Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.
Tosolve complex and diverse social problems and ensure the quality of life of individuals, social robots that can interact with humans are attracting attention. In the past, robots were recognized as beings that provide labor force as they put into industrial sites on behalf of humans. However, the concept of today's robot has been extended to social robots that coexist with humans and enable social interaction with the advent of Smart technology, which is considered an important driver in most industries. Specifically, there are service robots that respond to customers, the robots that have the purpose of edutainment, and the emotionalrobots that can interact with humans intimately. However, popularization of robots is not felt despite the current information environment in the modern ICT service environment and the 4th industrial revolution. Considering social interaction with users which is an important function of social robots, not only the technology of the robots but also other factors should be considered. The design elements of the robot are more important than other factors tomake consumers purchase essentially a social robot. In fact, existing studies on social robots are at the level of proposing "robot development methodology" or testing the effects provided by social robots to users in pieces. On the other hand, consumer emotions felt from the robot's appearance has an important influence in the process of forming user's perception, reasoning, evaluation and expectation. Furthermore, it can affect attitude toward robots and good feeling and performance reasoning, etc. Therefore, this study aims to verify the effect of appearance of social robot and consumer emotions on consumer's attitude toward social robot. At this time, a social robot design evaluation model is constructed by combining heterogeneous data from different sources. Specifically, the three quantitative indicator data for the appearance of social robots from the ABOT Database is included in the model. The consumer emotions of social robot design has been collected through (1) the existing design evaluation literature and (2) online buzzsuch as product reviews and blogs, (3) qualitative interviews for social robot design. Later, we collected the score of consumer emotions and attitudes toward various social robots through a large-scale consumer survey. First, we have derived the six major dimensions of consumer emotions for 23 pieces of detailed emotions through dimension reduction methodology. Then, statistical analysis was performed to verify the effect of derived consumer emotionson attitude toward social robots. Finally, the moderated regression analysis was performed to verify the effect of quantitatively collected indicators of social robot appearance on the relationship between consumer emotions and attitudes toward social robots. Interestingly, several significant moderation effects were identified, these effects are visualized with two-way interaction effect to interpret them from multidisciplinary perspectives. This study has theoretical contributions from the perspective of empirically verifying all stages from technical properties to consumer's emotion and attitudes toward social robots by linking the data from heterogeneous sources. It has practical significance that the result helps to develop the design guidelines based on consumer emotions in the design stage of social robot development.
Since financial crisis of IMF resulted in intensive competitiveness and adverse management environment, many hotel industries have responded it with restructuring. Since this restructuring is accompanied by reduction of employees, hence comes the recognition of justice in the procedure of restructuring. When the surviving employees in the restructuring process recognize unfairness in the procedure and practical operations, organization effectiveness can not be maintained due to losing trust of their employers. In this paper I will examine the relationship between validity of restructuring and compensatory programs for layoffs and surviving employees' trust of the employers. Also I will find out the relationship between remaining employees' trust of the employers and their job satisfaction and organization commitment. Through this relationship, we can prepare an alternative to reduce negative effect of restructuring. The hypotheses of this study are proposed as follows: H1: The higher surviving employees' recognition of procedural justice in restructuring process is, the higher their trust with a manager of the company is. H2: The higher surviving employees' recognition of distributive justice in restructuring process is, the higher their trust with a manager of the company is. H3: The higher surviving employees' recognition of procedural justice in restructuring process is, the higher their job satisfaction is. H4: The higher surviving employees' recognition of distributive justice in restructuring process is, the higher their job satisfaction is. H5: The higher surviving employees' recognition of procedural justice in restructuring process is, the higher their organization commitment is. H6: The higher surviving employees' recognition of distributive justice in restructuring process is, the higher their organization commitment is. H7: The higher surviving employees' trust with a manager of the company in restructuring process is, the higher their job satisfaction is. H8: The higher surviving employees' trust with a manager of the company in restructuring process is, the higher their organization commitment is. For the purposes of this study, employees working in luxury hotels located in Seoul were targeted. Self-administered questionnaires were distributed to those who consented with the investigation after explaining the purpose of the survey. A total of 500 questionnaires were distributed and 450 questionnaire were returned to the researcher for analysis. 430 of the returned questionnaires were used for analysis. As for the education for this survey, 250 junior college graduates or under (58.1%), 143 college graduates (33.3%) and 37 graduate school graduates (8.6%). As for the marital status, 315 persons (73.3%) are single and 115 are married (26.7%). As for the monthly income, 49 people (11.48%) are less than 2 million won, 148 (34.4%) are between 2 million and less than 2.5 million won, 153 (35.6%) are between 2.5 million to less than 3 million won, 80 (18.6%) are more than 3 million won. As for the workplace, 293 people (68.1%) work for the F&B department, 73 (17.0%) for rooms department, 41 (9.5%) for operation/ marketing department, 23 (5.3%) for account/ general affair department. As for the period of employment, 85 people (19.8%) are less than 5 years, 150 (34.9%) are between 6 to 9 years, 143 (33.3%) are between 10 to 14 years. and 52 (3.%) are more than 15 years. An exploratory factor analysis was used to survey validity and reliability of calculating tool on perceived values. This study used correlation between individual items and whole items and Cronbach's alpha value of multiple-item scale which is usually used to assess scale and reliability. Reliability of conceptual sub-dimension was assessed by basing on repeated procedure of correlation between individual items and whole items and factor loading. 1. Verification of correlation between validity of restructuring and trust This research showed that procedural and distributive justice of restructuring affects trust positively. The path coefficient between procedural justice of restructuring and trust is 0.719(t=10.135, p=0.000), and thereby the higher procedural justice results in higher trust. The path coefficient between distributive justice of restructuring and trust is 0.160(t=3.291, p=0.001), and thereby the higher distributive justice results in higher trust. Hence H1 and H2 are accepted. 2. Verification of correlation between validity of restructuring and job satisfaction The path coefficient between procedural justice of restructuring and job satisfaction is 0.179(t=2.202, p=0.028), and thereby the higher procedural justice results in higher job satisfaction. The path coefficient between distributive justice of restructuring and job satisfaction is 0.074(t=1.620, p=0.105), and thereby distributive justice of restructuring has no relationship with job satisfaction. Hence H3 is accepted, but H4 is removed. 3. Verification of correlation between validity of restructuring and organization commitment The path coefficient between procedural justice of restructuring and organization commitment is 0.188(t=2.466, p=0.014), and thereby the higher procedural justice results in higher organization commitment. The path coefficient between distributive justice of restructuring and organization commitment is 0.118(t=2.720, p=0.007), and thereby the higher distributive justice results in higher organization commitment. Hence H5 and H6 are accepted. 4. Verification of correlation between trust and job satisfaction The path coefficient between trust and job satisfaction is 0.610(t=6.736, p=0.000), and thereby the correlation has a meaningful result. Since the higher trust of the employer results in higher job satisfaction, H7 is accepted. 5. Verification of correlation between trust and organization commitment The path coefficient between procedural justice of restructuring and job satisfaction is 0.446(t=5.547 p=0.000), and thereby the higher trust of the employer results in higher organization commitment. Hence H8 is accepted. This research aimed to help the employers of hotel industries by analyzing the effects of validity of restructuring on employees' trust, job satisfaction and organization commitment. The research found that employer's validity of restructuring has significant affects on the degree of employee's trust with a manager, thereby reducing the negative effects of restructuring and enhancing organization commitment and job satisfaction. The principal purpose of this research is to confirm the correlation between employees' perceived validity of restructuring and their trust with a manager. Also whether this correlation results in competitive edge of the company is also investigated. It is also pointed out that employees had to participated the procedure of restructuring, sharing the philosophy and reason of restructuring. This participation and furthermore compensatory methods can reduce employees' anxiety of organization operations. Variable of trust appeared to have impact on intermediation effect between perceived variable of validity and job satisfaction, organization commitment, so that increase of trust with a manager plays an crucial role in increasing organization effectiveness. Since this research did not cover whole hotel industries which underwent restructuring, it showed a limit. Unlike previous studies which dealt with validity and trust of superior bosses, this research focussed on employers. Also the organization citizenship which is not considered in this study will be dealt with in the future study.