• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.113-129
• /
• 2015

Location branding is a very important income making activity, by giving special meanings to a specific location while producing identity and communal value which are based around the understanding of a place's location branding concept methodology. Many other areas, such as marketing, architecture, and city construction, exert an influence creating an impressive brand image. A place brand which shows great recognition to both native people of S. Korea and foreigners creates significant economic effects. There has been research on creating a strategically and detailed place brand image, and the representative research has been carried out by Anholt who surveyed two million people from 50 different countries. However, the investigation, including survey research, required a great deal of effort from the workforce and required significant expense. As a result, there is a need to make more affordable, objective and effective research methods. The purpose of this paper is to find a way to measure the intensity of the image of the brand objective and at a low cost through text mining purposes. The proposed method extracts the keyword and the factors constructing the location brand image from the related web documents. In this way, we can measure the brand image intensity of the specific location. The performance of the proposed methodology was verified through comparison with Anholt's 50 city image consistency index ranking around the world. Four methods are applied to the test. First, RNADOM method artificially ranks the cities included in the experiment. HUMAN method firstly makes a questionnaire and selects 9 volunteers who are well acquainted with brand management and at the same time cities to evaluate. Then they are requested to rank the cities and compared with the Anholt's evaluation results. TM method applies the proposed method to evaluate the cities with all evaluation criteria. TM-LEARN, which is the extended method of TM, selects significant evaluation items from the items in every criterion. Then the method evaluates the cities with all selected evaluation criteria. RMSE is used to as a metric to compare the evaluation results. Experimental results suggested by this paper's methodology are as follows: Firstly, compared to the evaluation method that targets ordinary people, this method appeared to be more accurate. Secondly, compared to the traditional survey method, the time and the cost are much less because in this research we used automated means. Thirdly, this proposed methodology is very timely because it can be evaluated from time to time. Fourthly, compared to Anholt's method which evaluated only for an already specified city, this proposed methodology is applicable to any location. Finally, this proposed methodology has a relatively high objectivity because our research was conducted based on open source data. As a result, our city image evaluation text mining approach has found validity in terms of accuracy, cost-effectiveness, timeliness, scalability, and reliability. The proposed method provides managers with clear guidelines regarding brand management in public and private sectors. As public sectors such as local officers, the proposed method could be used to formulate strategies and enhance the image of their places in an efficient manner. Rather than conducting heavy questionnaires, the local officers could monitor the current place image very shortly a priori, than may make decisions to go over the formal place image test only if the evaluation results from the proposed method are not ordinary no matter what the results indicate opportunity or threat to the place. Moreover, with co-using the morphological analysis, extracting meaningful facets of place brand from text, sentiment analysis and more with the proposed method, marketing strategy planners or civil engineering professionals may obtain deeper and more abundant insights for better place rand images. In the future, a prototype system will be implemented to show the feasibility of the idea proposed in this paper.

• Fiber Technology and Industry
• /
• v.2 no.4
• /
• pp.490-508
• /
• 1998

One of the latest fields of research in the area of output devices is tactual display devices [13,31]. These tactual or haptic devices allow the user to receive haptic feedback output from a variety of sources. This allows the user to actually feel virtual objects and manipulate them by touch. This is an emerging technology and will be instrumental in enhancing the realism of wearable augmented environments for certain applications. Tactual displays have previously been used for scientific visualization in virtual environments by chemists and engineers to improve perception and understanding of force fields and of world models populated with the impenetrable. In addition to tactual displays, the use of wearable audio displays that allow sound to be spatialized are being developed. With wearable computers, designers will soon be able to pair spatialized sound to virtual representations of objects when appropriate to make the wearable computer experience even more realistic to the user. Furthermore, as the number and complexity of wearable computing applications continues to grow, there will be increasing needs for systems that are faster, lighter, and have higher resolution displays. Better networking technology will also need to be developed to allow all users of wearable computers to have high bandwidth connections for real time information gathering and collaboration. In addition to the technology advances that make users need to wear computers in everyday life, there is also the desire to have users want to wear their computers. In order to do this, wearable computing needs to be unobtrusive and socially acceptable. By making wearables smaller and lighter, or actually embedding them in clothing, users can conceal them easily and wear them comfortably. The military is currently working on the development of the Personal Information Carrier (PIC) or digital dog tag. The PIC is a small electronic storage device containing medical information about the wearer. While old military dog tags contained only 5 lines of information, the digital tags may contain volumes of multi-media information including medical history, X-rays, and cardiograms. Using hand held devices in the field, medics would be able to call this information up in real time for better treatment. A fully functional transmittable device is still years off, but this technology once developed in the military, could be adapted tp civilian users and provide ant information, medical or otherwise, in a portable, not obstructive, and fashionable way. Another future device that could increase safety and well being of its users is the nose on-a-chip developed by the Oak Ridge National Lab in Tennessee. This tiny digital silicon chip about the size of a dime, is capable of 'smelling' natural gas leaks in stoves, heaters, and other appliances. It can also detect dangerous levels of carbon monoxide. This device can also be configured to notify the fire department when a leak is detected. This nose chip should be commercially available within 2 years, and is inexpensive, requires low power, and is very sensitive. Along with gas detection capabilities, this device may someday also be configured to detect smoke and other harmful gases. By embedding this chip into workers uniforms, name tags, etc., this could be a lifesaving computational accessory. In addition to the future safety technology soon to be available as accessories are devices that are for entertainment and security. The LCI computer group is developing a Smartpen, that electronically verifies a user's signature. With the increase in credit card use and the rise in forgeries, is the need for commercial industries to constantly verify signatures. This Smartpen writes like a normal pen but uses sensors to detect the motion of the pen as the user signs their name to authenticate the signature. This computational accessory should be available in 1999, and would bring increased peace of mind to consumers and vendors alike. In the entertainment domain, Panasonic is creating the first portable hand-held DVD player. This device weight less than 3 pounds and has a screen about 6' across. The color LCD has the same 16:9 aspect ratio of a cinema screen and supports a high resolution of 280,000 pixels and stereo sound. The player can play standard DVD movies and has a hour battery life for mobile use. To summarize, in this paper we presented concepts related to the design and use of wearable computers with extensions to smart spaces. For some time, researchers in telerobotics have used computer graphics to enhance remote scenes. Recent advances in augmented reality displays make it possible to enhance the user's local environment with 'information'. As shown in this paper, there are many application areas for this technology such as medicine, manufacturing, training, and recreation. Wearable computers allow a much closer association of information with the user. By embedding sensors in the wearable to allow it to see what the user sees, hear what the user hears, sense the user's physical state, and analyze what the user is typing, an intelligent agent may be able to analyze what the user is doing and try to predict the resources he will need next or in the near future. Using this information, the agent may download files, reserve communications bandwidth, post reminders, or automatically send updates to colleagues to help facilitate the user's daily interactions. This intelligent wearable computer would be able to act as a personal assistant, who is always around, knows the user's personal preferences and tastes, and tries to streamline interactions with the rest of the world.

• Korean Journal of Environmental Biology
• /
• v.39 no.4
• /
• pp.526-535
• /
• 2021

Spatial sampling design plays an important role in GIS-based modeling studies because it increases modeling efficiency while reducing the cost of sampling. In the field of agricultural systems, research demand for high-resolution spatial databased modeling to predict and evaluate climate change impacts is growing rapidly. Accordingly, the need and importance of spatial sampling design are increasing. The purpose of this study was to design spatial sampling of paddy fields (11,386 grids with 1 km spatial resolution) in Korea for use in agricultural spatial modeling. A stratified random sampling design was developed and applied in 2030s, 2050s, and 2080s under two RCP scenarios of 4.5 and 8.5. Twenty-five weather and four soil characteristics were used as stratification variables. Stratification and sample allocation were optimized to ensure minimum sample size under given precision constraints for 16 target variables such as crop yield, greenhouse gas emission, and pest distribution. Precision and accuracy of the sampling were evaluated through sampling simulations based on coefficient of variation (CV) and relative bias, respectively. As a result, the paddy field could be optimized in the range of 5 to 21 strata and 46 to 69 samples. Evaluation results showed that target variables were within precision constraints (CV<0.05 except for crop yield) with low bias values (below 3%). These results can contribute to reducing sampling cost and computation time while having high predictive power. It is expected to be widely used as a representative sample grid in various agriculture spatial modeling studies.

• Korean small business review
• /
• v.33 no.4
• /
• pp.77-93
• /
• 2011

Since 2000, the employment rate of small and medium enterprises (SMEs) has dwindled while the creation of new jobs and the emergence of healthy SMEs have been stagnant. The fundamental reason for these symptoms is that the economic structure is disadvantageous to SMEs. In particular, the greater gap between SMEs and large enterprises has resulted in polarization, and the resulting imbalance has become the largest obstacle to improving SMEs' competitiveness. For example, the total productivity has continued to drop, and the average productivity of SMEs is now merely 30% of that of large enterprises, and the average wage of SMEs' employees is only 53% of that of large enterprises. Along with polarization, rapid industrialization has also caused anti-enterprise consensus, the collapse of the middle class, hostility towards establishments, and other aftereffects. The general consensus is that unless these problems are solved, South Korea will not become an advanced country. Especially, South Korea is now facing issues that need urgent measures, such as the decline of its economic growth, the worsening distribution of profits, and the increased external volatility. Recognizing such negative trends, the MB administration proposed a win-win growth policy and recently introduced a new national value called "ecosystemic development." As the terms in such policy agenda are similar, however, the conceptual differences among such terms must first be fully understood. Therefore, in this study, the concepts of win-win growth policy and ecosystemic development, and the need for them, were surveyed, and their differences from and similarities with other policy concepts like win-win cooperation and symbiotic development were examined. Based on the results of the survey and examination, the study introduced a South Korean model of win-win growth, targeting the promotion of a sound balance between large enterprises and SMEs and an innovative ecosystem, and finally, proposing future policy tasks. Win-win growth is not an academic term but a policy term. Thus, it is less advisable to give a theoretical definition of it than to understand its concept based on its objective and method as a policy. The core of the MB administration's win-win growth policy is the creation of a partnership between key economic subjects such as large enterprises and SMEs based on each subject's differentiated capacity, and such economic subjects' joint promotion of growth opportunities. Its objective is to contribute to the establishment of an advanced capitalistic system by securing the sustainability of the South Korean economy. Such win-win growth policy includes three core concepts. The first concept, ecosystem, is that win-win growth should be understood from the viewpoint of an industrial ecosystem and should be pursued by overcoming the issues of specific enterprises. An enterprise is not an independent entity but a social entity, meaning it exists in relationship with the society (Drucker, 2011). The second concept, balance, points to the fact that an effort should be made to establish a systemic and social infrastructure for a healthy balance in the industry. The social system and infrastructure should be established in such a way as to create a balance between short- term needs and long-term sustainability, between freedom and responsibility, and between profitability and social obligations. Finally, the third concept is the behavioral change of economic entities. The win-win growth policy is not merely about simple transactional relationships or determining reasonable prices but more about the need for a behavior change on the part of economic entities, without which the objectives of the policy cannot be achieved. Various advanced countries have developed different win-win growth models based on their respective cultures and economic-development stages. Japan, whose culture is characterized by a relatively high level of group-centered trust, has developed a productivity improvement model based on such culture, whereas the U.S., which has a highly developed system of market capitalism, has developed a system that instigates or promotes market-oriented technological innovation. Unlike Japan or the U.S., Europe, a late starter, has not fully developed a trust-based culture or market capitalism and thus often uses a policy-led model based on which the government leads the improvement of productivity and promotes technological innovation. By modeling successful cases from these advanced countries, South Korea can establish its unique win-win growth system. For this, it needs to determine the method and tasks that suit its circumstances by examining the prerequisites for its success as well as the strengths and weaknesses of each advanced country. This paper proposes a South Korean model of win-win growth, whose objective is to upgrade the country's low-trust-level-based industrial structure, in which large enterprises and SMEs depend only on independent survival strategies, to a high-trust-level-based social ecosystem, in which large enterprises and SMEs develop a cooperative relationship as partners. Based on this objective, the model proposes the establishment of a sound balance of systems and infrastructure between large enterprises and SMEs, and to form a crenovative social ecosystem. The South Korean model of win-win growth consists of three axes: utilization of the South Koreans' potential, which creates community-oriented energy; fusion-style improvement of various control and self-regulated systems for establishing a high-trust-level-oriented social infrastructure; and behavioral change on the part of enterprises in terms of putting an end to their unfair business activities and promoting future-oriented cooperative relationships. This system will establish a dynamic industrial ecosystem that will generate creative energy and will thus contribute to the realization of a sustainable economy in the 21st century. The South Korean model of win-win growth should pursue community-based self-regulation, which promotes the power of efficiency and competition that is fundamentally being pursued by capitalism while at the same time seeking the value of society and community. Already existing in Korea's traditional roots, such objectives have become the bases of the Shinbaram culture, characterized by the South Koreans' spontaneity, creativity, and optimism. In the process of a community's gradual improvement of its rules and procedures, the trust among the community members increases, and the "social capital" that guarantees the successful control of shared resources can be established (Ostrom, 2010). This basic ideal can help reduce the gap between large enterprises and SMEs, alleviating the South Koreans' victim mentality in the face of competition and the open-door policy, and creating crenovative corporate competitiveness. The win-win growth policy emerged for the purpose of addressing the polarization and imbalance structure resulting from the evolution of 21st-century capitalism. It simultaneously pursues efficiency and fairness on one hand and economic and community values on the other, and aims to foster efficient interaction between the market and the government. This policy, however, is also evolving. The win-win growth policy can be considered an extension of the win-win cooperation that the past 'Participatory Government' promoted at the enterprise management level to the level of systems and culture. Also, the ecosystemic development agendum that has recently emerged is a further extension that has been presented as a national ideal of "a new development model that promotes the co-advancement of environmental conservation, growth, economic development, social integration, and national and individual development."

• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.107-118
• /
• 2016

The advent of 5G mobile communications, which is expected in 2020, will provide many services such as Internet of Things (IoT) and vehicle-to-infra/vehicle/nomadic (V2X) communication. There are many requirements to realizing these services: reduced latency, high data rate and reliability, and real-time service. In particular, a high level of reliability and delay sensitivity with an increased data rate are very important for M2M, IoT, and Factory 4.0. Around the world, 5G standardization organizations have considered these services and grouped them to finally derive the technical requirements and service scenarios. The first scenario is broadcast services that use a high data rate for multiple cases of sporting events or emergencies. The second scenario is as support for e-Health, car reliability, etc.; the third scenario is related to VR games with delay sensitivity and real-time techniques. Recently, these groups have been forming agreements on the requirements for such scenarios and the target level. Various techniques are being studied to satisfy such requirements and are being discussed in the context of software-defined networking (SDN) as the next-generation network architecture. SDN is being used to standardize ONF and basically refers to a structure that separates signals for the control plane from the packets for the data plane. One of the best examples for low latency and high reliability is an intelligent traffic system (ITS) using V2X. Because a car passes a small cell of the 5G network very rapidly, the messages to be delivered in the event of an emergency have to be transported in a very short time. This is a typical example requiring high delay sensitivity. 5G has to support a high reliability and delay sensitivity requirements for V2X in the field of traffic control. For these reasons, V2X is a major application of critical delay. V2X (vehicle-to-infra/vehicle/nomadic) represents all types of communication methods applicable to road and vehicles. It refers to a connected or networked vehicle. V2X can be divided into three kinds of communications. First is the communication between a vehicle and infrastructure (vehicle-to-infrastructure; V2I). Second is the communication between a vehicle and another vehicle (vehicle-to-vehicle; V2V). Third is the communication between a vehicle and mobile equipment (vehicle-to-nomadic devices; V2N). This will be added in the future in various fields. Because the SDN structure is under consideration as the next-generation network architecture, the SDN architecture is significant. However, the centralized architecture of SDN can be considered as an unfavorable structure for delay-sensitive services because a centralized architecture is needed to communicate with many nodes and provide processing power. Therefore, in the case of emergency V2X communications, delay-related control functions require a tree supporting structure. For such a scenario, the architecture of the network processing the vehicle information is a major variable affecting delay. Because it is difficult to meet the desired level of delay sensitivity with a typical fully centralized SDN structure, research on the optimal size of an SDN for processing information is needed. This study examined the SDN architecture considering the V2X emergency delay requirements of a 5G network in the worst-case scenario and performed a system-level simulation on the speed of the car, radius, and cell tier to derive a range of cells for information transfer in SDN network. In the simulation, because 5G provides a sufficiently high data rate, the information for neighboring vehicle support to the car was assumed to be without errors. Furthermore, the 5G small cell was assumed to have a cell radius of 50-100 m, and the maximum speed of the vehicle was considered to be 30-200 km/h in order to examine the network architecture to minimize the delay.

• Economic and Environmental Geology
• /
• v.39 no.4 s.179
• /
• pp.369-384
• /
• 2006

Korean Peninsula, located on the southeastern part of Eurasian plate, belongs to the intraplate region. The characteristics of intraplate earthquake show the low and rare seismicity and the sparse and irregular distribution of epicenters comparing to interplate earthquake. To evaluate the exact seismic activity in intraplate region, long-term seismic data including historical earthquake data should be archived. Fortunately the long-term historical earthquake records about 2,000 years are available in Korea Peninsula. By the analysis of this historical and instrumental earthquake data, seismic activity was very high in 16-18 centuries and is more active at the Yellow sea area than East sea area. Comparing to the high seismic activity of the north-eastern China in 16-18 centuries, it is inferred that seismic activity in two regions shows close relationship. Also general trend of epicenter distribution shows the SE-NW direction. In Korea Peninsula, the first seismic station was installed at Incheon in 1905 and 5 additional seismic stations were installed till 1943. There was no seismic station from 1945 to 1962, but a World Wide Standardized Seismograph was installed at Seoul in 1963. In 1990, Korean Meteorological Adminstration(KMA) had established centralized modem seismic network in real-time, consisted of 12 stations. After that time, many institutes tried to expand their own seismic networks in Korea Peninsula. Now KMA operates 35 velocity-type seismic stations and 75 accelerometers and Korea Institute of Geoscience and Mineral Resources operates 32 and 16 stations, respectively. Korea Institute of Nuclear Safety and Korea Electric Power Research Institute operate 4 and 13 stations, consisted of velocity-type and accelerometer. In and around the Korean Peninsula, 27 intraplate earthquake mechanisms since 1936 were analyzed to understand the regional stress orientation and tectonics. These earthquakes are largest ones in this century and may represent the characteristics of earthquake in this region. Focal mechanism of these earthquakes show predominant strike-slip faulting with small amount of thrust components. The average P-axis is almost horizontal ENE-WSW. In north-eastern China, strike-slip faulting is dominant and nearly horizontal average P-axis in ENE-WSW is very similar with the Korean Peninsula. On the other hand, in the eastern part of East Sea, thrust faulting is dominant and average P-axis is horizontal with ESE-WNW. This indicate that not only the subducting Pacific Plate in east but also the indenting Indian Plate controls earthquake mechanism in the far east of the Eurasian Plate. Crustal velocity model is very important to determine the hypocenters of the local earthquakes. But the crust model in and around Korean Peninsula is not clear till now, because the sufficient seismic data could not accumulated. To solve this problem, reflection and refraction seismic survey and seismic wave analysis method were simultaneously applied to two long cross-section traversing the southern Korean Peninsula since 2002. This survey should be continuously conducted.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.25-38
• /
• 2019

Selecting high-quality information that meets the interests and needs of users among the overflowing contents is becoming more important as the generation continues. In the flood of information, efforts to reflect the intention of the user in the search result better are being tried, rather than recognizing the information request as a simple string. Also, large IT companies such as Google and Microsoft focus on developing knowledge-based technologies including search engines which provide users with satisfaction and convenience. Especially, the finance is one of the fields expected to have the usefulness and potential of text data analysis because it's constantly generating new information, and the earlier the information is, the more valuable it is. Automatic knowledge extraction can be effective in areas where information flow is vast, such as financial sector, and new information continues to emerge. However, there are several practical difficulties faced by automatic knowledge extraction. First, there are difficulties in making corpus from different fields with same algorithm, and it is difficult to extract good quality triple. Second, it becomes more difficult to produce labeled text data by people if the extent and scope of knowledge increases and patterns are constantly updated. Third, performance evaluation is difficult due to the characteristics of unsupervised learning. Finally, problem definition for automatic knowledge extraction is not easy because of ambiguous conceptual characteristics of knowledge. So, in order to overcome limits described above and improve the semantic performance of stock-related information searching, this study attempts to extract the knowledge entity by using neural tensor network and evaluate the performance of them. Different from other references, the purpose of this study is to extract knowledge entity which is related to individual stock items. Various but relatively simple data processing methods are applied in the presented model to solve the problems of previous researches and to enhance the effectiveness of the model. From these processes, this study has the following three significances. First, A practical and simple automatic knowledge extraction method that can be applied. Second, the possibility of performance evaluation is presented through simple problem definition. Finally, the expressiveness of the knowledge increased by generating input data on a sentence basis without complex morphological analysis. The results of the empirical analysis and objective performance evaluation method are also presented. The empirical study to confirm the usefulness of the presented model, experts' reports about individual 30 stocks which are top 30 items based on frequency of publication from May 30, 2017 to May 21, 2018 are used. the total number of reports are 5,600, and 3,074 reports, which accounts about 55% of the total, is designated as a training set, and other 45% of reports are designated as a testing set. Before constructing the model, all reports of a training set are classified by stocks, and their entities are extracted using named entity recognition tool which is the KKMA. for each stocks, top 100 entities based on appearance frequency are selected, and become vectorized using one-hot encoding. After that, by using neural tensor network, the same number of score functions as stocks are trained. Thus, if a new entity from a testing set appears, we can try to calculate the score by putting it into every single score function, and the stock of the function with the highest score is predicted as the related item with the entity. To evaluate presented models, we confirm prediction power and determining whether the score functions are well constructed by calculating hit ratio for all reports of testing set. As a result of the empirical study, the presented model shows 69.3% hit accuracy for testing set which consists of 2,526 reports. this hit ratio is meaningfully high despite of some constraints for conducting research. Looking at the prediction performance of the model for each stocks, only 3 stocks, which are LG ELECTRONICS, KiaMtr, and Mando, show extremely low performance than average. this result maybe due to the interference effect with other similar items and generation of new knowledge. In this paper, we propose a methodology to find out key entities or their combinations which are necessary to search related information in accordance with the user's investment intention. Graph data is generated by using only the named entity recognition tool and applied to the neural tensor network without learning corpus or word vectors for the field. From the empirical test, we confirm the effectiveness of the presented model as described above. However, there also exist some limits and things to complement. Representatively, the phenomenon that the model performance is especially bad for only some stocks shows the need for further researches. Finally, through the empirical study, we confirmed that the learning method presented in this study can be used for the purpose of matching the new text information semantically with the related stocks.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.205-225
• /
• 2018

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.