A line parallel to the ground is frequently shown in our daily life, which enables us to guess its direction. Especially, such a guess tends to become clear when a vanishing line of the ground is shown together. In this paper, a vision based pallet measurement method is suggested, which uses a technique for estimating three-dimensional direction of a line parallel to the ground. The technique computes actually a vector heading to intersection of a given imaged line parallel to the ground and the ground vanishing line determined previously on calibrating a measurement camera. Through an experiment of measuring a real commercial pallet with various orientation and distance, we found that the technique could measure the orientation of the pallet correctly and accurately. The technique worked well even though an edge line available on the front plane of a pallet was almost parallel to the ground vanishing line.

In a most recent object tracking research work, applying Convolutional Neural Network and Recurrent Neural Network-based strategies become relevant for resolving the noticeable challenges in it, like, occlusion, motion, object, and camera viewpoint variations, changing several targets, lighting variations. In this paper, the LSTM Network-based Tracking association method has proposed where the technique capable of real-time multi-object tracking by creating one of the useful LSTM networks that associated with tracking, which supports the long term tracking along with solving challenges. The LSTM network is a different neural network defined in Keras as a sequence of layers, where the Sequential classes would be a container for these layers. This purposing network structure builds with the integration of tracking association on Keras neural-network library. The tracking process has been associated with the LSTM Network feature learning output and obtained outstanding real-time detection and tracking performance. In this work, the main focus was learning trackable objects locations, appearance, and motion details, then predicting the feature location of objects on boxes according to their initial position. The performance of the joint object tracking system has shown that the LSTM network is more powerful and capable of working on a real-time multi-object tracking process.

The early detection of diseases is important in agriculture because diseases are major threats of reducing crop yield for farmers. The shape and color of plant leaf are changed differently according to the disease. So we can detect and estimate the disease by inspecting the visual feature in leaf. This study presents a vision-based leaf classification method for detecting the diseases of tomato crop. ResNet-50 model was used to extract the visual feature in leaf and classify the disease of tomato crop, since the model showed the higher accuracy than the other ResNet models with different depths. We propose a new ensemble approach using several DCNN classifiers that have the same structure but have been trained at different ranges in the DCNN layers. Experimental result achieved accuracy of 97.19% for PlantVillage dataset. It validates that the proposed method effectively classify the disease of tomato crop.

The IoT(Internet of Things) service provides users with valuable services by collecting and analyzing data using Internet-connected IoT devices. Currently, IoT service platforms are accomplished by using edge computing to reduce the delay time required to collect data from IoT devices. However, if a user moves to another network with IoT device, the connection will be lost and IoT service will be suspended. To solve this problem, we proposes a service that automatically roaming IoT service when IoT device makes move. IoT roaming service provides a device automatic tracking management technique designed to continue receiving IoT services even if users move to other networks. To check if the proposed roaming service was effective, we implemented IoT roaming service and measured the data transfer time while move between networks along with devices while using IoT service. As a result, the average data transfer time was 124.62ms, and the average service interrupt time was 812.12ms. with this result, we can assume that the user could feel service interruption time very shortly and it will not affect the service experience. with IoT roaming service, we expect that it will present a method that stably providing IoT services even if user moves networks.

As a representative concept of the fourth industrial revolution era where everything is digitized, digital twin means analyzing and optimizing a complex system using a simulation model synchronized with the system. In this paper, we propose a digital twin simulation model for the efficient operation of urban railways in Busan. Due to the geopolitical nature of Busan, where there are many mountains and narrow roads, the railways are more useful than other public transportation. However, this inversely results in a high level of congestion, which is an inconvenience to citizens and may be fatal to the spread of the virus, such as COVID19. Considering these characteristics, the proposed model analyzes the congestion level of the railways in Busan. The model is developed based on a mathematical formalism called discrete-event system specification and deduces the congestion level and the average waiting time of passengers depending on the train schedule. In addition, a new schedule to reduce the congestion level is derived through particle swarm optimization, which helps the efficient operation of the railways. Although the model is developed for the railways in Busan, it can also be used for railways in other cities where a high level of congestion is a problem.

It has been increasingly difficult to predict the amounts of Acer mono sap to be collected due to droughts and cold waves caused by recent climate changes with few studies conducted on the prediction of its collection volume. This study thus set out to propose a Big Data prediction system based on meteorological information for the collection of Acer mono sap. The proposed system would analyze collected data and provide managers with a statistical chart of prediction values regarding climate factors to affect the amounts of Acer mono sap to be collected, thus enabling efficient work. It was designed based on Hadoop for data collection, treatment and analysis. The study also analyzed and proposed an optimal prediction model for climate conditions to influence the volume of Acer mono sap to be collected by applying a multiple regression analysis model based on Hadoop and Mahout.

Childhood verbal communication impacts children's language skills and has a positive effect as partners use more vocabulary. But reduction in family time, caused by lowered age for private education and so on, has reduced the chance for children to speak with partners who have a proficient language skill. This vacancy was naturally occupied by the media, which has become one of the cornerstones of the growth of kids' contents. Kids contents are making various attempts to expand the breadth of services. But most contents still focus on unilateral visual information delivery yet, so there is a limit to satisfy the vacancy of conversation partners. Therefore this paper suggests an ECA(Embodied conversational agent) to induce children's spoken conversation using a virtual character frequently used in kids contents. This system is implemented by the voice bot and agent model produced using an IBM assistant and Unity. As a result of using ECA for 66 children of 5-9 years old, it showed meaningful results in terms of induction of verbal communication.

In recent years, the PV plant is gradually increasing in korea and has begun to focus on PV system O&M(Operation and Management). The legacy PV system can hardly be gathering realtime information. That is why it is difficult for the facility to respond immediately to situations in which problems arise. This leads to economic losses due to reduced power generation. In this study, we implemented an RMC(Remote Maintenance Control) gateway that supports multi-area equipment(inverters, junction boxes, switchboards, environmental sensors) that are not limited to specific manufacturers. It provides a function to visualize the collected data. Users can easily check the power generation and operation status of PV system equipment. In the future, we will develop an algorithm capable of analyzing beta factors that cause equipment performance degradation, parts aging, and deterioration using data collected from facilities. We intend to use this algorithm as a fundamental technology for O&M by transplanting it to the RMC gateway.

The purpose of this study is to identify the effect of the innovation characteristics that AI Elderly Care Robots have on elderly consumers and to verify the acceptance or mediated resistance by the elderly of the innovation characteristics. Research was conducted throughout this study of the characteristics of the elderly so that the study results could contribute to the improvement of the quality and manufacture of AI Elderly Care Robots by lowering the psychological resistance of the elderly. Survey questions were answered by senior citizens aged 65 and older. The SPSS25 and AMOS22 programs were used for analysis. The analysis confirmed that innovation resistance has a significant mediated effect on the characteristics of elderly consumers and their willingness to accept the innovation characteristics of the AI Elderly Care Robots. Through this study, Ram's innovation resistance model has been verified empirically and it is estimated that by considering the specificities of elderly consumers and using the information to contribute to the development and modification of AI Elderly Care Robots will increase the willingness of the elderly to accept the innovation characteristics of the AI Elderly Care Robots.

Social viewing has become an increasingly common viewing pattern by combining SNS use with video-watching. Accordingly, social viewing has attracted much scholarly attention, but a more comprehensive understanding of the process and effects of social viewing is warranted. For this, this study incorporated social viewing motivations, viewer satisfaction, and the continuous use intention, taking the viewer's communicative behavior into account as a possible moderator. This study conducted an online survey (N=334). Among four motivations, enjoyment, sharing and expression were significant predictors of program and communication satisfaction. Information, however, was only associated with program satisfaction but not with communication satisfaction. The moderating effects of three communication behaviors, production, sharing, and reception, were discussed in the relationship between user motivations and viewing satisfaction and continuous use intention. Production behaviors played a significant moderating role in between enjoyment, information, sharing, and communication satisfaction. Sharing moderatied information, sharing, and program satisfaction, whereas reception was not a significant moderator.

This study is a preliminary study to design a character automation system that considers the facial characteristics of mammals. The experimental data of this study was conducted on dogs (dog breeds) and humans, which were designed to be used in many contents. First, data was extracted from 100 types of dogs and 100 human data. Second, the criteria for measuring the ratio of important parts of the dog and human face were suggested. In addition, a comparative analysis of the face of a dog and a human face is conducted. Lastly, by analyzing the main component(PCA), the most characteristic elements in the faces of dogs and humans were analyzed. As a result, it was confirmed that the length of the face, the size of the eyes, the length of the glabellar, and the length of the glabellar and other parts are important. Through this study, the features of the dog's face that are different from humans are expected to contribute to the animal character automation.