• The KIPS Transactions:PartB
• /
• v.8B no.5
• /
• pp.455-462
• /
• 2001

The World Wide Web has become one of the major services provided through Internet. When searching the vast web space, users use bookmarking facilities to record the sites of interests encountered during the course of navigation. One of the typical problems arising from bookmarking is that the list of bookmarks lose coherent organization when the the becomes too lengthy, thus ceasing to function as a practical finding aid. In order to maintain the bookmark file in an efficient, organized manner, the user has to classify all the bookmarks newly added to the file, and update the folders. This paper introduces our learning agent called BClassifier that automatically classifies bookmarks by analyzing the contents of the corresponding web documents. The chief source for the training examples are the bookmarks already classified into several bookmark folders according to their subject by the user. Additionally, the web pages found under top categories of Yahoo site are collected and included in the training examples for diversifying the subject categories to be represented, and the training examples for these categories as well. Our agent employs naive Bayesian learning method that is a well-tested, probability-based categorizing technique. In this paper, the outcome of some experimentation is also outlined and evaluated. A comparison of naive Bayesian learning method alongside other learning methods such as k-Nearest Neighbor and TFIDF is also presented.

• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.133-144
• /
• 2020

The number of elderly people with dementia is increasing as fast as the proportion of older people due to aging, which creates a social and economic burden. In particular, dementia care costs, including indirect costs such as increased care costs due to lost caregiver hours and caregivers, have grown exponentially over the years. In order to reduce these costs, it is urgent to introduce a management system to care for dementia patients. Therefore, this study proposes a sensor-based abnormal behavior detection system to manage dementia patients who live alone or in an environment where they cannot always take care of dementia patients. Existing studies were merely evaluating behavior or evaluating normal behavior, and there were studies that perceived behavior by processing images, not data from sensors. In this study, we recognized the limitation of real data collection and used both the auto-encoder, the unsupervised learning model, and the LSTM, the supervised learning model. Autoencoder, an unsupervised learning model, trained normal behavioral data to learn patterns for normal behavior, and LSTM further refined classification by learning behaviors that could be perceived by sensors. The test results show that each model has about 96% and 98% accuracy and is designed to pass the LSTM model when the autoencoder outlier has more than 3%. The system is expected to effectively manage the elderly and dementia patients who live alone and reduce the cost of caring.

• Journal of Internet Computing and Services
• /
• v.17 no.3
• /
• pp.107-113
• /
• 2016

Following the recent advancement in the use of social networks, a vast amount of different online reviews is created. These variable online reviews which provide feedback data of contents' are being used as sources of valuable information to both contents' users and providers. With the increasing importance of online reviews, studies on opinion mining which analyzes online reviews to extract opinions or evaluations, attitudes and emotions of the writer have been on the increase. However, previous sentiment analysis techniques of opinion-mining focus only on the classification of reviews into positive or negative classes but does not include detailed information analysis of the user's satisfaction or sentiment grounds. Also, previous designs of the sentiment analysis technique only applied to one content domain that is, either product or movie, and could not be applied to other contents from a different domain. This paper suggests a sentiment analysis technique that can analyze detailed satisfaction of online reviews and extract detailed information of the satisfaction level. The proposed technique can analyze not only one domain of contents but also a variety of contents that are not from the same domain. In addition, we design a system based on Hadoop to process vast amounts of data quickly and efficiently. Through our proposed system, both users and contents' providers will be able to receive feedback information more clearly and in detail. Consequently, potential users who will use the content can make effective decisions and contents' providers can quickly apply the users' responses when developing marketing strategy as opposed to the old methods of using surveys. Moreover, the system is expected to be used practically in various fields that require user comments.

• Journal of Internet Computing and Services
• /
• v.22 no.5
• /
• pp.47-55
• /
• 2021

Analysis of research trends in specific subject areas is performed by examining related topics and subject changes by using topic modeling techniques through keyword extraction for most of the literature information (paper, patents, etc.). Unlike existing research methods, this paper extracts topics related to the research topic using the LDA topic modeling technique for the project information of national R&D projects provided by the National Science and Technology Knowledge Information Service (NTIS) in the field of artificial intelligence. By analyzing these topics, this study aims to analyze research topics and investment directions for national R&D projects. NTIS provides a vast amount of national R&D information, from information on tasks carried out through national R&D projects to research results (thesis, patents, etc.) generated through research. In this paper, the search results were confirmed by performing artificial intelligence keywords and related classification searches in NTIS integrated search, and basic data was constructed by downloading the latest three-year project information. Using the LDA topic modeling library provided by Python, related topics and keywords were extracted and analyzed for basic data (research goals, research content, expected effects, keywords, etc.) to derive insights on the direction of research investment.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.29-39
• /
• 2021

As damages to individuals, private sectors, and businesses increase due to newly occurring cyber attacks, the underlying network security problem has emerged as a major problem in computer systems. Therefore, NIDS using machine learning and deep learning is being studied to improve the limitations that occur in the existing Network Intrusion Detection System. In this study, a deep learning-based NIDS model study is conducted using the Convolution Neural Network (CNN) algorithm. For the image classification-based CNN algorithm learning, a discrete algorithm for continuity variables was added in the preprocessing stage used previously, and the predicted variables were expressed in a linear relationship and converted into easy-to-interpret data. Finally, the network packet processed through the above process is mapped to a square matrix structure and converted into a pixel image. For the performance evaluation of the proposed model, NSL-KDD, a representative network packet data, was used, and accuracy, precision, recall, and f1-score were used as performance indicators. As a result of the experiment, the proposed model showed the highest performance with an accuracy of 85%, and the harmonic mean (F1-Score) of the R2L class with a small number of training samples was 71%, showing very good performance compared to other models.

• Journal of Internet Computing and Services
• /
• v.19 no.6
• /
• pp.21-29
• /
• 2018

In the era of the 4-th industrial revolution, the concept of smart factory is emerging. There are efforts to predict the occurrences of facility errors which have negative effects on the utilization and productivity by using data analysis. Data composed of the situation of a facility error and the type of the error, called the facility error log, is required for the prediction. However, in many manufacturing companies, the types of facility error are not precisely defined and categorized. The worker who operates the facilities writes the type of facility error in the form with unstructured text based on his or her empirical judgement. That makes it impossible to analyze data. Therefore, this paper proposes a framework for constructing a phrase network to support the identification and classification of facility error types by using facility error logs written by operators. Specifically, phrase indicating the types are extracted from text data by using dictionary which classifies terms by their usage. Then, a phrase network is constructed by calculating the similarity between the extracted phrase. The performance of the proposed method was evaluated by using real-world facility error logs. It is expected that the proposed method will contribute to the accurate identification of error types and to the prediction of facility errors.

• Journal of Internet Computing and Services
• /
• v.21 no.6
• /
• pp.13-21
• /
• 2020

The Android author identification study can be interpreted as a method for revealing the source in a narrow range, but if viewed in a wide range, it can be interpreted as a study to gain insight to identify similar works through known works. The problem found in the Android author identification study is that it is an important code on the Android system, but it is difficult to find the important feature of the author due to the meaningless codes. Due to this, legitimate codes or behaviors were also incorrectly defined as malicious codes. To solve this, we introduced the concept of survival network to solve the problem by removing the features found in various Android apps and surviving unique features defined by authors. We conducted an experiment comparing the proposed framework with a previous study. From the results of experiments on 440 authors' identified apps, we obtained a classification accuracy of up to 92.10%, and showed a difference of up to 3.47% from the previous study. It used a small amount of learning data, but because it used unique features without duplicate features for each author, it was considered that there was a difference from previous studies. In addition, even in comparative experiments with previous studies according to the feature definition method, the same accuracy can be shown with a small number of features, and this can be seen that continuously overlapping meaningless features can be managed through the concept of a survival network.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.17-27
• /
• 2023

Today, as AI (Artificial Intelligence) technology develops and its practicality increases, it is widely used in various application fields in real life. At this time, the AI model is basically learned based on various statistical properties of the learning data and then distributed to the system, but unexpected changes in the data in a rapidly changing data situation cause a decrease in the model's performance. In particular, as it becomes important to find drift signals of deployed models in order to respond to new and unknown attacks that are constantly created in the security field, the need for lifecycle management of the entire model is gradually emerging. In general, it can be detected through performance changes in the model's accuracy and error rate (loss), but there are limitations in the usage environment in that an actual label for the model prediction result is required, and the detection of the point where the actual drift occurs is uncertain. there is. This is because the model's error rate is greatly influenced by various external environmental factors, model selection and parameter settings, and new input data, so it is necessary to precisely determine when actual drift in the data occurs based only on the corresponding value. There are limits to this. Therefore, this paper proposes a method to detect when actual drift occurs through an Anomaly analysis technique based on XAI (eXplainable Artificial Intelligence). As a result of testing a classification model that detects DGA (Domain Generation Algorithm), anomaly scores were extracted through the SHAP(Shapley Additive exPlanations) Value of the data after distribution, and as a result, it was confirmed that efficient drift point detection was possible.

• The KIPS Transactions:PartC
• /
• v.15C no.5
• /
• pp.351-358
• /
• 2008

Recently, as network flooding attacks such as DoS/DDoS and Internet Worm have posed devastating threats to network services, rapid detection and proper response mechanisms are the major concern for secure and reliable network services. However, most of the current Intrusion Detection Systems(IDSs) focus on detail analysis of packet data, which results in late detection and a high system burden to cope with high-speed network environment. In this paper we propose a lightweight and fast detection mechanism for traffic flooding attacks. Firstly, we use SNMP MIB statistical data gathered from SNMP agents, instead of raw packet data from network links. Secondly, we use a machine learning approach based on a Support Vector Machine(SVM) for attack classification. Using MIB and SVM, we achieved fast detection with high accuracy, the minimization of the system burden, and extendibility for system deployment. The proposed mechanism is constructed in a hierarchical structure, which first distinguishes attack traffic from normal traffic and then determines the type of attacks in detail. Using MIB data sets collected from real experiments involving a DDoS attack, we validate the possibility of our approaches. It is shown that network attacks are detected with high efficiency, and classified with low false alarms.

• KIPS Transactions on Computer and Communication Systems
• /
• v.7 no.7
• /
• pp.183-194
• /
• 2018

With the rapid development of IoT(Internet of Things) technology, various convenient services such as smart home and smart city have been realized. However, IoT devices in unmanned environments are exposed to various security threats including eavesdropping and data forgery, information leakage due to unauthorized access. To build a secure IoT environment, it is necessary to use proper cryptographic technologies to IoT devices. But, it is impossible to apply the technologies applied in the existing IT environment, due to the limited resources of the IoT devices. In this paper, we survey the classification of IoT devices according to the performance and analyze the security requirements for IoT devices. Also we survey and analyze the use of cryptographic technologies in the current status of IoT open standard platform such as AllJoyn, oneM2M, IoTivity. Based on the research of cryptographic usage, we examine whether each platform satisfies security requirements. Each IoT open platform provides cryptographic technology for supporting security services such as confidentiality, integrity, authentication an authorization. However, resource constrained IoT devices such as blood pressure monitoring sensors are difficult to apply existing cryptographic techniques. Thus, it is necessary to study cryptographic technologies for power-limited and resource constrained IoT devices in unattended environments.