• Journal of Practical Engineering Education
• /
• v.14 no.3
• /
• pp.491-498
• /
• 2022

In this paper, as a liberal arts course for non-major students, a case study of recurrent neural network SW practice, which is essential for designing a basic recurrent neural network subject curriculum, was developed. The developed SW practice case focused on understanding the operation principle of the recurrent neural network, and used a spreadsheet to check the entire visualized operation process. The developed recurrent neural network practice case consisted of creating supervised text completion training data, implementing the input layer, hidden layer, state layer (context node), and output layer in sequence, and testing the performance of the recurrent neural network on text data. The recurrent neural network practice case developed in this paper automatically completes words with various numbers of characters. Using the proposed recurrent neural network practice case, it is possible to create an artificial intelligence SW practice case that automatically completes by expanding the maximum number of characters constituting Korean or English words in various ways. Therefore, it can be said that the utilization of this case of basic practice of recurrent neural network is high.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.23-43
• /
• 2016

As a result of the growth of Internet data and the rapid development of Internet technology, "big data" analysis has gained prominence as a major approach for evaluating and mining enormous data for various purposes. Especially, in recent years, people tend to share their experiences related to their leisure activities while also reviewing others' inputs concerning their activities. Therefore, by referring to others' leisure activity-related experiences, they are able to gather information that might guarantee them better leisure activities in the future. This phenomenon has appeared throughout many aspects of leisure activities such as movies, traveling, accommodation, and dining. Apart from blogs and social networking sites, many other websites provide a wealth of information related to leisure activities. Most of these websites provide information of each product in various formats depending on different purposes and perspectives. Generally, most of the websites provide the average ratings and detailed reviews of users who actually used products/services, and these ratings and reviews can actually support the decision of potential customers in purchasing the same products/services. However, the existing websites offering information on leisure activities only provide the rating and review based on one stage of a set of evaluation criteria. Therefore, to identify the main issue for each evaluation criterion as well as the characteristics of specific elements comprising each criterion, users have to read a large number of reviews. In particular, as most of the users search for the characteristics of the detailed elements for one or more specific evaluation criteria based on their priorities, they must spend a great deal of time and effort to obtain the desired information by reading more reviews and understanding the contents of such reviews. Although some websites break down the evaluation criteria and direct the user to input their reviews according to different levels of criteria, there exist excessive amounts of input sections that make the whole process inconvenient for the users. Further, problems may arise if a user does not follow the instructions for the input sections or fill in the wrong input sections. Finally, treating the evaluation criteria breakdown as a realistic alternative is difficult, because identifying all the detailed criteria for each evaluation criterion is a challenging task. For example, if a review about a certain hotel has been written, people tend to only write one-stage reviews for various components such as accessibility, rooms, services, or food. These might be the reviews for most frequently asked questions, such as distance between the nearest subway station or condition of the bathroom, but they still lack detailed information for these questions. In addition, in case a breakdown of the evaluation criteria was provided along with various input sections, the user might only fill in the evaluation criterion for accessibility or fill in the wrong information such as information regarding rooms in the evaluation criteria for accessibility. Thus, the reliability of the segmented review will be greatly reduced. In this study, we propose an approach to overcome the limitations of the existing leisure activity information websites, namely, (1) the reliability of reviews for each evaluation criteria and (2) the difficulty of identifying the detailed contents that make up the evaluation criteria. In our proposed methodology, we first identify the review content and construct the lexicon for each evaluation criterion by using the terms that are frequently used for each criterion. Next, the sentences in the review documents containing the terms in the constructed lexicon are decomposed into review units, which are then reconstructed by using the evaluation criteria. Finally, the issues of the constructed review units by evaluation criteria are derived and the summary results are provided. Apart from the derived issues, the review units are also provided. Therefore, this approach aims to help users save on time and effort, because they will only be reading the relevant information they need for each evaluation criterion rather than go through the entire text of review. Our proposed methodology is based on the topic modeling, which is being actively used in text analysis. The review is decomposed into sentence units rather than considering the whole review as a document unit. After being decomposed into individual review units, the review units are reorganized according to each evaluation criterion and then used in the subsequent analysis. This work largely differs from the existing topic modeling-based studies. In this paper, we collected 423 reviews from hotel information websites and decomposed these reviews into 4,860 review units. We then reorganized the review units according to six different evaluation criteria. By applying these review units in our methodology, the analysis results can be introduced, and the utility of proposed methodology can be demonstrated.

• Horticultural Science & Technology
• /
• v.29 no.5
• /
• pp.461-466
• /
• 2011

In genetic and molecular breeding studies of plants, researchers need to design various kinds of primers based on their research purposes. So far many kinds of web- or script-based non-commercial programs for primer design are available. Because most of them do not include user interface for multipurpose usage including gene structure prediction and direct target selection on sequences, it has been a laborious work to design primers targeting on the exon or intron regions of interesting genes. Here we report a primer designing graphic user interface program, Pickprimer, that includes gene structure prediction and primer design modules by combining source codes of the Spidey and Primer3 programs. This program provides simple graphic user interface to input sequences and design primers. Genomic sequence and mRNA or coding sequence of genes can be copy and pasted or input as fasta or text files. Based on alignment of the input sequences using the Spidey module, a putative gene structure is graphically visualized along with exon-intron sequences of color codes. Primer design can be easily performed by dragging mouse on the displayed sequences or input primer targeting position with desirable values of primers. The output of designed primers with detailed information is provided by the Primer3 module. PCR evaluation of 24 selected primer sets successfully amplified single amplicons from six Brassica rapa cultivars. The Pickprimer will be a convenient tool for genetic and molecular breeding studies of plants.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.20 no.3
• /
• pp.243-251
• /
• 2018

The gridded simulation of crop growth, which would be useful for shareholders and policy makers, often requires specialized computation tasks for preparation of weather input data and operation of a given crop model. Here we developed an automated system to allow for crop growth simulation over a region using the DSSAT (Decision Support System for Agrotechnology Transfer) model. The system consists of modules implemented using R and shell script languages. One of the modules has a functionality to create weather input files in a plain text format for each cell. Another module written in R script was developed for GIS data processing and parallel computing. The other module that launches the crop model automatically was implemented using the shell script language. As a case study, the automated system was used to determine the maximum soybean yield for a given set of management options in Illinois state in the US. The AgMERRA dataset, which is reanalysis data for agricultural models, was used to prepare weather input files during 1981 - 2005. It took 7.38 hours to create 1,859 weather input files for one year of soybean growth simulation in Illinois using a single CPU core. In contrast, the processing time decreased considerably, e.g., 35 minutes, when 16 CPU cores were used. The automated system created a map of the maturity group and the planting date that resulted in the maximum yield in a raster data format. Our results indicated that the automated system for the DSSAT model would help spatial assessments of crop yield at a regional scale.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.6
• /
• pp.121-126
• /
• 2017

Recently, a lot of people use touch-pen devices such as smart phones and tab computers. To generate the picture and text, a user can give input or control the touch-pen device through simple or multi-touch gestures by touching the screen with a special stylus pen and/or one or more fingers. The accuracy and response time from the moment of contact with the touch board is very important to the touch device. Therefore, research is needed to find a way of removing the noise included in the touch signal quickly and efficiently. In this paper, we propose a method for removing a noise mixed in with a touch point coordinate which has been caused by a input pen on the touch screen. For effective filtering, the fast sampling of the coordinate corresponding to the noise from the input signal is required primarily. Secondly the total compensation of the touch coordinates using the characteristics of the B-Spline curve is applied to correct coordinates of the points. This method can ensure a real-time response than other algorithms. The applied performance evaluation method is comparing error pixels with evaluation values by dividing 10 intervals on the touch pad diagonally. Usually the average error is 7.1 pixels but our proposed method shows an average 4.1 errors. Therefore, our proposed touch pen method can express the input signal on the coordinates more correctly.

• Journal of KIISE
• /
• v.44 no.3
• /
• pp.306-313
• /
• 2017

Named entity recognition (NER) seeks to locate and classify named entities in text into pre-defined categories such as names of persons, organizations, locations, expressions of times, etc. Recently, many state-of-the-art NER systems have been implemented with bidirectional LSTM CRFs. Deep learning models based on long short-term memory (LSTM) generally depend on word representations as input. In this paper, we propose an approach to expand word representation by using pre-trained word embedding, part of speech (POS) tag embedding, syllable embedding and named entity dictionary feature vectors. Our experiments show that the proposed approach creates useful word representations as an input of bidirectional LSTM CRFs. Our final presentation shows its efficacy to be 8.05%p higher than baseline NERs with only the pre-trained word embedding vector.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.5
• /
• pp.974-983
• /
• 2017

In this paper, we have discussed the search function that can be embedded and used on Android-based applications. We used BM25 to suppress insignificant and too frequent words such as postpositions, Pivoted Length Normalization technique used to resolve the search priority problem related to each item's length, and Rocchio's method to pull items inferred to be related to the query closer to the query vector on Vector Space Model to support implicit feedback function. The index operation is divided into two methods; simple index to support offline operation and complex index for online operation. The implementation uses query inference function to guess user's future input by collating given present input with indexed data and with it the function is able to handle and correct user's error. Thus the implementation could be easily adopted into smartphone applications to improve their search functions.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.10
• /
• pp.4632-4641
• /
• 2011

The detailed production traceability information is a fundamental element in successful introduction and revitalization of traceability system. In this paper, we propose a production traceability information gathering system which is based on handwritten data digitalization technology in agro-livestock products. By the proposed system, we can effectively gather the detailed production traceability information with digital pen and the management ledger of paper document type by only writing the ledger. The server of the system generates the same digital image as the ledger and converts the handwritten data into digital text to insert the data into the database. Because the system is superior to data gathering system based on PC, PDA and touch screen in mobility, usability, data input speed, suitability in agro-livestock environment, it is possible to effectively gather traceability information of high quality by users even if they have low information ability and insufficient time to input data. We expect that the handwritten data digitalization technology is used to gather document based information in stage of manufacturing, distribution and marketing. In addition, this technology is applied to implementing advanced traceability system with RFID/USN based systems.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.674-679
• /
• 2017

In big-data environments wherein large amounts of text documents are produced daily, titles are very important clues that enable a prompt catching of the key ideas in documents; however, titles are absent for numerous document types such as blog articles and social-media messages. In this paper, a title-generation model for which sequence-to-sequence RNNs with attention and copying mechanisms are employed is proposed. For the proposed model, input sentences are encoded based on bi-directional GRU (gated recurrent unit) networks, and the title words are generated through a decoding of the encoded sentences with keywords that are automatically selected from the input sentences. Regarding the experiments with 93631 training-data documents and 500 test-data documents, the attention-mechanism performances are more effective (ROUGE-1: 0.1935, ROUGE-2: 0.0364, ROUGE-L: 0.1555) than those of the copying mechanism; in addition, the qualitative-evaluation radiative performance of the former is higher.

• Journal of Digital Convergence
• /
• v.14 no.7
• /
• pp.331-337
• /
• 2016

The purpose of this study is to provide a method to visualize the sound data to the three-dimensional image. The visualization of the sound data is performed according to the algorithm set after production of the text-based script that form the channel range of the sound data. The algorithm consists of a total of five levels, including setting sound channel range, setting picture frame for sound visualization, setting 3D image unit's property, extracting channel range of sound data and sound visualization, 3D visualization is performed with at least an operation signal input by the input device such as a mouse. With the sound files with the amount an animator can not finish in the normal way, 3D visualization method proposed in this study was highlighted that the low-cost, highly efficient way to produce creative artistic image by comparing the working time the animator with a study presented method and time for work. Future research will be the real-time visualization method of the sound data in a way that is going through a rendering process in the game engine.