• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1916-1934
• /
• 2023

The phishing attack is a malicious emerging threat on the internet where the hackers try to access the user credentials such as login information or Internet banking details through pirated websites. Using that information, they get into the original website and try to modify or steal the information. The problem with traditional defense systems like firewalls is that they can only stop certain types of attacks because they rely on a fixed set of principles to do so. As a result, the model needs a client-side defense mechanism that can learn potential attack vectors to detect and prevent not only the known but also unknown types of assault. Feature selection plays a key role in machine learning by selecting only the required features by eliminating the irrelevant ones from the real-time dataset. The proposed model uses Hyperparameter Optimized Artificial Neural Networks (H-ANN) combined with a Hybrid Firefly and Grey Wolf Optimization algorithm (H-FFGWO) to detect and block phishing websites in Internet of Things(IoT) Applications. In this paper, the H-FFGWO is used for the feature selection from phishing datasets ISCX-URL, Open Phish, UCI machine-learning repository, Mendeley website dataset and Phish tank. The results showed that the proposed model had an accuracy of 98.07%, a recall of 98.04%, a precision of 98.43%, and an F1-Score of 98.24%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• pp.2334-2347
• /
• 2023

Metaverse services generate text data, data of ubiquitous computing, in real-time to analyze user emotions. Analysis of user emotions is an important task in metaverse services. This study aims to classify user sentiments using deep learning and pre-trained language models based on the transformer structure. Previous studies collected data from a single platform, whereas the current study incorporated the review data as "Metaverse" keyword from the YouTube and Google Play Store platforms for general utilization. As a result, the Bidirectional Encoder Representations from Transformers (BERT) and Robustly optimized BERT approach (RoBERTa) models using the soft voting mechanism achieved a highest accuracy of 88.57%. In addition, the area under the curve (AUC) score of the ensemble model comprising RoBERTa, BERT, and A Lite BERT (ALBERT) was 0.9458. The results demonstrate that the ensemble combined with the RoBERTa model exhibits good performance. Therefore, the RoBERTa model can be applied on platforms that provide metaverse services. The findings contribute to the advancement of natural language processing techniques in metaverse services, which are increasingly important in digital platforms and virtual environments. Overall, this study provides empirical evidence that sentiment analysis using deep learning and pre-trained language models is a promising approach to improving user experiences in metaverse services.

• Journal of Information Processing Systems
• /
• v.19 no.4
• /
• pp.483-497
• /
• 2023

Depth estimation is one of the most complicated and difficult problems to deal with in the light field. In this paper, a compound attention convolutional neural network (CAttNet) is proposed to extract depth maps from light field images. To make more effective use of the sub-aperture images (SAIs) of light field and reduce the redundancy in SAIs, we use a compound attention mechanism to weigh the channel and space of the feature map after extracting the primary features, so it can more efficiently select the required view and the important area within the view. We modified various layers of feature extraction to make it more efficient and useful to extract features without adding parameters. By exploring the characteristics of light field, we increased the network depth and optimized the network structure to reduce the adverse impact of this change. CAttNet can efficiently utilize different SAIs correlations and features to generate a high-quality light field depth map. The experimental results show that CAttNet has advantages in both accuracy and time.

• Herbal Formula Science
• /
• v.26 no.3
• /
• pp.207-221
• /
• 2018

Objectives : Present study investigated hepatoprotective effect of Haegan-jeon extract (HE) and tried to elucidate molecular mechanism involved. According to molecular mechanism, present study optimized herbal composition of HE (op-HE) and compared in vitro and in vivo hepatoprotective effects of op-HE to HE. Methods : For in vitro experiments, HepG2 cells were exposed to arachidonic acid (AA, $10{\mu}M$) and iron ($5{\mu}M$) for inducing oxidative stress. Cell viability, GSH contents, $H_2O_2$ production, mitochondrial membrane potential, immunoblot and reporter gene assay were performed to investigate cytoprotective effects and responsible molecular mechanisms. For in vivo experiments, hepatoprotective effect of HE and op-HE were assessed on $CCl_4-induced$ liver injury mice model. Results : HE pretreatment prevented AA+iron-mediated hepatocytes apoptosis. In addition, AA+iron-induced mitochondrial dysfunction, $H_2O_2$ production, glutathione depletion were reduced by HE pretreatment. In addition, nuclear factor erythroid 2-related factor 2 (Nrf2) phosphorylation, antioxidant response element (ARE)-driven reporter gene activity, and antioxidant genes expression were increased by HE. Based on reporter gene and MTT assays, we found that op-HE consisting three medicinal herbs also significantly increased transactivation of Nrf2 and reduced the AA+iron-mediated cytotoxicity. Moreover, in $CCl_4-induced$ liver injury mice model, HE-op had an ability to ameliorate $CCl_4-mediated$ increases in serum alanine transferase and aspartate aminotransferase activity, hepatic degeneration, inflammatory cell infiltration, and collagen deposition. Hepatoprotective effects of op-HE were comparable to those of HE. Conclusions : Present study suggests that op-HE as well as HE exhibit hepatoprotective effect against oxidative stress-mediated liver injury via Nrf2 activation.

• Korean Journal of Construction Engineering and Management
• /
• v.5 no.6 s.22
• /
• pp.170-178
• /
• 2004

Public construction companies have strictly followed a rule that they should not work in the wet area such as structural frame for a certain period during the winter season. It is usually known that the non-working period during the winter causes increase of the project duration, and the project cost escalation. Also, it makes negative effects on national economy because it reduces workers income. Therefore, the site work for the structural frame should be performed even during the whiter season. But the site work for the structural frame during that period cannot proceeds in the same way as during other periods, and requires a different method for estimating project duration. Through an analysis of time scheduling mechanism, actual working days are obtained for 1 cycle of typical floors in the structural frame during these periods, and non-working days of 5 years average are calculated based on calendar day using data of 5 years weather forecasts for that season. This study proposes an optimized way of estimating project duration for 1 cycle of typical floors in the structural frame during these periods. This estimating method uses the combined actual working days and non-working days of 5 years' average, and the estimated results are confirmed by being compared with field data. This study is expected to be used in estimating the construction duration of the structural frame during the winter season.

• Journal of KIISE:Information Networking
• /
• v.34 no.1
• /
• pp.1-15
• /
• 2007

Increase in the wireless mobile network users brings the issue of mobility management into the Virtual Private Network (VPN) services. We propose a provider edge (PE)-based provider provisioned mobile VPN mechanism, which enables efficient communication between a mobile VPN user and one or more correspondents located in different VPN sites. The proposed mechanism not only reduces the IPSec tunnel overhead at the mobile user node to the minimum, but also enables the traffic to be delivered through optimized paths among the (mobile) VPN users without incurring significant extra IPSec tunnel overhead regardless of the user's locations. The proposed architecture and protocols are based on the BGP/MPLS VPN technology that is defined in RFC24547. A service provider platform entity named PPVPN Network Server (PNS) is defined in order to extend the BGP/MPLS VPN service to the mobile users. Compared to the user- and CE-based mobile VPN mechanisms, the proposed mechanism requires less overhead with respect to the IPSec tunnel management. The simulation results also show that it outperforms the existing mobile VPN mechanisms with respect to the handoff latency and/or the end-to-end packet delay.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.5B
• /
• pp.253-263
• /
• 2005

This paper proposed a mobile multicast technique to satisfy end-to-end QoS for various user requirements in mobile network environment. In order to provide seamless mobility, fast handoff technique was applied. By using L2 mobile trigger, it was possible to minimize remarkable amount of packet loss by delay occurred during handoff. To provide efficient multicast, concept of hierarchy was introduced to Xcast++, which results in a creation of HXcast++. HXcast++ optimized transfer path of multicast and reduced expensive multicast maintenance costs caused by frequent handoff. Suggestion of GMA (Group Management Agent) mechanism allows joining to group immediately without waiting IGMP Membership query during handoff. GMA mechanism will minimize the delay for group registration process and the resource usage due to delay of withdrawal process. And also use of buffering & forwarding technique minimized packet loss during generation of multicast tree. IntServ/RSVP was used to provide End-to-End QoS in local domain and DiffServ was used in global domain. To minimize reestablishment of RSVP session delay, extended HXcast++ control messages ware designed to require PATH message. HXcast++ proposed in this thesis is defined as multicast technique to provide end-to-end QoS and also to satisfy various user requirements in mobile network environment.

• Clean Technology
• /
• v.24 no.3
• /
• pp.175-182
• /
• 2018

In this research, we investigated the cleanliness by optimizing the water content of the aqueous stripper in fluidic strip process. The stripping properties of the photoresist with optimized aqueous stripper were compared with the commercial organic stripper. The stripping performance was evaluated by electrical and optical characteristics on the surface of the transparent electrode that compare with stripped the transparent electrode surface and the rare surface before patterning by the photoresist. As a result of the photoresist stripping process of the organic stripper and the aqueous stripper optimized for water content, the aqueous stripper exhibited better electrical and optical characteristics than the organic stripper. In the case of the fluidic strip process with organic stripper, the photoresist dissolves in the stripper solution during stripping which can cause re-adsorption by contamination. Whereas that the aqueous stripper under development seems to decrease the photoresist dissolution in the stripper solution. Because the cyclodextrin contained in the stripper captures organic photoresist into hall of cyclodextrin which stripped through swelling and tearing. The photoresist residue captured by the cyclodextrin can be filtered. After the fluidic stripping process by different chemical stripping mechanism, the cleanliness of the organic stripper and aqueous stripper was compared and analyzed.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.970-976
• /
• 2007

In this study, Polynomial Network Pattern Classifier(PNC) based on Fuzzy Inference Mechanism is designed and its parameters such as learning rate, momentum coefficient and fuzzification coefficient are optimized by means of Particle Swarm Optimization. The proposed PNC employes a partition function created by Fuzzy C-means(FCM) clustering as an activation function in hidden layer and polynomials weights between hidden layer and output layer. Using polynomials weights can help to improve the characteristic of the linear classification of basic neural networks classifier. In the viewpoint of linguistic analysis, the proposed classifier is expressed as a collection of "If-then" fuzzy rules. Namely, architecture of networks is constructed by three functional modules that are condition part, conclusion part and inference part. The condition part relates to the partition function of input space using FCM clustering. In the conclusion part, a polynomial function caries out the presentation of a partitioned local space. Lastly, the output of networks is gotten by fuzzy inference in the inference part. The proposed PNC generates a nonlinear discernment function in the output space and has the better performance of pattern classification as a classifier, because of the characteristic of polynomial based fuzzy inference of PNC.

• 한국체육학회지인문사회과학편
• /
• v.57 no.6
• /
• pp.293-308
• /
• 2018

This study was carried out to investigate the current trends in skiing-related research from existing literature in the field of kinematics, measurement sensor and computer simulation. In the field of kinematics, research is being conducted on the mechanism of ski turn, posture analysis according to the grade and skill level of skiers, friction force of ski and snow, and air resistance. In the field of measurement sensor and computer simulation, researches are being conducted for researching and developing equipment using IMU sensor and GPS. The results of this study are as follows. First, beyond the limits of the existing kinematic analysis, it is necessary to develop measurement equipment that can analyze the entire skiing area and can be deployed with ease at the sports scene. Second, research on the accuracy of information obtained using measurement sensors and various analysis techniques based on these measures should be carried out continuously to provide data that can help the sports scene. Third, it is necessary to use computer simulation methods to clarify the injury mechanism and discover ways to prevent injuries related to skiing. Fourth, it is necessary to provide optimized ski trajectory algorithm by developing 3D ski model using computer simulation and comparing with actual skiing data.