few. Furthermore, the analysis of various emotions of Sindhi language in MAVDESS has been carried out to annotate the emotions using line features such as pitch, volume, and base, as well as toolkits such as OpenSmile, Scikit-Learn, and some important classification schemes such as LR, SVC, DT, and KNN, which will be further classified and computed to the machine via Python language for training a machine. Meanwhile, the dataset can be accessed in future via https://doi.org/10.5281/zenodo.5213073.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.53 no.6
• /
• pp.954-959
• /
• 2020

This study aimed to verify the effectiveness of rescue apparatus, that can capture crabs using external stimuli such as food and electricity, without relying on divers. In this study, a microcomputer-based controller and an IC-device-based controller were developed, and spot inspection was conducted using 20 modules and 30 sea urchin removal modules. Accordingly, 58, 18, 17, and 74 sea urchins were introduced in the first, second, third and fourth experiments, respectively. The result of evaluating the lure of each removal mechanism, based on the catch per unit effort, with an electrical stimulus was 1.1 (32/10), with a feeding stimulus was 3.4 (100/29), and with electrical and feeding stimuli was 3.5 (35/10).

• Journal of Information Technology Services
• /
• v.20 no.1
• /
• pp.55-65
• /
• 2021

For smart defense innovation, the key is to apply state-of-the-art technologies of the Fourth Industrial Revolution to national defense. In order to apply state-of-the-art technology to the defense sector, we need to apply and develop technologies to analyze and respond to uncertain future operational environments. To this end, our military is investing a lot of time and effort. To understand future operational environment analysis and to apply and develop our military, we explored the perspectives of operational environment analysis in major countries and studied specific cases of U.S. troops with systematic analysis functions. The U.S. Army has established a cooperative system to analyze future operational environment under the leadership of the Education Command and operates the organization organically. It also utilizes the collective intelligence of expert groups in various fields by utilizing the MSC, and it is time for the Korean military to take the lead in keeping with the era of transformation. To that end, the organization of the U.S. Education Command should be benchmarked and the Korean Future Operation Environment Analysis Organization should be established and operated. Through this study, we have developed an understanding of the future operational environment analysis system of the U.S. Army and presented a plan to apply the ROK MND.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.6
• /
• pp.1075-1080
• /
• 2022

Recently, the effort is continuously applied in machine learning and deep learning algorithm which is represented as artificial intelligence algorithm in the varies field such as prediction, classification and clustering. In this paper, we propose detection algorithm for un-peeling status of PCB protection film by using Dectron2. We use 42 images of data as training and 19 images of data as testing based on 61 images which was taken under the condition of a critical reflection angel of 42.8°. As a result, we get 16 images that was detected and 3 images that was not detected among 19 images of testing data.

• Steel and Composite Structures
• /
• v.44 no.3
• /
• pp.389-406
• /
• 2022

Recycling concrete construction waste is an encouraging step toward green and sustainable building. A lot of research has been done on recycled aggregate concretes (RACs), but not nearly as much has been done on concrete made with recycled aggregate. Recycled aggregate concrete, on the other hand, has been found to have a lower mechanical productivity compared to conventional one. Accurately estimating the mechanical behavior of the concrete samples is a most important scientific topic in civil, structural, and construction engineering. This may prevent the need for excess time and effort and lead to economic considerations because experimental studies are often time-consuming, costly, and troublous. This study presents a comprehensive data-mining-based model for predicting the splitting tensile strength of recycled aggregate concrete modified with glass fiber and silica fume. For this purpose, first, 168 splitting tensile strength tests under different conditions have been performed in the laboratory, then based on the different conditions of each experiment, some variables are considered as input parameters to predict the splitting tensile strength. Then, three hybrid models as GWO-RF, GWO-MLP, and GWO-SVR, were utilized for this purpose. The results showed that all developed GWO-based hybrid predicting models have good agreement with measured experimental results. Significantly, the GWO-RF model has the best accuracy based on the model performance assessment criteria for training and testing data.

• The Journal of Economics, Marketing and Management
• /
• v.4 no.4
• /
• pp.29-35
• /
• 2016

This study has focused on the transfer of infants and Toddlers-protecting responsibilities from families to infants and Toddlers education agencies due to an increase of a double-income family and nuclear family. It is because there is insufficient safe play space from the moment when infants and Toddlers return from infants and Toddlers education agencies to home due to a high crowding of housing and increase of vehicle, and there can be difficulties to take responsibilities of infants and Toddlers safety with a mere recognition and effort of parent. Thus, to suggest a safety education through mutual contact between the communities and agencies supporting parent role in a level of social welfare, its potential has been identified through a frequency analysis on 60 participants of experimental group who have trained a safety education and 60 participants of control group who have not trained a safety education. As a result of frequency analysis, the increase in safety condition in Korea, safety and development of infants and Toddlers, safety of play materials, and safety knowledge on general part of facility safety has detected and the practice of safety and safety consciousness has also identified to be more effective. The results of this study has shown a potential to verify its efficacy if it is verified through an elaborative model of safety education based on parents of young infants and Toddlers family.

• International conference on construction engineering and project management
• /
• 2013.01a
• /
• pp.74-79
• /
• 2013

Aiming at reducing deaths and injuries involving construction crane operations, OSHA has recently updated its 40-year-old crane safety standards with new rules addressing the use of cranes and derricks in construction. The goal of this change in rule is to deal with the leading causes of fatalities related to crane and derrick operations. Employers in the construction industry are mandated to ensure that employees in the work zone are trained to recognize hazards associated with the use of the equipment and any related duties that they are assigned to perform. However, those responsible at construction sites for the supervision and management of safe crane operations often lack the integrated knowledge of the standards, regulations and best practices for conducting or supervising daily, monthly, or quarterly inspection of cranes. As such, proper planning, management and implementation of crane operations, including inspections are just as paramount to reducing accidents on the construction site. It is important that engineers responsible for the management and planning of crane operations understand the latest OSHA crane and hoisting standards to ensure a safer work environment is maintained. Many on site engineers overseeing crane operations do not have adequate training, experience, and knowledge of the inspection requirements to assess safe crane operation and too often rely on the crane operator's judgement. This paper highlights recent research effort in defining significant changes in new crane and hoisting standards and provides basis for safety construction operations.

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.673-687
• /
• 2023

Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.

• The Journal of Industrial Distribution & Business
• /
• v.15 no.4
• /
• pp.1-9
• /
• 2024

Purpose: The purpose of this paper is to explore literature on performance management in order to get insight into how the concept could be optimised during VUCA times for better performance of organisations. Research design, data and methodology: The study adopted a desktop research methodology. Extensive literature review has been conducted from various sources such as journals, research papers, organizational reports, government reports, media reports and articles available on web and effort has been made to assimilate the knowledge body on the topic in the current paper. Literature that enhances understanding on managing performance during VUCA times was reviewed. Results: Solutions to optimise performance management in organisations during VUCA times were proffered and these include innovative planning, innovative monitoring, innovative training and development, innovative rating and innovative rewarding. Conclusions: The study proves that, performance management process should not be done the ordinary way during VUCA times, but innovatively. In this regard innovative performance management can optimise performance of organisations during VUCA period. The study recommends that a further quantitative study be done to test the suitability of each of the proposed ways of innovatively practicing each element of the performance management process across different industries, countries or sector.