-
公开(公告)号：KR1020140025701A
公开(公告)日：2014-03-05
申请号：KR1020120091681
申请日：2012-08-22
Applicant: 국민대학교산학협력단
CPC classification number: G01N33/0004 , G06N3/02
Abstract: The present invention relates to a method for estimating the number of persons in a room based on carbon dioxide concentration using a dynamic neural network. The method comprises: a measurement step for measuring the concentration of carbon dioxide contained in the indoor air; a storage step for storing the concentration of carbon dioxide measured in the measurement step in real time; a neural network configuration step for configuring at least one dynamic neural network part in order to estimate the number of residual persons positioned in a room using the concentration of carbon dioxide stored in the storage step; a neural network learning step for comparing the number of residual persons estimated from the dynamic neural network part configured in the neural network configuration step with a reference value previously input for the number of residual persons, comparing an error between the number of residual persons and the reference value with a predetermined threshold, and adjusting a weighted value and a deflection value of a transfer function which configures the dynamic neural network part in a direction along which the error of the reference value decreases; and an estimation step for estimating the number of residual persons through the dynamic neural network part adjusted in the neural network learning step, and proposes a technique of efficiently grasping persons in a room of a building. Thus, installation and maintenance costs can be cheaper than those of a conventional method for checking the number of persons in a room using video cameras or motion recognition sensors, and reliability can be improved by removing a dead zone. [Reference numerals] (100) Sensor part; (200) Storage part; (300) Dynamic neural network part; (400) Neural network learning part
Abstract translation: 本发明涉及一种使用动态神经网络基于二氧化碳浓度估计房间中的人数的方法。 该方法包括：测量室内空气中含有的二氧化碳浓度的测量步骤; 存储步骤，用于实时地存储在测量步骤中测量的二氧化碳的浓度; 神经网络配置步骤，用于配置至少一个动态神经网络部分，以便使用存储在存储步骤中的二氧化碳的浓度来估计位于房间中的残留人的数量; 神经网络学习步骤，用于将从神经网络配置步骤中配置的动态神经网络部分估计出的剩余人数与预先输入的剩余人数相对应的参考值进行比较，将剩余人数与 参考值与预定阈值，并且调整在所述参考值的误差减小的方向上配置所述动态神经网络部分的传递函数的加权值和偏转值; 以及用于通过在神经网络学习步骤中调整的动态神经网络部分估计剩余人数的估计步骤，并且提出了一种有效地抓住建筑物的房间中的人的技术。 因此，安装和维护成本可以比用于使用摄像机或运动识别传感器检查房间中的人数的常规方法的成本更便宜，并且可以通过去除死区来提高可靠性。 （附图标记）（100）传感器部分; （200）储存部分; （300）动态神经网络部分; （400）神经网络学习部分
-
公开(公告)号：KR1020140120287A
公开(公告)日：2014-10-13
申请号：KR1020140109459
申请日：2014-08-22
Applicant: 국민대학교산학협력단
Abstract: 본 발명은 동적신경망을 이용한 이산화탄소 농도 기반 재실인원 추정 시스템에 관한 것으로, 동적신경망을 이용한 이산화탄소 농도 기반 재실인원 추정 시스템은 실내의 대기 중에 포함된 이산화탄소의 농도를 측정하는 센서부; 상기 센서부로부터 측정된 이산화탄소의 농도를 실시간으로 저장하는 저장부; 상기 저장부로부터 저장된 이산화탄소의 농도값을 통해 실내에 위치한 잔류인원수를 추정하도록 설정된 적어도 하나 이상의 동적신경망부; 및 상기 동적신경망부에서 추정된 상기 잔류인원수와 상기 잔류인원수에 대해 사전에 입력된 기준값을 비교하고, 상기 잔류인원수 및 상기 기준값의 오차를 기설정된 임계값과 비교하여 상기 기준값의 오차가 감소되는 방향으로 상기 동적신경망부를 구성하는 전달 함수의 가중값 및 편향값을 조절하는 신경망 학습부; 를 포함하고, 그로 인해 효율적으로 건물 내의 재실인원을 파악하는 기술을 제시한다.
본 발명에 의하면, 본 발명은 비디오카메라 또는 동작인식 센서를 활용한 종래의 재실인원 확인 방법보다 설치 및 유지비용이 저렴하고, 사각지대가 없으므로 신뢰도가 향상된 효과가 있다.Abstract translation: 本发明涉及使用动态神经网络的基于二氧化碳浓度的占用率估计系统。 使用动态神经网络的基于二氧化碳浓度的占用率估计系统包括：测量室内二氧化碳浓度的传感器单元; 存储单元，其实时地存储由所述传感器单元测量的二氧化碳的浓度; 至少一个动态神经网络单元，通过使用存储在存储单元中的二氧化碳的浓度值来估计房间中剩余人的数量; 以及神经网络学习单元，通过比较通过动态神经网络估计的剩余人数，来调整构成动态神经网络单元的传递函数的权重值和偏差值， 网络单元，其具有先前输入的剩余人员的参考值，并将剩余人员的数量和参考值的误差与预设阈值进行比较，从而有效地检查建筑物中的人数。 本发明的系统可以提高可靠性，因为安装和维护成本比使用摄像机或运动识别传感器的常规占用检查方法便宜，并且没有盲点。
-
公开(公告)号：KR1020140118946A
公开(公告)日：2014-10-08
申请号：KR1020140109460
申请日：2014-08-22
Applicant: 국민대학교산학협력단
Abstract: The present invention relates to an occupancy estimation method based on carbon dioxide concentration using a dynamic neural network. An occupancy estimation method based on carbon dioxide concentration using a dynamic neural network includes a measuring step of measuring carbon dioxide concentration included in a room atmosphere; a storing step of storing the carbon dioxide concentration measured by the measuring step in real time; a configuring step of configuring at least one dynamic neural network to estimate the number of remaining occupants in a room based on the carbon dioxide concentration stored by the storing step; a neural network training step of comparing the number of remaining occupants, which is estimated by the dynamic neural network configured by the configuring step, with a reference value previously input for the number of remaining occupants, and comparing an error between the number of remaining occupants and the reference value with a preset threshold value in order to control a weight value and a deviation value of a transfer function for configuring the dynamic neural network to allow the error to be decreased; and an estimating step of estimating the number of remaining occupants through the dynamic neural network controlled by the neural network training step. Thus, the present invention proposes a technique of efficiently recognizing the number of occupants in a building. According to the present invention, as compared with those of a occupancy confirming method using a video camera or a motion recognition sensor according to the related art, the installation and maintenance costs are inexpensive and there is no blind spot so that the reliability is improved.
Abstract translation: 本发明涉及使用动态神经网络的基于二氧化碳浓度的占用率估计方法。 使用动态神经网络的基于二氧化碳浓度的占用率估计方法包括：测量包含在室内气氛中的二氧化碳浓度的测量步骤; 存储步骤，实时地存储由测量步骤测量的二氧化碳浓度; 一种配置步骤，用于基于由所述存储步骤存储的二氧化碳浓度来配置至少一个动态神经网络以估计房间中的剩余占用者的数量; 神经网络训练步骤，将由配置步骤配置的动态神经网络估计的剩余乘员数与预先输入的剩余乘员数相对应的参考值进行比较，并比较剩余乘客数量之间的误差 以及具有预设阈值的参考值，以便控制用于配置动态神经网络的传递函数的权重值和偏差值，以允许误差减小; 以及估计步骤，通过由神经网络训练步骤控制的动态神经网络来估计剩余乘员人数。 因此，本发明提出了一种有效识别建筑物中的乘客人数的技术。 根据本发明，与使用根据现有技术的摄像机或运动识别传感器的占用确认方法相比，安装和维护成本便宜，并且没有盲点，从而提高了可靠性。
-
公开(公告)号：KR1020140025702A
公开(公告)日：2014-03-05
申请号：KR1020120091682
申请日：2012-08-22
Applicant: 국민대학교산학협력단
CPC classification number: G01N33/0004 , G06N3/02
Abstract: The present invention relates to a system for estimating a number of people in a room based on carbon dioxide concentration using dynamic neural network. The system comprises: a sensor unit for measuring the concentration of carbon dioxide contained in the indoor air; a storage unit for storing the concentration of carbon dioxide, measured by the sensor unit, in real time; at least one dynamic neural network unit for estimating a number of residual people positioned in a room using the concentration of carbon dioxide stored in the storage unit; and a neural network learning unit for comparing the number of residual people estimated by the dynamic neural network unit with a reference value previously inputted for the number of residual people, comparing an error between the number of residual people and the reference value with a predetermined threshold, and adjusting a weighted value and a deflection value of a transfer function which configures the dynamic neural network unit in a direction in which the error of the reference value decreases, and proposes a technique of efficiently grasping people in a building room. Thus, installation and maintenance costs can be cheaper than those of a conventional method for checking the number of people in a room using video cameras or motion recognition sensors, and reliability can be improved by removing a dead zone. [Reference numerals] (100) Sensor unit; (200) Storage unit; (300) Dynamic neural network unit; (400) Neural network learning unit
Abstract translation: 本发明涉及一种基于使用动态神经网络的二氧化碳浓度来估计房间中的人数的系统。 该系统包括：用于测量室内空气中所含二氧化碳浓度的传感器单元; 用于存储由传感器单元测量的二氧化碳浓度的存储单元; 至少一个动态神经网络单元，用于使用存储在所述存储单元中的二氧化碳的浓度来估计位于房间中的残留人的数量; 以及神经网络学习单元，用于将由动态神经网络单元估计的残差人数与对于剩余人数预先输入的参考值进行比较，将剩余人数与参考值之间的误差与预定阈值进行比较 并且调整在参考值的误差减小的方向上配置动态神经网络单元的传递函数的加权值和偏转值，并且提出一种有效地抓住建筑房间中的人的技术。 因此，安装和维护成本比使用摄像机或运动识别传感器检查房间中的人数的常规方法的成本便宜，并且可以通过去除死区来提高可靠性。 （附图标记）（100）传感器单元; （200）存储单元; （300）动态神经网络单元; （400）神经网络学习单元
-
-
-
Search Results
4
records
(took 0.04 seconds)
