• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.21-31
• /
• 2023

In this paper, we focused on the problem of evaluating multi-class classification accuracy and simulation of multiple classifier performance metrics. Multi-class classifiers for sentiment analysis involved many challenges, whereas previous research narrowed to the binary classification model since it provides higher accuracy when dealing with text data. Thus, we take inspiration from the non-linear Support Vector Machine to modify the algorithm by embedding dynamic hyperplanes representing multiple class labels. Then we analyzed the performance of multi-class classifiers using macro-accuracy, micro-accuracy and several other metrics to justify the significance of our algorithm enhancement. Furthermore, we hybridized Enhanced Convolution Neural Network (ECNN) with Dynamic Support Vector Machine (DSVM) to demonstrate the effectiveness and efficiency of the classifier towards multi-class text data. We performed experiments on three hybrid classifiers, which are ECNN with Binary SVM (ECNN-BSVM), and ECNN with linear Multi-Class SVM (ECNN-MCSVM) and our proposed algorithm (ECNNDSVM). Comparative experiments of hybrid algorithms yielded 85.12 % for single metric accuracy; 86.95 % for multiple metrics on average. As for our modified algorithm of the ECNN-DSVM classifier, we reached 98.29 % micro-accuracy results with an f-score value of 98 % at most. For the future direction of this research, we are aiming for hyperplane optimization analysis.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.190-194
• /
• 2023

By looking the importance of communication, data delivery and access in various sectors including governmental, business and individual for any kind of data, it becomes mandatory to identify faults and flaws during cyber communication. To protect personal, governmental and business data from being misused from numerous advanced attacks, there is the need of cyber security. The information security provides massive protection to both the host machine as well as network. The learning methods are used for analyzing as well as preventing various attacks. Machine learning is one of the branch of Artificial Intelligence that plays a potential learning techniques to detect the cyber-attacks. In the proposed methodology, the Decision Tree (DT) which is also a kind of supervised learning model, is combined with the different cross-validation method to determine the accuracy and the execution time to identify the cyber-attacks from a very recent dataset of different network attack activities of network traffic in the UNSW-NB15 dataset. It is a hybrid method in which different types of attributes including Gini Index and Entropy of DT model has been implemented separately to identify the most accurate procedure to detect intrusion with respect to the execution time. The different DT methodologies including DT using Gini Index, DT using train-split method and DT using information entropy along with their respective subdivision such as using K-Fold validation, using Stratified K-Fold validation are implemented.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.3
• /
• pp.55-62
• /
• 2014

This paper has proposed Hybrid QoS Routing Link State Update(LSU) Algorithm that has had a both advantage of LSU message control in periodic QoS routing LSU algorithm and QoS routing performance in adaptive LSU algorithm. Hybrid LSU algorithm can adapt the threshold based network traffic information and has the mechanism that calculate LSU message transmission priority using the flow of statistical request bandwidth and available bandwidth and determine the transmission of the message according to update rate per a unit of time. We have evaluated the performance of the proposed algorithm and the existing algorithms on MCI simulation network using the performance metric as the QoS routing blocking rate and the mean update rate per link, it thus appears that we have verified the performance of this algorithm that it can diminish to 10% of the LSU message count.

• The Research Journal of the Costume Culture
• /
• v.18 no.1
• /
• pp.64-79
• /
• 2010

The digital era in the 21st century is globalized and is collapsed boundary among countries, thereby being able to be said to be characterized most largely by proceeding with being a form like a federation and EU. A change into digital era brought about a change in all the aspects of human behavior and culture, not a change simply in temporal significance and technological significance. In recent days, all the services came to be possibly used the integrated device with the same network owing to innovation of communication technology, which is represented by digital, network, and internet. Now, the broadcasting industry, computer industry, and communication industry are exceeding the peculiar sphere by being mutually merged. Each of industrial sector centering on internet is showing the phenomenon of being united. The hybrid trend, which was formed by phenomenon in the complex digital media society, tended to be indicated in fashion and makeup design. As the digital media era was generated, the hybrid trend induced a change into society in open and horizontal idea. It came to be known that there is independent trend in each field even while organically working in the middle of the whole frame that fashion and makeup express a human being's external beauty. This implies that makeup is not what is always influenced by fashion as an accessory in fashion and a supplementary role, but what can show its contrary phenomenon. This study examined characteristics, which are shown in fashion and makeup due to hybrid influence with greeting the digital media era. This study was carried out in order to be conducive to objective data available for giving help to the future direction and marketing data in product of the relevant businesses, through the results of this study.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.7
• /
• pp.1030-1040
• /
• 2018

In Distributed Mobility Management (DMM) protocol, the mobility functions are distributed to network edge closer to mobile users. DMM protocol has some advantages of low-cost traffic delivery, optimized routing path, high scalability. However, it needs many mobile anchors to exchange signaling messages and it results in a high signaling cost. Thus, previous works suggested the hybrid DMM protocol to reduce the high signaling cost for long-live sessions and this paper extends a hybrid scheme to the NEMO environment. The mobile routers are installed at vehicles and can move together with several mobile devices. So we can define the high-mobility property for mobile routers and suggest the hybrid scheme using this property. According to the high-mobility property of mobile routers, we can distribute the mobile anchors or allocate a centralized mobile anchor. In this paper, we mathematically analyze the performance of the proposed NEMO-enabled hybrid DMM protocol and show superior performance.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.9 no.6
• /
• pp.544-552
• /
• 2004

This paper deals with the hybrid active filter which can reduce the 11th/13th harmonics in AC network by using the single tuned filter. Since the proposed algorithm uses the detuning compensation capability of the filter, the output voltage of the proposed active power filter is changed according to the capacitance of capacitors, magnitude of harmonic current, resonance frequency and control mode. In this paper, the control characteristics and the design of hybrid active filter is investigated. A new hybrid active filter with new algorithm, which is an active filter with single tuned filter instead of double tuned filter, is proposed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.215-217
• /
• 2016

With the popularity of smart device, mobile applications are playing more and more important role in people's daily life, these applications stores various information which greatly facilitate the user's daily life. However due to the frequent transmission of data in the network also increases the risk of data leakage, more and more developers began to focus on how to protect user data. Current mainstream development models include Native development, Web development and Hybrid development. Hybrid development is based on JavaScript and HTML5, it has a cross platform advantages similar to Web Apps and a good user experience similar to Native Apps. In this paper according to the features of Hybrid applications, we proposed a security scheme in Hybrid development model implements message-level data encryption to protect user information. And through the performance evaluation we found that in some scenario the proposed security scheme has a better performance.

• Journal of Industrial Technology
• /
• v.27 no.A
• /
• pp.141-147
• /
• 2007

In this paper, we define the multi-states exponential cell resident time mobility model for describing the mobility characteristics of mobile user and analyzed the total cost of the hybrid method using multi-states cell resident time. Generally, the mobile user has three states for its movement, such as staying, walking and driving. This multi-states cell resident time based hybrid method reflects the movement characteristics of mobile user and adapts the location update period according to the states of mobility speed. As a results of the performance analysis, we can get the optimum parameters of the hybrid method for multi-states based mobile users.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.2 no.2
• /
• pp.129-135
• /
• 2007

In this paper, we present hybrid ARQ techniques to improve the throughput performance in high speed packet transmission such as Internet or multimedia services in Hospital. In order to evaluate the performance of the three different types of hybrid ARQ schemes, systemized link level simulations based on WWW traffic model are considered. In this paper, we also consider the simulated performance for an average link throughput and a normalized packet delay to compare the hybrid ARQ with link adaptation scheme in GPRS.

• Journal of Adhesion and Interface
• /
• v.7 no.4
• /
• pp.32-38
• /
• 2006

A series of organic-inorganic hybrids, PCL/EP/$SiO_2$, involving epoxy resin and triethoxysilane-terminated polycaprolactone elastomer (PCL-TESi) were prepared via polymerization of diglycidyl ether of bisphenol A (DGEBA) with amine curing agent KB-2 and sol-gel process of PCL-TESi. The curing reactions were started from the initially homogeneous mixture of DGEBA, KB-2 and the PCL-TESi. The organicinorganic hybrids containing up to 4.95% (wt) of $SiO_2$ were obtained and characterized by FT-IR, transmission electron microscopy (TEM), differential scanning calorimetry (DSC) and thermogravimetry analysis (TGA). It was experimentally shown that the swelling property in toluene, morphologies and thermal properties of the resulting hybrids were quite dependent on the contents of $SiO_2$. The crosslink network density decreases with increasing of the PCL-TESi. And in TEM, the phase separated morphology of these hybrids was found, which resulted from the coagulation of Si-O-Si networks resulting from $-Si(OC_2H_5)_3$ of PCL-TESi self-curing by hydrolytic silanol condensation, with the advancement of the curing reaction in the modified epoxy resin systems. Meanwhile, the change of the $SiO_2$ content made the morphologies changed from aggregated particles of Si-O-Si in the hybrid to nanocluster of interconnected Si-O-Si particles, then to aggregated Si-O-Si dispersing in the continuous cured epoxy phase again, and last to co-continuous interpenetrating network. The glass transition behavior of the hybrid material was cooperative motion of large chain segments, which were hindered by the inorganic Si-O-Si network. And in TG analysis, the characteristic temperature at 5% of weight loss was evidently increased from $120.5^{\circ}C$ of pure cured epoxy to $277.6^{\circ}C$ of 3.84% (wt) of $SiO_2$ modified epoxy due to the existence of Si-O-Si when PCL-TESi was added in the hybrid.