• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.609-611
• /
• 2022

본 논문에서는 맞춤형 반려동물 사료제품 추천을 위해 최근의 자연어처리 모델인 KoBERT 모델에 기반하여 반료동물 사료제품에 대한 감성분석 모델을 설계하고 구현한다. 본 논문을 통해 구현된 반려동물 사료제품의 감성분석 모델은 정확도 평가에 대해서 비교적 우수한 성능을 보였으며, 학습과정에 참여하지 않은 새로운 반려동물 사료제품에 대해서 0.93 이상의 정확도를 산출하였다.

• International Journal of Computer Science & Network Security
• /
• v.23 no.10
• /
• pp.67-72
• /
• 2023

This paper portrays the design and optimization of a wideband four element triangular dielectric resonator antenna (TDRA) using PSO. The proposed antenna's radiation characteristics were extracted using Ansoft HFSS software. At a resonant frequency of 5-7 GHz, the four element antenna provides nearly 21 percent bandwidth and the optimized gives 5.82 dBi peak gain. The radiation patterns symmetry and uniformity are maintained throughout the operating bandwidth. for WLAN (IEEE 802.16) and WiMAX applications, the proposed antenna exhibits a consistent symmetric monopole type radiation pattern with low cross polarisation. The proposed antenna's performance was compared to that of other dielectric resonator antenna (DRA) shapes, and it was discovered that the TDRA uses a lot less radiation area to provide better performance than other DRA shapes and PSO optimized antenna increases the gain of the antenna

• Journal of Korea Multimedia Society
• /
• v.23 no.5
• /
• pp.641-649
• /
• 2020

As the usage of mobile devices extremely increases, malicious mobile apps(applications) that target mobile users are also increasing. It is challenging to detect these malicious apps using traditional malware detection techniques due to intelligence of today's attack mechanisms. Deep learning (DL) is an alternative technique of traditional signature and rule-based anomaly detection techniques and thus have actively been used in numerous recent studies on malware detection. In order to develop DL-based defense mechanisms against intelligent malicious apps, feeding recent datasets into DL models is important. In this paper, we develop a DL-based model for detecting intelligent malicious apps using KU-CISC 2018-Android, the most up-to-date dataset consisting of benign and malicious Android apps. This dataset has hardly been addressed in other studies so far. We extract OPcode sequences from the Android apps and preprocess the OPcode sequences using an N-gram model. We then feed the preprocessed data into LSTM and apply the concept of Information Gain to improve performance of detecting malicious apps. Furthermore, we evaluate our model with numerous scenarios in order to verify the model's design and performance.

• Korean Journal of Organic Agriculture
• /
• v.20 no.2
• /
• pp.185-200
• /
• 2012

It has been reported that world population continues to increase so that a matter of food security can be a world-wide problem for mankind. An anticipated rise in world population of 30% and the subsequent increased demand for food brings with it challenges in terms of global resource usage and food security. However, ruminant livestock production and consumption make a large contribution to the greenhouse gas (GHG) emissions which can be attributable to food production. Given the association between GHG and climate change, this is clearly of great concern to the livestock industry worldwide. Nevertheless, ruminant livestock also play an important role in global food security as they can convert the plant cell wall materials and non-protein nitrogen compounds, found widely in plants but indigestible to all monogastric animals including man, into high value proteins for human consumption. Much effort has been made to maximize animal production, feed conversion ratio, and to improve animal breeding in ruminant agriculture. In addition improving feed formulation techniques, developing chemical additives, plant extracts, and new plant varieties for grazing have been tested. Future ruminant production systems will need to capitalize on important benefits of ruminants. It is therefore suggested that ruminant agriculture has a key role to play in maintaining and enhancing provision of quality proteins and essential nutrients for human being but the challenge of reducing GHG emissions, and methane in particular, needs to be successfully addressed.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.5
• /
• pp.437-445
• /
• 2018

Devices have a lot of small breakdowns rather than big breakdowns. But it often wastes time and increases cost of maintenance, such as calling a service technician for small breakdowns. So, if we use remote control and monitoring service using Internet of Things, we can minimize the time period and cost for the maintenance. However, security is important because remote control and monitoring services contain personal information which when leaked, may be dangerous. There are many types of Internet based monitoring devices that are in use, but it is difficult to expect a high level of security because there are many cases in which the performance is minimal. Therefore, in this paper, we classify remote control and monitoring services based on Internet of Things type and derive encryption requirement for four types. We also compared and analyzed the lightweight cryptographic algorithms that can be expected to use high performance even on the Internet of Things. And it is derived that LED is used as a equipment management type, DESLX as a environment management type, CLEFIA as a healthcare management type and LEA as a security management type are the optimal lightweight cryptographic algorithms for each type.

• International Journal of Computer Science & Network Security
• /
• v.22 no.12
• /
• pp.245-251
• /
• 2022

In this paper, a high gain, broadband planar vivaldi antenna (PVA) by utilizing a broadband stripline feed is developed for wireless communication for IoT systems. The suggested antenna is designed by attaching a tapered-slot construction to a typical vivaldi antenna, which improves the antenna's radiation properties. The PVA is constructed on a low-cost FR4 substrate. The dimensions of the patch are 1.886λ₀×1.42λ₀×0.026λ₀, dielectric constant Ɛ_r=4.4, and loss tangent δ=0.02. The width of the feed line is reduced to improve the impedance bandwidth of the antenna. The computed reflection coefficient findings show that the suggested antenna has a 46.2% wider relative bandwidth calculated at a 10 dB return loss. At the resonance frequencies of 6.5 GHz, the studied results show an optimal gain of 5.82 dBi and 85% optimal radiation efficiency at the operable band. The optometric analysis of the proposed structure shows that the proposed antenna can achieve wide enough bandwidth at the desired frequency and hence make the designed antenna appropriate to work in satellite communication and medical internet of things (M-IoT) healthcare applications.

• International Journal of Computer Science & Network Security
• /
• v.22 no.12
• /
• pp.185-196
• /
• 2022

The Internet of Things (IoT) has become more and more widespread in recent years, thus attackers are placing greater emphasis on IoT environments. The IoT connects a large number of smart devices via wired and wireless networks that incorporate sensors or actuators in order to produce and share meaningful information. Attackers employed IoT devices as bots to assault the target server; however, because of their resource limitations, these devices are easily infected with IoT malware. The Distributed Denial of Service (DDoS) is one of the many security problems that might arise in an IoT context. DDOS attempt involves flooding a target server with irrelevant requests in an effort to disrupt it fully or partially. This worst practice blocks the legitimate user requests from being processed. We explored an intelligent intrusion detection system (IIDS) using a particular sort of machine learning, such as Artificial Neural Networks, (ANN) in order to handle and mitigate this type of cyber-attacks. In this research paper Feed-Forward Neural Network (FNN) is tested for detecting the DDOS attacks using a modified version of the KDD Cup 99 dataset. The aim of this paper is to determine the performance of the most effective and efficient Back-propagation algorithms among several algorithms and check the potential capability of ANN- based network model as a classifier to counteract the cyber-attacks in IoT environments. We have found that except Gradient Descent with Momentum Algorithm, the success rate obtained by the other three optimized and effective Back- Propagation algorithms is above 99.00%. The experimental findings showed that the accuracy rate of the proposed method using ANN is satisfactory.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.5
• /
• pp.2062-2069
• /
• 2015

In the series hybrid active power filter (SHAPF) with magnetic flux compensation (MFC), the system current oscillate in the experimental results when adding the same phase harmonic current command in current control block. This condition endangers the security of the SHAPF. Taking the digit period average arithmetic as example, this paper explains the inter-harmonics current oscillation in the experiment. The conclusion is that the SHAPF is unstable to the inter-harmonics current in theory. Limited by the capacity of the inverter, the system current and the inverter output current do not increase to infinite. At last, some methods are proposed to solve this problem. From the practical viewpoint, the voltage feed-forward control is easy to achieve. It can suppress the current oscillation problems, and also improve the filtering effect. The feasibility of the methods is validated by both the emulation and experiment results.

• Journal of Korean Society of societal Security
• /
• v.3 no.2
• /
• pp.47-55
• /
• 2010

It was developing of portable hybrid water purification system for clean water production in the disaster area. because there are no way to supply a drinking water to the victims of calamity. currently, the government has been supplying bottled water to victims. but it is a limit to the reserves. It is composed of a filter, a feed pump, a solar-cell, a controller, and a case and is possible supplying a drinking water not to limit time and a place. Field test was carried out to developed portable water purification system and the purified water was satisfied a criterion for a drinking water.

• Bulletin of the Korea Photovoltaic Society
• /
• v.6 no.1
• /
• pp.56-68
• /
• 2020

Cameroon is a lower middle-income country with a population of 25.87 million inhabitants distributed over a surface area of 475,442 ㎢. Cameroon has very rich potentials in renewable energy resources such as solar energy, wind energy, small hydropower, geothermal energy and biomass. However, renewable energy constitutes less than 0.1% of energy mix of the country. The energy generation mix of Cameroon is dominated by large hydropower and thermal power. Cameroon ratified the Paris Agreement in July 2016 with an ambitious 20% greenhouse gas (GHG) emission reduction. This study attempts to investigate some renewable energy deployment policy-instruments that could enable the country enhance renewable energy deployment, gain energy independence, fulfill Nationally Determined Contribution (NDC) and achieve Sustainable Development Goals. It begins with an analysis of the status of energy sector in Cameroon. It further highlights the importance of renewable energy in mitigating climate change by decarbonizing the energy mix of the country to fulfill NDC and SDGs. Moreover, this study proposes some renewable energy deployment policy-solutions to the government. Solar energy is the most feasible renewable energy source in Cameroon. Feed-in Tariffs (FiT), is the best renewable energy support policy for Cameroon. Finally, this study concludes with some recommendations such as the necessity of building an Energy Storage System as well a renewable energy information and statistics infrastructure.