• Journal of People, Plants, and Environment
• /
• v.22 no.1
• /
• pp.1-14
• /
• 2019

This study was designed to examine agro-healing services and programs provided and operated by farms in Korea. The results of the analysis of the agro-healing programs and operation of farms were as follows. The purpose of the operation of farms was to raise productivity by managing farms in a cooperative way through agricultural production, education and healing, and to raise income by processing and selling agricultural products. It was difficult to access farms by public transport and thus visitors had to use their own cars. The size of farms varied. The main resources utilized in the surveyed programs were plants, rural environments and landscapes, and agricultural products. The programs were conducted using resources that were commonly found in rural areas. Facilities on each farm were equipped with facilities (indoor and outdoor learning place, gardens, vegetable gardens, orchards, etc.) and convenience facilities (parking lots, drinking fountains, kiosks, etc.) to support program operation. However, facilities for the handicapped and accommodation facilities were insufficient. The programs operated on each farm utilized agricultural resources, farm produce, and rural resources and were classified into activities such as making, feeling, and growing. The average number of people who operated the family-centered program was 2-3, having qualifications such as welfare horticultural therapists, forest interpreters, experience instructors, and social workers. In addition, they had expertise in medicinal food, dietary life, and social welfare, and they also had essential expertise required to operate programs.

• 재활복지
• /
• v.14 no.3
• /
• pp.95-119
• /
• 2010

This study aims to develope participation scale of people with disabilities according to the International classification of Functioning, Disability, and Health(ICF). ICF includes a component for classifying and qualifying participation of individuals in the context of their environments. The participation scale were developed using 7 times with different focus groups using the ICIDH-2 as a contextual framework. Candidate 41 items were developed based on the 8 participation components and put into a survey format. Finally, purposeful sample of 363 people with mobility limitations was conducted survey. As a result of survey, participation scale is composed of 38 items that are placed in 7 domains used in the activity/participation component of the ICF: holisitc health; communication; mobility; domestic life; interpersonal interactions and relationships; social and economic life; civic life. This scale does not include the domains of learning and applying knowledge, general tasks and demands, recreation and leisure but more focuses on social and civic life.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.137-145
• /
• 2020

Providing safety training to construction workers is essential to reduce safety accidents at the construction site. With the prosperity of visualization technologies, Immersive Virtual Reality (IVR) has been adopted for construction safety training by providing interactive learning experiences in a virtual environment. Previous research efforts on IVR-based training have found that the level of fidelity of interaction between real and virtual worlds is one of the important factors contributing to the sense of presence that would affect training performance. Various interactive devices that link activities between real and virtual worlds have been applied in IVR-based training, ranging from existing computer input devices (e.g., keyboard, mouse, joystick, etc.) to specially designed devices such as high-end VR simulators. However, the need for high-fidelity interactive devices may hinder the applicability of IVR-based training as they would be more expensive than IVR headsets. In this regard, this study aims to understand the impact of the level of fidelity of interactive devices in the sense of presence in a virtual environment and the training performance during IVR-based forklift safety training. We conducted a comparative study by recruiting sixty participants, splitting them into two groups, and then providing different interactive devices such as a keyboard for a low fidelity group and a steering wheel and pedals for a high-fidelity group. The results showed that there was no significant difference between the two groups in terms of the sense of presence and task performance. These results indicate that the use of low-fidelity interactive devices would be acceptable for IVR-based safety training as safety training focuses on delivering safety knowledge, and thus would be different from skill transferring training that may need more realistic interaction between real and virtual worlds.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.115-122
• /
• 2024

Multi-object tracking (MOT) is a vital component in understanding the surrounding environments. Previous research has demonstrated that MOT can successfully detect and track surrounding objects. Nonetheless, inaccurate classification of the tracking objects remains a challenge that needs to be solved. When an object approaching from a distance is recognized, not only detection and tracking but also classification to determine the level of risk must be performed. However, considering the erroneous classification results obtained from the detection as the track class can lead to performance degradation problems. In this paper, we discuss the limitations of classification in tracking under the classification uncertainty of the detector. To address this problem, a class update module is proposed, which leverages the class uncertainty estimation of the detector to mitigate the classification error of the tracker. We evaluated our approach on the VisDrone-MOT2021 dataset,which includes multi-class and uncertain far-distance object tracking. We show that our method has low certainty at a distant object, and quickly classifies the class as the object approaches and the level of certainty increases.In this manner, our method outperforms previous approaches across different detectors. In particular, the You Only Look Once (YOLO)v8 detector shows a notable enhancement of 4.33 multi-object tracking accuracy (MOTA) in comparison to the previous state-of-the-art method. This intuitive insight improves MOT to track approaching objects from a distance and quickly classify them.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.2
• /
• pp.281-288
• /
• 2024

The sixth generation(6G) wireless communication technology is advancing toward ultra-high speed, ultra-high bandwidth, and hyper-connectivity. With the development of communication technologies, the formation of a hyper-connected society is rapidly accelerating, expanding from the IoT(Internet of Things) to the IoE(Internet of Everything). However, at the same time, security threats targeting IoT devices have become widespread, and there are concerns about security incidents such as unauthorized access and information leakage. As a result, the need for security-enhancing solutions is increasing. In this paper, we implement an autoencoder-based anomaly detection model utilizing real-time collected network traffics in respond to IoT security threats. Considering the difficulty of capturing IoT device traffic data for each attack in real IoT environments, we use an unsupervised learning-based autoencoder and implement 6 different autoencoder models based on the use of noise in the training data and the dimensions of the latent space. By comparing the model performance through experiments, we provide a performance evaluation of the anomaly detection model for detecting abnormal network traffic.

• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.135-142
• /
• 2023

In addressing the prominent issues of climate change, resource scarcity, and environmental pollution associated with household waste, extensive research has been conducted on intelligent waste classification methods. These efforts range from traditional classification algorithms to machine learning and neural networks. However, challenges persist in effectively classifying waste in diverse environments and conditions due to insufficient datasets, increased complexity in neural network architectures, and performance limitations for real-world applications. Therefore, this paper proposes i-YOLOX as a solution for rapid classification and improved accuracy. The proposed model is evaluated based on network parameters, detection speed, and accuracy. To achieve this, a dataset comprising 10,000 samples of household waste, spanning 17 waste categories, is created. The i-YOLOX architecture is constructed by introducing the Involution channel convolution operator and the Convolution Branch Attention Module (CBAM) into the YOLOX structure. A comparative analysis is conducted with the performance of the existing YOLO architecture. Experimental results demonstrate that i-YOLOX enhances the detection speed and accuracy of waste objects in complex scenes compared to conventional neural networks. This confirms the effectiveness of the proposed i-YOLOX architecture in the detection and classification of multiple household waste objects.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.456-477
• /
• 2024

With information technology's rapid development, the Internet faces serious security problems. Studies have shown that malware has become a primary means of attacking the Internet. Therefore, adversarial samples have become a vital breakthrough point for studying malware. By studying adversarial samples, we can gain insights into the behavior and characteristics of malware, evaluate the performance of existing detectors in the face of deceptive samples, and help to discover vulnerabilities and improve detection methods for better performance. However, existing adversarial sample generation methods still need help regarding escape effectiveness and mobility. For instance, researchers have attempted to incorporate perturbation methods like Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), and others into adversarial samples to obfuscate detectors. However, these methods are only effective in specific environments and yield limited evasion effectiveness. To solve the above problems, this paper proposes a malware adversarial sample generation method (PixGAN) based on the pixel attention mechanism, which aims to improve adversarial samples' escape effect and mobility. The method transforms malware into grey-scale images and introduces the pixel attention mechanism in the Deep Convolution Generative Adversarial Networks (DCGAN) model to weigh the critical pixels in the grey-scale map, which improves the modeling ability of the generator and discriminator, thus enhancing the escape effect and mobility of the adversarial samples. The escape rate (ASR) is used as an evaluation index of the quality of the adversarial samples. The experimental results show that the adversarial samples generated by PixGAN achieve escape rates of 97%, 94%, 35%, 39%, and 43% on the Random Forest (RF), Support Vector Machine (SVM), Convolutional Neural Network (CNN), Convolutional Neural Network and Recurrent Neural Network (CNN_RNN), and Convolutional Neural Network and Long Short Term Memory (CNN_LSTM) algorithmic detectors, respectively.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.31-36
• /
• 2024

Recently, mobile apps that utilize AI technologies are increasing. In the personal mobile environment, performance degradation may occur during the training phase of large AI workload due to limitations in memory capacity. In this paper, we extract memory reference traces of AI workloads and analyze their characteristics. From this analysis, we observe that AI workloads can cause frequent storage access due to weak temporal locality and irregular popularity bias during memory write operations, which can degrade the performance of mobile devices. Based on this observation, we discuss ways to efficiently manage memory write operations of AI workloads using persistent memory-based swap devices. Through simulation experiments, we show that the system architecture proposed in this paper can improve the I/O time of mobile systems by more than 80%.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.309-316
• /
• 2024

Facial recognition technology is widely used in various fields but faces challenges due to its vulnerability to fraudulent activities such as photo spoofing. Extensive research has been conducted to overcome this challenge. Most of them, however, require the use of specialized equipment like multi-modal cameras or operation in high-performance environments. In this paper, we introduce LH-FAS v2 (: Lightweight Head-pose-based Face Anti-Spoofing v2), a system designed to operate on a commercial webcam without any specialized equipment, to address the issue of facial recognition spoofing. LH-FAS v2 utilizes FSA-Net for head pose estimation and ArcFace for facial recognition, effectively assessing changes in head pose and verifying facial identity. We developed the VD4PS dataset, incorporating photo spoofing scenarios to evaluate the model's performance. The experimental results show the model's balanced accuracy and speed, indicating that head pose estimation-based facial anti-spoofing technology can be effectively used to counteract photo spoofing.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.23-32
• /
• 2024

Large-scale fires and their consequential damages are becoming increasingly common, but confidence in fire detection systems is waning. Recently, widely-used chemical fire detectors frequently generate lots of false alarms, while video-based deep learning fire detection is hampered by its time-consuming and expensive nature. To tackle these issues, this study proposes a fire detection model utilizing an autoencoder approach. The objective is to minimize false alarms while achieving swift and precise fire detection. The proposed model, employing an autoencoder methodology, can exclusively learn from normal data without the need for fire-related data, thus enhancing its adaptability to diverse environments. By amalgamating data from five distinct sensors, it facilitates rapid and accurate fire detection. Through experiments with various hyperparameter combinations, the proposed model demonstrated that out of 14 scenarios, only one encountered false alarm issues. Experimental results underscore its potential to curtail fire-related losses and bolster the reliability of fire detection systems.