• 한국산업정보학회논문지
• /
• 제23권3호
• /
• pp.49-57
• /
• 2018

Cho는 확률적 활동 네트워크 분석에서 활동시간이 상호 독립적이고 정규분포를 따른다는 가정 하에서 사업완성시간의 적률 (평균, 분산, 왜도, 첨도)을 추정하기 위한 방법을 제안하였다. 본 논문에서는 활동시간의 분포가 일반적인 분포일 때 사업완성시간의 적률을 추정하기 위한 방법을 제안한다. 제안된 방법은 활동시간 분포의 이산화를 위해 적률매칭 방법을 사용하며, 사업완성시간의 계산에 사용될 활동시간을 결정하는데 이산형 역변환 방법을 사용한다. 제안된 방법은 대규모 네트워크에 적용하기 쉽고, 몬테칼로 시뮬레이션 보다 계산적으로 효율적이며, 제안된 방법의 결과는 몬테칼로 시뮬레이션에 의한 결과와 잘 일치함을 보여준다.

• International Journal of Computer Science & Network Security
• /
• 제21권2호
• /
• pp.221-228
• /
• 2021

Recent improvements on the quality, fidelity and availability of biometric data have led to effective human physical activity detection (HPAD) in real time which adds significant value to applications such as human behavior identification, healthcare monitoring, and user authentication. Current approaches usually use machine-learning techniques for human physical activity recognition based on the data collected from wearable accelerometer sensor from a single wearable smart device on the user. However, collecting data from a single wearable smart device may not provide the complete user activity data as it is usually attached to only single part of the user's body. In addition, in case of the absence of the single sensor, then no data can be collected. Hence, in this paper, a continuous HPAD will be presented to effectively perform user activity detection with mobile service infrastructure using multiple wearable smart devices, namely smartphone and smartwatch placed in various locations on user's body for more accurate HPAD. A case study on a comprehensive dataset of classified human physical activities with our HAPD approach shows substantial improvement in HPAD accuracy.

• Journal of applied mathematics & informatics
• /
• 제20권1_2호
• /
• pp.119-132
• /
• 2006

This paper presents an approach for using right-truncated exponentially distributed random variables to model activity times in stochastic activity networks. The advantages of using the right-truncated exponential distribution are discussed. The moments of a project completion time using the proposed distribution are derived and compared with other estimated moments in literature.

• 한국멀티미디어학회논문지
• /
• 제23권12호
• /
• pp.1540-1551
• /
• 2020

Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

• International Journal of Computer Science & Network Security
• /
• 제22권12호
• /
• pp.51-56
• /
• 2022

In space based constellation network, users are allowed to enter or leave the network arbitrarily. Hence, the number, identities and transmitted data of active users vary with time and have considerable impacts on the receiver's performance. The so-called problem of multiuser detection means identifying the identity of each active user and detecting the data transmitted by each active user. Traditional methods assume that the number of active users is equal to the maximum number of users that the network can hold. The model of traditional methods are simple and the performance are suboptimal. In this paper a Maximum A Posteriori Probability (MAP) based multiuser detection method is proposed. The proposed method models the activity state of users as Markov chain and transforms multiuser detection into searching optimal path in grid map with BCJR algorithm. Simulation results indicate that the proposed method obtains 2.6dB and 1dB E_b/N₀ gains respectively when activity detection error rate and symbol error rate reach 10^-3, comparing with reference methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.481-481
• /
• 2000

We investigated the structure-activity relationships on use of multi-layer neural networks. The relationships are techniques required in developments of medicines. Since many kinds of observations might be adopted on the techniques, we discussed some points between the observations and the properties of multi-layer neural networks. In the structure-activity relationships, an important property is not that standard deviations are nearly equal to zero for observed physiological activity, but prediction ability for unknown medicines. Since we adopted non-linear approximation, the function to represent the activity can be defined by observations; therefore, we believe that the standard deviations have not significance. The function was examined by "leave-one-out" method, which was originally introduced for the multi-regression analysis. In the linear approximation, the examination is significance, however, we believe that the method is inappropriate in case of nonlinear fitting as neural networks; therefore, we derived a new index fer the relationships from the differential of information propagation in the neural network. By using the index, we discussed physiological activity of an anti-cancer medicine, Mitomycine derivatives. The neuro-computing suggests that there is no direction to extend the anti-cancer activity of Mitomycine, which is close to the trend of anticancer developing.

• 산업경영시스템학회지
• /
• 제29권4호
• /
• pp.65-74
• /
• 2006

This research tried to grasp present condition of domestic corporation's society contribution activity and grope desirable direction of society contribution activity hereafter. As analysis result, establishment of the responsible department or human power in charge for society contribution activity is insufficient, and depend on contribution activity of simple donation than to administer program directly, result of contribution activity is not linked with corporation's purpose or result and practical use of network with similar organization for society contribution was proved by low. Desirable direction of domestic corporation society contribution activity is as following hereafter based on analysis result. First, corporation must put in good order inside system with an establishment of the responsible department for society contribution, security of human power in charge and introducing education program for training specialist. Second, corporation must select specific field with capacity that corporation is holding and improve result of society contribution activity as concentrated investment. Third, corporation must construct network with various similar groups and organizations including NPO/NGO and heighten consummativeness of society contribution activity through mutual interchange and cooperation.

• 한국항행학회논문지
• /
• 제28권4호
• /
• pp.428-435
• /
• 2024

본 논문에서는 다중 입출력 주파수 변조 연속파 (MIMO FMCW; multiple input multiple output frequency modulation continuous wave) 레이다 기반 HAR (human activity recognition) 시스템의 설계 및 구현 결과를 제시하였다. 다중 입력 다중 출력 레이다 센서를 통한 포인트 클라우드 데이터를 활용하여 HAR 시스템을 구현하면 사생활 보호와 함께, 안전성 및 정확성 측면에서 장점이 있다. 본 논문에서는, MIMO FMCW 레이다 센서로부터의 포인트클라우드 데이터 기반 HAR을 위해 PointPillars와 DS-CNN (depthwise separable convolutional neural network)을 기반으로 최적 경량 네트워크를 개발하였다. 경량화된 네트워크를 통해 고해상도 포인트 클라우드 데이터를 처리하여 높은 인식 정확도와 함께 효율성을 달성하였다. 결과적으로, 98.27%의 정확도와 11.27M Macs (multiply-accumulates) 연산 복잡도로 구현 가능함을 확인하였다. 또한, 개발한 모델을 라즈베리파이(Raspberry-Pi) 시스템에 구현하여 최대 8 fps의 속도로 포인트 클라우드 데이터 처리가 가능함을 확인하였다.

• 인터넷정보학회논문지
• /
• 제14권2호
• /
• pp.25-34
• /
• 2013

본 논문에서는 워크플로우 기반 인적 자원의 소속성 분석을 위한 업무-수행자 이분 행렬 생성 알고리즘을 제안한다. 워크플로우 기반 인적 자원은 워크플로우 관리 시스템에 의해 관리되는 조직의 모든 수행자들을 말하며, 워크플로우 모델의 실행 과정에서 특정 업무 집합에 참여하게 된다. 이러한 워크플로우 모델에 정의된 수행자들과 업무들과의 소속성을 나타내는 소셜 네트워크를 업무-수행자 소속성 네트워크라 정의하였으며, 본 논문에서 제안하는 알고리즘은 워크플로우 모델로부터 발견된 업무-수행자 소속성 네트워크 모델(APANM)에 대한 이분 행렬을 생성하기 위한 알고리즘이다. 결론적으로, 알고리즘에 의해 생성된 업무-수행자 이분 행렬은 중심성(centrality), 밀집도(density), 상관 관계(correlation)와 같은 다양한 소셜 네트워크 관련 속성들을 분석하는데 적용될 수 있으며, 이를 통해 워크플로우 기반 인적 자원의 소속성에 대한 유용한 지식을 획득할 수 있다.

• 융합신호처리학회논문지
• /
• 제24권2호
• /
• pp.90-96
• /
• 2023

합성곱 신경망을 비롯하여 딥러닝 신경망의 학습에서 많은 양의 훈련데이터의 확보는 과적합 현상을 피하고 우수한 성능을 가지기 위해서 매우 중요하다. 하지만, 딥러닝 신경망에서의 레이블화된 훈련데이터의 확보는 실제로는 매우 제한적이다. 이를 극복하기 위해, 이미 획득한 훈련데이터를 변형, 조작 등으로 추가로 훈련데이터를 생성하는 여러 증강 방법이 제안되었다. 하지만, 이미지, 문자 등의 훈련데이터와 달리, 인간 동작 인식을 행하는 합성곱 신경망의 생체신호 훈련데이터를 추가로 생성하는 증강 방법은 연구 문헌에서 찾아보기 어렵다. 본 연구에서는 합성곱 신경망에 기반한 인간 동작 인식을 위한 생체신호 훈련데이터를 생성하는 간편하지만, 효과적인 증강 방법을 제안한다. 본 연구의 제안된 증강 방법의 유용성은 추가로 생성된 생체신호 훈련데이터로 학습하여 합성곱 신경망이 인간 동작을 높은 정확도로 인식하는 것을 보임으로써 검증하였다.