• Journal of Software Assessment and Valuation
• /
• v.17 no.2
• /
• pp.1-10
• /
• 2021

The ability to recognize human emotions by computer vision is a very important task, with many potential applications. Therefore the demand for emotion recognition using not only RGB images but also thermal images is increasing. Compared to RGB images, thermal images has the advantage of being less affected by lighting conditions but require a more sophisticated recognition method with low-resolution sources. In this paper, we propose a Divide and Conquer-based CNN training strategy to improve the performance of facial thermal image-based emotion recognition. The proposed method first trains to classify difficult-to-classify similar emotion classes into the same class group by confusion matrix analysis and then divides and solves the problem so that the emotion group classified into the same class group is recognized again as actual emotions. In experiments, the proposed method has improved accuracy in all the tests than when recognizing all the presented emotions with a single CNN model.

• Journal of Software Assessment and Valuation
• /
• v.17 no.2
• /
• pp.143-150
• /
• 2021

There is a need for an artificial intelligent technology that can reduce various types of safety accidents by analyzing the risk factors that cause safety accidents in industrial site. In this paper, user safety profiling methods are proposed that can prevent safety accidents in advance by specifying and modeling user information data related to safety accidents. User information data is classified into normal and abnormal conditions through deep learning based artificial intelligence analysis. As a result of verifying user safety profiling technology using more than 10 types of industrial field data, 93.6% of user safety profiling accuracy was obtained.

• Journal of Software Assessment and Valuation
• /
• v.16 no.2
• /
• pp.1-8
• /
• 2020

The similarity detection to plagiarism or duplication of computer programs requires a different type of analysis methods and tools according to the programming language used in the implementation and the sort of code to be analyzed. In recent years, the similarity appraisal for the object code in the embedded system, which requires a considerable resource along with a more complicated procedure and advanced skill compared to the source code, is increasing. In this study, we described a method for analyzing the similarity of functional units in the assembly language through the conversion of object code using the reverse engineering approach, such as the reverse assembly technique to the object code. The instruction and operand table for comparing the similarity is generated by using the syntax analysis of the code in assembly language, and a tool for detecting the similarity is designed.

• Journal of Software Assessment and Valuation
• /
• v.16 no.1
• /
• pp.13-19
• /
• 2020

It can be seen that the infringement of copyright cases is increasing as the society becomes more complex and advanced. During the software copyright dispute, there may be a dispute over whether the software is duplicated and made into upgraded software. In this paper, we intend to propose an analysis method for determining whether to upgrade software. For the software upgrade analysis, a software similarity analysis technique was used. The analysis program covers servers, management programs, and Raspberry PC programs. The first analysis confirms the correspondence between program creation information and content. In addition, it analyzes the similarity of functions and screen composition between the submitted program and the program installed in the field. The second comparative analysis compares and analyzes similarities by operating two programs in the same environment. As a result of comparative analysis, it was confirmed that the operation and configuration screens of the two programs were identical. Thus, minor differences were found in a few files, but it was confirmed that the two programs were mostly made using the same or almost similar source code. Therefore, this program can be judged as an upgrade program.

• Journal of Software Assessment and Valuation
• /
• v.16 no.2
• /
• pp.135-142
• /
• 2020

In this paper, we describe the iris localization method in RGB images. Most of the iris localization methods are developed for infrared images, thus an iris localization method in RGB images is required for various applications. The proposed method consists of four stages: i) detection of the candidate irises using circular Hough transform (CHT) from an input image, ii) detection of a pupil center based on deep learning, iii) determine the iris using the pupil center, and iv) correction of the iris region. The candidate irises are detected in the order of the number of intersections of the center point candidates after generating the Hough space, and the iris in the candidates is determined based on the detected pupil center. Also, the error due to distortion of the iris shape is corrected by finding a new boundary point based on the detected iris center. In experiments, the proposed method has an improved accuracy about 27.4% compared to the CHT method.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.741-747
• /
• 2022

Fatigue lowers an individual's ability and makes it difficult to perform work. As fatigue accumulates, concentration decreases and thus the possibility of causing a safety accident increases. Awareness of fatigue is subjective, but it is necessary to quantitatively measure the level of fatigue in the actual field. In previous studies, it was proposed to measure the level of fatigue by expert judgment by adding objective indicators such as bio-signal analysis to subjective evaluations such as multidisciplinary fatigue scales. However this method is difficult to evaluate fatigue in real time in daily life. This paper is a study on the fatigue classification model that determines the fatigue level of workers in real time using speech data recorded in the field. Machine learning models such as logistic classification, support vector machine, and random forest are trained using speech data collected in the field. The performance evaluation showed good performance with accuracy of 0.677 to 0.758, of which logistic classification showed the best performance. From the experimental results, it can be seen that it is possible to classify the fatigue level using speech signals.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.6
• /
• pp.578-586
• /
• 2021

We propose a semi-supervised learning method based on Variational AutoEncoder (VAE) and Unsupervised Data Augmentation (UDA) to improve the performance of an end-to-end speech recognizer. In the proposed method, first, the VAE-based augmentation model and the baseline end-to-end speech recognizer are trained using the original speech data. Then, the baseline end-to-end speech recognizer is trained again using data augmented from the learned augmentation model. Finally, the learned augmentation model and end-to-end speech recognizer are re-learned using the UDA-based semi-supervised learning method. As a result of the computer simulation, the augmentation model is shown to improve the Word Error Rate (WER) of the baseline end-to-end speech recognizer, and further improve its performance by combining it with the UDA-based learning method.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.573-587
• /
• 2022

The agricultural sector is completely different from other sectors since it completely relies on various natural and climatic factors. Climate changes have many effects, including lack of annual rainfall and pests, heat waves, changes in sea level, and global ozone/atmospheric CO₂ fluctuation, on land and agriculture in similar ways. Climate change also affects the environment. Based on these factors, farmers chose their crops to increase productivity in their fields. Many existing agricultural ontologies are either domain-specific or have been created with minimal vocabulary and no proper evaluation framework has been implemented. A new agricultural ontology focused on subdomains is designed to assist farmers using Jaccard relative extractor (JRE) and Naïve Bayes algorithm. The JRE is used to find the similarity between two sentences and words in the agricultural documents and the relationship between two terms is identified via the Naïve Bayes algorithm. In the proposed method, the preprocessing of data is carried out through natural language processing techniques and the tags whose dimensions are reduced are subjected to rule-based formal concept analysis and mapping. The subdomain ontologies of weather, pest, and soil are built separately, and the overall agricultural ontology are built around them. The gold standard for the lexical layer is used to evaluate the proposed technique, and its performance is analyzed by comparing it with different state-of-the-art systems. Precision, recall, F-measure, Matthews correlation coefficient, receiver operating characteristic curve area, and precision-recall curve area are the performance metrics used to analyze the performance. The proposed methodology gives a precision score of 94.40% when compared with the decision tree(83.94%) and K-nearest neighbor algorithm(86.89%) for agricultural ontology construction.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.8
• /
• pp.241-248
• /
• 2022

In this paper, the PID controller and Kalman filter are applied to improve the automobile cruise control in the environment with disturbance and noise, and the performance is verified through diverse simulation. First, a mathematical model for a automobile cruise control system is introduced. Second, the performance degradation due to disturbance in the basic open-loop control based cruise control system is shown and then PID controller-based feedback control system to resolve this problem is verified. Third, to improve the performance degradation due to sensor noise that may occur during the feedback process, a Kalman filter is applied and verified. Ultimately, it is verified that the designed cruise control system with PID controller and Kalman filter not only satisfies all performance conditions but also has the ability for disturbance rejection and noise reduction.

• Journal of Advanced Navigation Technology
• /
• v.27 no.1
• /
• pp.139-145
• /
• 2023

When a doctor examines a patient in a hospital, the doctor directly checks the patient's condition and conducts a face-to-face diagnosis through dialogue with the patient. However, it is often difficult for doctors to directly treat patients. Recently, several types of telemedicine systems have been developed. However, the systems have lack of capabilities to observe heart disease, neck condition, skin condition, inside ear condition, etc. To solve this problem, in this paper, an interactive telemedicine robot system with autonomous driving in a room capable of visual examination and auscultation of patients is developed. The developed robot can be controlled remotely through the WebRTC platform to move toward the patient and check a patient's condition under the doctor's observation using the multi-joint robot arm. The video information, audio information, patient's heart sound, and other data obtained remotely from patients can be transmitted to a doctor through the web RTC platform. The developed system can be applied to the various places where doctors are not possible to attend.