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.

BACKGROUND The aging population is increasing due to declining birth rates and advancements in medical technology, leading to a rise in single-person elderly households. While factors such as spousal loss, children's independence, and the pursuit of autonomy enable independent living, they also raise concerns about vulnerability during emergencies. Additionally, health issues such as reduced muscle strength, impaired balance, weakened vision, and arthritis significantly increase the risk of falls, which can result in severe injuries, decreased mobility, and mental health challenges. Consequently, fall prevention and management have become essential for maintaining and improving the quality of life in the elderly. The growing demand for technological solutions to enhance elderly safety has driven research into smart healthcare services that provide real-time monitoring and immediate fall response. OBJECTIVE A non-contact fall detection system, which integrates 4D imaging radar sensors with artificial 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. METHODS 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 postures 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 enhance the learning efficiency. RESULTS 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. CONCLUSIONS In conclusion, this study demonstrates the effectiveness of real-time fall detection technology and highlights the need for further research on multi-sensor integration and application in various indoor environments.

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.