• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.229-235
• /
• 2024

Recent years have seen active research on methods for efficiently processing and interpreting large volumes of data in the fields of artificial intelligence and machine learning. One of these data processing technologies, Vector Symbolic Architecture (VSA), offers an innovative approach to representing complex symbols and data using high-dimensional vectors. VSA has garnered particular attention in various applications such as natural language processing, image recognition, and robotics. This study quantitatively evaluates the characteristics and performance of VSA methodologies by applying five VSA methodologies to the MNIST dataset and measuring key performance indicators such as encoding speed, decoding speed, memory usage, and recovery accuracy across different vector lengths. BSC and VT demonstrated relatively fast performance in encoding and decoding speeds, while MAP and HRR were relatively slow. In terms of memory usage, BSC was the most efficient, whereas MAP used the most memory. The recovery accuracy was highest for MAP and lowest for BSC. The results of this study provide a basis for selecting appropriate VSA methodologies depending on the application area.

• Nuclear Engineering and Technology
• /
• v.56 no.7
• /
• pp.2690-2697
• /
• 2024

With advancements in machine learning technologies, artificial neural networks (ANNs) are being widely used to improve the performance of gamma-ray spectroscopy based on NaI(Tl) scintillation detectors. Typically, the performance of ANNs is evaluated using test datasets composed of actual spectra. However, the generation of such test datasets encompassing a wide range of actual spectra representing various scenarios often proves inefficient and time-consuming. Thus, instead of measuring actual spectra, we generated virtual spectra with diverse spectral features by sampling from categorical distribution functions derived from the base spectra of six radioactive isotopes: ⁵⁴Mn, ⁵⁷Co, ⁶⁰Co, ¹³⁴Cs, ¹³⁷Cs, and ²⁴¹Am. For practical applications, we determined the optimum counting time (OCT) as the point at which the change in the Kullback-Leibler divergence (ΔKLDV) values between the synthetic spectra used for training the ANN and the virtual spectra approaches zero. The accuracies of the actual spectra were significantly improved when measured up to their respective OCTs. The outcomes demonstrated that the proposed method can effectively determine the OCTs for gamma-ray spectroscopy based on ANNs without the need to measure actual spectra.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.455-462
• /
• 2024

In the construction industry, known for its dynamic and hazardous environments, there exists a crucial demand for effective safety incident prevention. Traditional approaches to monitoring on-site safety, despite their importance, suffer from being laborious and heavily reliant on subjective, paper-based reports, which results in inefficiencies and fragmented data. Additionally, the incorporation of computer vision technologies for automated safety monitoring encounters a significant obstacle due to the lack of suitable training datasets. This challenge is due to the rare availability of safety accident images or videos and concerns over security and privacy violations. Consequently, this paper explores an innovative method to address the shortage of safety-related datasets in the construction sector by employing generative artificial intelligence (AI), specifically focusing on the Stable Diffusion model. Utilizing real-world construction accident scenarios, this method aims to generate photorealistic images to enrich training datasets for safety surveillance applications using computer vision. By systematically generating accident prompts, employing static prompts in empirical experiments, and compiling datasets with Stable Diffusion, this research bypasses the constraints of conventional data collection techniques in construction safety. The diversity and realism of the produced images hold considerable promise for tasks such as object detection and action recognition, thus improving safety measures. This study proposes future avenues for broadening scenario coverage, refining the prompt generation process, and merging artificial datasets with machine learning models for superior safety monitoring.

• Journal of KIISE:Software and Applications
• /
• v.37 no.6
• /
• pp.455-463
• /
• 2010

In this paper, we present an approach to sentence boundary detection for web documents that builds on statistical-based methods and uses rule-based correction. The proposed system uses the classification model learned offline using a training set of human-labeled web documents. The web documents have many word-spacing errors and frequently no punctuation mark that indicates the end of sentence boundary. As sentence boundary candidates, the proposed method considers every Ending Eomis as well as punctuation marks. We optimize engine performance by selecting the best feature, the best training data, and the best classification algorithm. For evaluation, we made two test sets; Set1 consisting of articles and blog documents and Set2 of web community documents. We use F-measure to compare results on a large variety of tasks, Detecting only periods as sentence boundary, our basis engine showed 96.5% in Set1 and 56.7% in Set2. We improved our basis engine by adapting features and the boundary search algorithm. For the final evaluation, we compared our adaptation engine with our basis engine in Set2. As a result, the adaptation engine obtained improvements over the basis engine by 39.6%. We proved the effectiveness of the proposed method in sentence boundary detection.

• Journal of Broadcast Engineering
• /
• v.22 no.3
• /
• pp.282-294
• /
• 2017

In this paper, we propose a novel intelligent headlight control (IHC) system which is durable to various road lights and camera movement caused by vehicle driving. For detecting candidate light blobs, the region of interest (ROI) is decided as front ROI (FROI) and back ROI (BROI) by considering the camera geometry based on perspective range estimation model. Then, light blobs such as headlights, taillights of vehicles, reflection light as well as the surrounding road lighting are segmented using two different adaptive thresholding. From the number of segmented blobs, taillights are first detected using the redness checking and random forest classifier based on Haar-like feature. For the headlight and taillight classification, we use the random forest instead of popular support vector machine or convolutional neural networks for supporting fast learning and testing in real-life applications. Pairing is performed by using the predefined geometric rules, such as vertical coordinate similarity and association check between blobs. The proposed algorithm was successfully applied to various driving sequences in night-time, and the results show that the performance of the proposed algorithms is better than that of recent related works.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.221-241
• /
• 2018

Deep learning is getting attention recently. The deep learning technique which had been applied in competitions of the International Conference on Image Recognition Technology(ILSVR) and AlphaGo is Convolution Neural Network(CNN). CNN is characterized in that the input image is divided into small sections to recognize the partial features and combine them to recognize as a whole. Deep learning technologies are expected to bring a lot of changes in our lives, but until now, its applications have been limited to image recognition and natural language processing. The use of deep learning techniques for business problems is still an early research stage. If their performance is proved, they can be applied to traditional business problems such as future marketing response prediction, fraud transaction detection, bankruptcy prediction, and so on. So, it is a very meaningful experiment to diagnose the possibility of solving business problems using deep learning technologies based on the case of online shopping companies which have big data, are relatively easy to identify customer behavior and has high utilization values. Especially, in online shopping companies, the competition environment is rapidly changing and becoming more intense. Therefore, analysis of customer behavior for maximizing profit is becoming more and more important for online shopping companies. In this study, we propose 'CNN model of Heterogeneous Information Integration' using CNN as a way to improve the predictive power of customer behavior in online shopping enterprises. In order to propose a model that optimizes the performance, which is a model that learns from the convolution neural network of the multi-layer perceptron structure by combining structured and unstructured information, this model uses 'heterogeneous information integration', 'unstructured information vector conversion', 'multi-layer perceptron design', and evaluate the performance of each architecture, and confirm the proposed model based on the results. In addition, the target variables for predicting customer behavior are defined as six binary classification problems: re-purchaser, churn, frequent shopper, frequent refund shopper, high amount shopper, high discount shopper. In order to verify the usefulness of the proposed model, we conducted experiments using actual data of domestic specific online shopping company. This experiment uses actual transactions, customers, and VOC data of specific online shopping company in Korea. Data extraction criteria are defined for 47,947 customers who registered at least one VOC in January 2011 (1 month). The customer profiles of these customers, as well as a total of 19 months of trading data from September 2010 to March 2012, and VOCs posted for a month are used. The experiment of this study is divided into two stages. In the first step, we evaluate three architectures that affect the performance of the proposed model and select optimal parameters. We evaluate the performance with the proposed model. Experimental results show that the proposed model, which combines both structured and unstructured information, is superior compared to NBC(Naïve Bayes classification), SVM(Support vector machine), and ANN(Artificial neural network). Therefore, it is significant that the use of unstructured information contributes to predict customer behavior, and that CNN can be applied to solve business problems as well as image recognition and natural language processing problems. It can be confirmed through experiments that CNN is more effective in understanding and interpreting the meaning of context in text VOC data. And it is significant that the empirical research based on the actual data of the e-commerce company can extract very meaningful information from the VOC data written in the text format directly by the customer in the prediction of the customer behavior. Finally, through various experiments, it is possible to say that the proposed model provides useful information for the future research related to the parameter selection and its performance.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.141-154
• /
• 2019

Rapid growth of internet technology and social media is progressing. Data mining technology has evolved to enable unstructured document representations in a variety of applications. Sentiment analysis is an important technology that can distinguish poor or high-quality content through text data of products, and it has proliferated during text mining. Sentiment analysis mainly analyzes people's opinions in text data by assigning predefined data categories as positive and negative. This has been studied in various directions in terms of accuracy from simple rule-based to dictionary-based approaches using predefined labels. In fact, sentiment analysis is one of the most active researches in natural language processing and is widely studied in text mining. When real online reviews aren't available for others, it's not only easy to openly collect information, but it also affects your business. In marketing, real-world information from customers is gathered on websites, not surveys. Depending on whether the website's posts are positive or negative, the customer response is reflected in the sales and tries to identify the information. However, many reviews on a website are not always good, and difficult to identify. The earlier studies in this research area used the reviews data of the Amazon.com shopping mal, but the research data used in the recent studies uses the data for stock market trends, blogs, news articles, weather forecasts, IMDB, and facebook etc. However, the lack of accuracy is recognized because sentiment calculations are changed according to the subject, paragraph, sentiment lexicon direction, and sentence strength. This study aims to classify the polarity analysis of sentiment analysis into positive and negative categories and increase the prediction accuracy of the polarity analysis using the pretrained IMDB review data set. First, the text classification algorithm related to sentiment analysis adopts the popular machine learning algorithms such as NB (naive bayes), SVM (support vector machines), XGboost, RF (random forests), and Gradient Boost as comparative models. Second, deep learning has demonstrated discriminative features that can extract complex features of data. Representative algorithms are CNN (convolution neural networks), RNN (recurrent neural networks), LSTM (long-short term memory). CNN can be used similarly to BoW when processing a sentence in vector format, but does not consider sequential data attributes. RNN can handle well in order because it takes into account the time information of the data, but there is a long-term dependency on memory. To solve the problem of long-term dependence, LSTM is used. For the comparison, CNN and LSTM were chosen as simple deep learning models. In addition to classical machine learning algorithms, CNN, LSTM, and the integrated models were analyzed. Although there are many parameters for the algorithms, we examined the relationship between numerical value and precision to find the optimal combination. And, we tried to figure out how the models work well for sentiment analysis and how these models work. This study proposes integrated CNN and LSTM algorithms to extract the positive and negative features of text analysis. The reasons for mixing these two algorithms are as follows. CNN can extract features for the classification automatically by applying convolution layer and massively parallel processing. LSTM is not capable of highly parallel processing. Like faucets, the LSTM has input, output, and forget gates that can be moved and controlled at a desired time. These gates have the advantage of placing memory blocks on hidden nodes. The memory block of the LSTM may not store all the data, but it can solve the CNN's long-term dependency problem. Furthermore, when LSTM is used in CNN's pooling layer, it has an end-to-end structure, so that spatial and temporal features can be designed simultaneously. In combination with CNN-LSTM, 90.33% accuracy was measured. This is slower than CNN, but faster than LSTM. The presented model was more accurate than other models. In addition, each word embedding layer can be improved when training the kernel step by step. CNN-LSTM can improve the weakness of each model, and there is an advantage of improving the learning by layer using the end-to-end structure of LSTM. Based on these reasons, this study tries to enhance the classification accuracy of movie reviews using the integrated CNN-LSTM model.

• Journal of KIISE:Software and Applications
• /
• v.29 no.4
• /
• pp.270-277
• /
• 2002

Text filtering is a task of deciding whether a document has relevance to a specified topic. As Internet and Web becomes wide-spread and the number of documents delivered by e-mail explosively grows the importance of text filtering increases as well. The aim of this paper is to improve the accuracy of text filtering systems by using machine learning techniques. We apply AdaBoost algorithms to the filtering task. An AdaBoost algorithm generates and combines a series of simple hypotheses. Each of the hypotheses decides the relevance of a document to a topic on the basis of whether or not the document includes a certain word. We begin with an existing AdaBoost algorithm which uses weak hypotheses with their output of 1 or -1. Then we extend the algorithm to use weak hypotheses with real-valued outputs which was proposed recently to improve error reduction rates and final filtering performance. Next, we attempt to achieve further improvement in the AdaBoost's performance by first setting weights randomly according to the continuous Poisson distribution, executing AdaBoost, repeating these steps several times, and then combining all the hypotheses learned. This has the effect of mitigating the ovefitting problem which may occur when learning from a small number of data. Experiments have been performed on the real document collections used in TREC-8, a well-established text retrieval contest. This dataset includes Financial Times articles from 1992 to 1994. The experimental results show that AdaBoost with real-valued hypotheses outperforms AdaBoost with binary-valued hypotheses, and that AdaBoost iterated with random weights further improves filtering accuracy. Comparison results of all the participants of the TREC-8 filtering task are also provided.

• The KIPS Transactions:PartB
• /
• v.13B no.2 s.105
• /
• pp.163-170
• /
• 2006

With rapidly developing Internet applications, an e-mail has been considered as one of the most popular methods for exchanging information. The e-mail, however, has a serious problem that users ran receive a lot of unwanted e-mails, what we called, spam mails, which cause big problems economically as well as socially. In order to block and filter out the spam mails, many researchers and companies have performed many sorts of research on spam filtering. In general, users of e-mail have different criteria on deciding if an e-mail is spam or not. Furthermore, in e-mail client systems, users do different actions according to a spam mail or not. In this paper, we propose a mail filtering system using such user actions. The proposed system consists of two steps: One is an action inference step to draw user actions from an e-mail and the other is a mail classification step to decide if the e-mail is spam or not. All the two steps use incremental learning, of which an algorithm is IB2 of TiMBL. To evaluate the proposed system, we collect 12,000 mails of 12 persons. The accuracy is $81{\sim}93%$ according to each person. The proposed system outperforms, at about 14% on the average, a system that does not use any information about user actions.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.7
• /
• pp.291-298
• /
• 2024

Despite its wide application, cloud computing raises privacy leakage concerns because users should send their private data to the cloud. Homomorphic encryption (HE) can resolve the concerns by allowing cloud servers to compute on encrypted data without decryption. However, due to the huge computation overhead of HE, simply executing an entire cloud program with HE causes significant computation. Manually partitioning the program and applying HE only to the partitioned program for the cloud can reduce the computation overhead. However, the manual code partitioning and HE-transformation are time-consuming and error-prone. This work proposes a new homomorphic encryption enabled annotation-guided code partitioning compiler, called Heapa, for privacy preserving cloud computing. Heapa allows programmers to annotate a program about the code region for cloud computing. Then, Heapa analyzes the annotated program, makes a partition plan with a variable list that requires communication and encryption, and generates a homomorphic encryptionenabled partitioned programs. Moreover, Heapa provides not only two region-level partitioning annotations, but also two instruction-level annotations, thus enabling a fine-grained partitioning and achieving better performance. For six machine learning and deep learning applications, Heapa achieves a 3.61 times geomean performance speedup compared to the non-partitioned cloud computing scheme.