The performance of convolutional deep learning networks is generally determined according to parameters of target dataset, structure of network, convolution kernel, activation function, and optimization algorithm. In this paper, a genetic algorithm is used to select the appropriate deep learning model and parameters for Alzheimer's classification and to compare the learning results with preliminary experiment. We compare and analyze the Alzheimer's disease classification performance of VGG-16, GoogLeNet, and ResNet to select an effective network for detecting AD and MCI. The simulation results show that the network structure is ResNet, the activation function is ReLU, the optimization algorithm is Adam, and the convolution kernel has a 3-dilated convolution filter for the accuracy of dementia medical images.

Recently, as e-learning technology advances, interaction and data exchange between lecturers and learners have become very important. In addition, accuracy of data delivery and efficiency of system implementation should be ensured. Considering these aspects, SignalR is the most suitable communication method for constructing an audience response system in e-learning. Existing audience response systems require separate wireless devices and have problems with system compatibility. SignalR, on the other hand, is capable of operating in all environments including PC programs, web, Android, and iOS, and has an advantage of being easy to develop applications. As such, SignalR is widely used in chatting functions for small scale, real-time communication system, and it has never been used to implement an audience response system. Thus, for the first time in this paper, an audience response system using SignalR was proposed and an experiment was conducted on whether it was applicable at the e-learning education field. Therefore, from the results fo an experiment, a variety of e-learning environments can be built through the audience response system using SignalR proposed in this paper.

Nowadays, one of the most common diseases is chronic mental fatigue syndrome. This can be caused by many factors, such as busy life, heavy workload, high population density, and adverse technological impact. Most office workers and students who are sitting all day long while being exposed to this kind of environments are likely to be involved in the mental illness. Therefore, to prevent the illness, it has been highly required to design a device that enables mental fatigue to be monitored continuously without human intervention. This paper proposes a linear regression method to reliably estimating the level of human mental fatigue using wearable physiological sensors, with an estimation error of 0.852. Also, this paper presents an Android application that is able to check mental health conditions in daily life.

Deep learning approach is emerging as a new way to improve the accuracy of tree species identification using bark image. However, the approach has not been studied enough because it is confronted with the problem of acquiring a large volume of bark image dataset. This study solved this problem by utilizing a pretrained off-the-shelf DCNN model. It compares the discrimination power of bark features extracted by each DCNN model. Then it extracts the features by using a selected DCNN model and feeds them to a multi-layer perceptron (MLP). We found out that the ResNet50 model is effective in extracting bark features and the MLP could be trained well with the features reduced by the principal component analysis. The proposed approach gives accuracy of 99.1% and 98.4% for BarkTex and Trunk12 datasets respectively.

In this paper, we consider the wireless-powered backscatter communication which consists of a power beacon, a source, a relay, and a destination. For the proposed wireless-powered backscatter communication, the source transmits its signals to both the relay and the destination via a backscattering channel and the relay which has a rechargeable battery performs an energy harvesting as well as an information forwarding based on the time switching relay (TSR) protocol. Based on the decode-and-forward (DF) relay transmission, we investigate performances of the proposed system in terms of outage probability and transmission rate in which the exact performance analysis of outage probability is given. Finally, some numerical examples are given to verify our provided analytical results for different system conditions.

The number of the PV systems installed in south korea has been gradually increasing. Interest of operation & management of PV System is rising up as PV System installation trends to increase. The vital function of operation & management is the monitoring system. Most monitoring systems are only available for equipment of suppliers and manufacturers. In this study, a monitoring system was implemented to support multi-domain equipment (inverter, junction box, water distribution board, environmental sensors) that are not limited to specific manufacturers. Monitoring system includes a visualization function, which makes it easy for users to check the power generation and the operation status of the equipment of PV System. In the future, this monitoring system will be utilized as an operation & maintenance foundation element in the PV system industry.

Detection of an anomaly pattern deviating normal data distribution in streaming data is an important technique in many application areas. In this paper, a method for detection of an newly emerging pattern in text streaming data which is an ordered sequence of texts is proposed based on text embedding and anomaly pattern detection. Using text embedding methods such as BOW(Bag Of Words), Word2Vec, and BERT, the detection performance of the proposed method is compared. Experimental results show that anomaly pattern detection using BERT embedding gave an average F1 value of 0.85 and the F1 value of 1 in three cases among five test cases.

In this paper, we proposed DEVS based programming education model that based on the cognitive information processing theory, not a grammatical programming education, and studied effectiveness analysis using computer thinking patterns. By creating a small range of patterns in the grammar which underlies the programming language and solving various examples through combinations, this paper shows an education method to develop problem-solving skills based on algorithmic thinking. The purpose of this study is to facilitate non-majors learn programming languages and understand patterned program structures when writing programs by patterning of control statements which the most important in learning programming.

Based on the risk factor evaluation for the file format, this paper defines the procedures for presenting the long-term preservation plan for that format and the technical information registry necessary for building the system. This is a procedure to perform a risk assessment for the format, evaluate the risk, and select a long-term preservation strategy based on the information registered in the registry and information on the external signature and internal signature of the electronic record. We also reviewed the criteria for selecting appropriate long-term preservation strategies in the process and provided the criteria for adopting each detailed strategy of migration and emulation, which are long-term preservation strategies. And we implemented this process as a long-term preservation decision support system. This system can be used to provide guidelines for the maintenance, management, service and long-term preservation of information resources of electronic records in public institutions such as National Archives of Korea and Libraries.

This study selected brand logos of six South Korean and Chinese banks including KB, IBK, SH, ICBC, ABC, and SISB, conducted Eye Tracking experiment among 36 South Korean and Chinese university students(Nine male and female students, respectively), and analyzed the difference of visual attention of consumers on bank brand logo, symbol, Korean/Chinese character logo types as well as the difference of visual attention of these consumers on English logo types. Results were represented by using statistics and visualization including GAZEPLOT, HEATMAP, and visual expression. Results showed that most generally gazed logo types more often and longer than symbols when they watched bank brand logos. A slight difference was observed between both groups in terms of gazing English logo types. This study has a implication that it proposed the possibility of drawing quantitative and reliable outcomes by utilizing eye tracking device and approaching in an objective standpoint beyond a methodological aspect on bank brand logo primarily leaning over the analysis of case research or design development. Moreover, findings are expected to serve as basic data for proposing the direction of special bank brand logo design and marketing strategies.

In this study, the factors affecting the acceptance intention for level 4-5 of autonomous vehicles were investigated by applying TAM(Technology Acceptance Model). To this end, 332 ordinary persons interested in autonomous vehicle and experienced in driving car were analyzed by using SEM(Structural Equation Modeling). The results showed that self-efficacy and personal innovation had a positive effect on perceived usefulness. On the other hand personal innovation has been shown to have a negative effect on perceived usefulness. Perceived ease of use has a positive effect on perceived usefulness, perceived ease of use and perceived usefulness has a positive effect on acceptance intention. Safety and Privacy has been shown to have a positive effect on trust, trust has a positive effect on acceptance intention. Lastly, autonomous vehicles have a higher impact on their 20s and 30s. The result of this study is expected to be a very useful basic research for the development of target autonomous vehicles, the selection of targets, the direction of corporate marketing strategies, and the preparation of government policies.