Sungtaek Chung

Large language models generate code effectively but falter in enterprise settings that demand complex business rules, particularly in rule consistency and conflict detection. This study proposes the Atomic Logic Sheet (ALS), a structured representation of business logic, injected through the Hierarchical Business Logic Injection (H-BLI) framework. Four conditions were compared on a warehouse management domain, 20 runs each: requirements only; a natural-language design document; the same content with worked examples, anti-patterns, and an explicit conflict-handling directive in prose; and that content expressed in ALS. Conflict responses were adjudicated by two independent raters (κ = 0.993 and 1.000) and cross-checked against a byte-level code comparison. Logic compliance converged near 97% whenever a design document was supplied; conflict detection separated them: 10.0% and 43.1% for the requirements-only and plain-document conditions, and 100% for both content-bearing conditions, neither of which modified code. The two notations detected conflicts identically, and where they differed, the prose condition was better, so the effect follows the content a document is obliged to carry rather than its notation. A replication under a second model reproduced the gap between the requirements-only baseline and the full treatment, and a replication on independently designed conflicts reproduced the detection result for the document conditions; neither included the prose condition, so neither reproduces the comparison between notations. Schema deviation, however, was higher under ALS. As a single-domain study, replication elsewhere remains necessary.

건설, 제조, 광업 등과 같은 산업현장 근로자들의 인지 및 심리적 상태를 평가하여 안전한 업무 수행을 지원하는 것이 매우 중요하다. 그러나 현재 상용화된 디지털 TBM(Tool Box Meeting) 시스템은 근로자의 인지 및 정신건강 상태를 직접 평가하는 데 한계가 있다. 이에 본 연구에서는 근로자의 인지 기능을 평가하기 위한 6종의 기능성 게임형 콘텐츠와 정신건강 상태를 측정하는 설문을 통합한 디지털 정신건강 모니터링 플랫폼을 제안하였다. 또한, 인지 기능 콘텐츠의 타당성을 검증하기 위해 12명의 자원자를 대상으로 음주 후 인지 기능 저하를 평가하였다. 이에 대한 대응 표본 t-검정 결과, 모든 인지 기능 과제에서 음주 후 수행 저하가 통계적으로 유의하게 나타났다. 결과적으로 제안된 인지 기능 콘텐츠는 실시간으로 근로자의 인지 상태를 평가하여, 산업현장에서의 안전관리 효율성을 향상시킬 수 있는 플랫폼 연구의 기초로 활용할 수 있을 것이다.

Progressive global aging has increased the number of elderly individuals living alone. The consequent rise in fall accidents has worsened physical injuries, reduced the quality of life, and increased medical expenses. Existing wearable fall-detection devices may cause discomfort, and camera-based systems raise privacy concerns. Here, we propose a non-contact fall-detection system that integrates 4D imaging radar sensors with artificial intelligence (AI) technology to detect falls through real-time monitoring and visualization using a web-based dashboard and Unity engine-based avatar, along with immediate alerts. The system eliminates the need for uncomfortable wearable devices and mitigates the privacy issues associated with cameras. The radar sensors generate Point Cloud data (the spatial coordinates, velocity, Doppler power, and time), which allow analysis of the body position and movement. A CNN model classifies postures into standing, sitting, and lying, while changes in the speed and position distinguish falling actions from lying-down actions. The Point Cloud data were normalized and organized using zero padding and k-means clustering to improve the learning efficiency. The model achieved 98.66% accuracy in posture classification and 95% in fall detection. This study demonstrates the effectiveness of the proposed fall detection approach and suggests future directions in multi-sensor integration for indoor applications.

A non-contact fall detection system, which integrates 4D imaging radar sensors with arti-ficial intelligence (AI) technology, is proposed to monitor fall accidents among the elderly. Existing wearable devices may cause discomfort during use, and camera-based systems raise privacy concerns. The solution developed in this study addresses these issues by adopting 4D radar sensors. The radar sensors generate Point Cloud data to enable the system to analyze the positions and postures of the body. Using a CNN model, these pos-tures are classified into standing, sitting, and lying, while criteria based on changes in the speed and position distinguish between falls and slow-lying movements. The Point Cloud data were normalized and organized using zero padding and k-means clustering to en-hance the learning efficiency. The proposed model achieved 98.66% accuracy in posture classification and 95% in fall detection. The monitoring system provides real-time visual representations through a web-based dashboard and Unity-based 3D avatars, along with immediate alerts in case of a fall. In conclusion, this study demonstrates the effectiveness of real-time fall detection technology and highlights the need for further research on mul-ti-sensor integration and application in various indoor environments.

본 연구에서는 낙상을 효과적으로 검출하기 위해 4D 이미징 레이더 센서와 인공지능(AI) 기반의 비접촉 낙상 감지 시스템을 제안하였다. 이 시스템은 레이더 센서를 통해 추출한 Point Cloud 데이터를 가공하여 신체의 위치와 자세를 분석하며, CNN 모델을 활용한 서기, 앉기, 눕기 등의 자세를 분류한 후 낙상과 천천히 눕는 동작을 구별하기 위해 속도 및 위치 변화를 비교하는 판별 기준을 수립하였다. 이에 대한 결과로는 낙상 감지정확도 90%, 자세 분류 정확도 98.66%를 달성하였다. 더불어, 웹 기반 인터페이스와 Unity 엔진을 활용한 아바타 시뮬레이션을 통합하여 사용자 친화적인 실시간 모니터링 환경을 제공하고자 하였다. 향후 연구에서는 다양한 환경에서 추가적인 검증을 수행하고, 낙상의 단계를 더욱 세분화하는 한편, 레이더 센서 외에 추가적인 센서를 융합하여 통합 헬스케어 플랫폼으로 발전시킬 필요가 있다.

노화로 인한 근감소증은 근력 감소로 인하여 삶의 질을 떨어뜨릴 수 있으므로, 특히 고령자의 상지 근력 강화를 위한 중재 방법이 필요하다. 근감소증 예방과 관리는 신체 부하를 줄이고 근육 수축과 이완을 반복하는 운동기구 사용이 효과적이다. 본 연구에서는 신체의 움직임을 측정하기 위한 IMU 센서와 정량적인 악력 측정을 위한 로드셀을 결합하여, 사용자의 근력에 따라 무게를 조절할 수 있는 Smart Dumbbell을 새롭게 구현하였다. 또한, 상지 근력의 정량적 평가와 저항성 운동을 위한 근육 수축 및 이완 운동 콘텐츠를 제작하여, 상지근력 강화를 위한 통합적인 운동 플랫폼을 제안하였다. 제안된 Smart Dumbbell과 콘텐츠를 활용한 운동이 표적 근육군의 활성화를 효과적으로 유도하여, 상지 근력 강화를 위한 중재 방법으로서 적합함을 확인하였다.

In this study, we collected various past study results on tools and analytical methods for measuring hand functions of patients with degenerative brain diseases, such as Parkinson’s disease and stroke, and selected and proposed appropriate hand function measurement tools, methods, and analysis software based on text network analysis. We searched the literatures using keywords related to degenerative brain disease and stroke patients for participant types, use of devices and sensors for the intervention types, and hand function assessment for measurement types. Among the 2484 literatures collected, 19 were eventually selected based on certain inclusion and exclusion criteria. As a result of text network analysis, the degree-centrality and the betweenness centrality were the highest in the keyword of Parkinson’s disease for the participant type, force sensor for the intervention type, and finger tapping for the measurement type. Based on these results, pinch gloves comprising an FSR sensor were manufactured, and software and contents were implemented to measure and analyze various quantitative parameter values during finger tapping. The software can evaluate endurance and agility by measuring the finger-tapping intensity and operation time using the index finger and thumb. The contents can evaluate the stability of hand functions by analyzing the coefficient of variation of the tapping interval, the average contact time, and the accuracy of hand functions by analyzing the reaction rate to the presented visual stimulus. As a result of comparing hand functions through 10 types of analysis parameters with a sample of 12 ordinary subjects (8 men and 4 women) using the manufactured pinch gloves, there was a difference between the two genders in the items evaluating muscle strength and agility, and a significant difference in the analysis parameters evaluating stability and accuracy. The results indicate that using the text network analysis-based hand function measurement tool and the method proposed in this study should help derive the objective research results as well as a quantitative comparison of research results of various researchers.

The present study proposes a music recommendation service in a mobile environment using the DASS-21 questionnaire to distinguish and measure certain psychological state instability symptoms—viz. anxiety, depression, and stress—that anyone can experience regardless of job or age. In general, the outcome of the DASS-21 from almost every participant did not reveal any single psychological state out of the abovementioned three states. Therefore, the weighted scores were calculated for each scale and fuzzy clustering was used to cluster users into groups with similar states. For the initial dataset’s generation, we used the DASS inventory collected from the Open-Source Psychometrics Project conducted from 2017 to 2019 on approximately 39,000 respondents, and the results of the survey showed that the average scores for each scale were 23.6 points for depression, 17.4 for anxiety, and 23.3 for stress. Based on the datasets collected from fuzzy clustering, the individuals were classified into three groups: Group 1 was recommended with music for “high” depression, “high” anxiety, and “low” stress; Group 2 was recommended with music for “normal” depression, “low” anxiety, and “normal” stress; and Group 3 was recommended with music for “high” depression, “high” anxiety, and “high” stress. Especially, the largest numbers of recommended music in the three groups were for Group 1 with “High” depressive (4.64), Group 2 for “Low” anxiety (4.54), and Group 3 for “High” anxiety (4.76). In addition, to compare the results of fuzzy clustering with other data, the silhouette coefficient of the samples extracted with the same severity ratio and those generated by simple random sampling were 0.641 and 0.586, respectively, which were greater than 0. The proposed service can recommend not only the music of users with similar trends at all psychological states, but also the music of users with similar psychological states in part.

This study investigated the characteristics for the optimal concentration of addition of the mixing solution through the corn husk pulverization and surface modification of biomass byproducts adding mixed solution between ESO and silane. And surveyed the specific surface area, water absorption, particle size and physical properties of bio- degradable plastic sheet. The specific surface area was 1.105m2/g, particle size was the highest at 19 μm. The impact strength, tensile strength, elongation and hardness of plastic sheet showed the highest at the 1% concentration among the mixing solutions. The flexural strength and modulus was high according to the increasing the mixing solution. The results above showed that it was the best the adding 1% of mixed solution after silane treatment of corn husks for its manufacture as a bio-based plastic sheet.