• Journal of Internet Computing and Services
• /
• v.16 no.1
• /
• pp.57-65
• /
• 2015

As information technology fusion is accelerated, the researches to improve the quality and productivity of crops inside a plant factory actively progress. Advanced growth environment management technology that can provide thermal environment and air flow suited to the growth of crops and considering the characteristics inside a facility is necessary to maximize productivity inside a plant factory. Currently running plant factories are designed to rely on experience or personal judgment; hence, design and operation technology specific to plant factories are not established, inherently producing problems such as uneven crop production due to the deviation of temperature and air flow and additional increases in energy consumption after prolonged cultivation. The optimization process has to be set up in advance for the arrangement of air flow devices and operation technology using computational fluid dynamics (CFD) during the design stage of a facility for plant factories to resolve the problems. In this study, the optimum arrangement and air flow of air circulation fans were investigated to save energy while minimizing temperature deviation at each point inside a plant factory using CFD. The condition for simulation was categorized into a total of 12 types according to installation location, quantity, and air flow changes in air circulation fans. Also, the variables of boundary conditions for simulation were set in the same level. The analysis results for each case showed that an average temperature of 296.33K matching with a set temperature and average air flow velocity of 0.51m/s suiting plant growth were well-maintained under Case 4 condition wherein two sets of air circulation fans were installed at the upper part of plant cultivation beds. Further, control of air circulation fan set under Case D yielded the most excellent results from Case D-3 conditions wherein air velocity at the outlet was adjusted to 2.9m/s.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.20 no.12
• /
• pp.844-861
• /
• 2008

The papers published in the Korean Journal of Air-Conditioning and Refrigeration Engineering during the year of 2007 have been reviewed. Focus has been put on current status of research in the aspect of heating, cooling, ventilation, sanitation and building environments. The conclusions are as follows. (1) The research trends of fluid engineering have been surveyed as groups of general fluid flow, fluid machinery and piping, etc. New research topics include micro nano fluid, micropump and fuel cell. Traditional CFD was still popular and widely used in research and development. Studies about fans and pumps were performed in the field of fluid machinery. Characteristics of flow and fin shape optimization are studied in the field of piping system. (2) The research works on heat transfer have been reviewed in the field of heat transfer characteristics, heat exchangers, and desiccant cooling systems. The research on heat transfer characteristics includes thermal transport in pulse tubes, high temperature superconductors, ground heat exchangers, fuel cell stacks and ice slurry systems. For the heat 'exchangers, the research on pin-tube heat exchanger, plate heat exchanger, condensers and gas coolers has been cordially implemented. The research works on heat transfer augmenting tubes have been also reported. For the desiccant cooling systems, the studies on the design and operating conditions for desiccant rotors as well as performance index are noticeable. (3) In the field of refrigeration, many papers were presented on the air conditioning system using CO2 as a refrigerant. The issues on the two-stage compression, the oil selection, and the appropriate oil charge were treated. The subjects of alternative refrigerants were also studied steadily. Hydrocarbons, DME and their mixtures were considered and various heat transfer correlations were proposed. (4) Research papers have been reviewed in the field of building facilities by grouping into the researches on heat and cold sources, air conditioning and air cleaning, ventilation and fire research including tunnel ventilation, flow control of piping system, and sound research with drain system. Main focuses have been addressed to the promotion of efficient or effective use of energy, which helps to save energy and results in reduced environmental pollution and operating cost. (5) Studies were mostly focused on analyzing the indoor environment in various spaces like cars, old tombs, machine rooms, and etc. in an architectural environmental field. Moreover, subjects of various fields such as the evaluation of noise, thermal environment, indoor air quality and development of energy analysis program were researched by various methods of survey, simulation, and field experiment.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.