检索结果-南通市图书馆

A Model Training Method for DDoS Detection Using CTGAN under 5GC Traffic

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第10期47卷 1125-1147页

作者： Yea-Sul Kim Ye-Eun Kim Hwankuk Kim Department of Electronics Information and System Engineering Sangmyung UniversityCheonan31066Korea Department of Information Security Engineering Sangmyung UniversityCheonan31066Korea

With the commercialization of 5th-generation mobile communications(5G)networks,a large-scale internet of things(IoT)environment is being built.Security is becoming increasingly crucial in 5G network environments due to the growing risk of various distributed denial of service(DDoS)attacks across vast IoT devices.Recently,research on automated intrusion detection using machine learning(ML)for 5G environments has been actively conducted.However,5G traffic has insufficient data due to privacy protection problems and imbalance problems with significantly fewer attack data.If this data is used to train an ML model,it will likely suffer from generalization errors due to not training enough different features on the attack data.Therefore,this paper aims to study a training method to mitigate the generalization error problem of the ML model that classifies IoT DDoS attacks even under conditions of insufficient and imbalanced 5G traffic.We built a 5G testbed to construct a 5G dataset for training to solve the problem of insufficient data.To solve the imbalance problem,synthetic minority oversampling technique(SMOTE)and generative adversarial network(GAN)-based conditional tabular GAN(CTGAN)of data augmentation were used.The performance of the trained ML models was compared and meaningfully analyzed regarding the generalization error problem.The experimental results showed that CTGAN decreased the accuracy and f1-score compared to the Baseline.Still,regarding the generalization error,the difference between the validation and test results was reduced by at least 1.7 and up to 22.88 times,indicating an improvement in the problem.This result suggests that the ML model training method that utilizes CTGANs to augment attack data for training data in the 5G environment mitigates the generalization error problem.

关键词： 5G core traffic machine learning SMOTE GAN-CTGAN IoT DDoS detection tabular form cyber security B5G mobile network security

Empathic Responses of Behavioral-Synchronization in Human-Agent Interaction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第5期71卷 3761-3784页

作者： Sung Park Seongeon Park Mincheol Whang Savannah College of Art and Design SavannahGA31401USA Sangmyung University Seoul03016Korea

Artificial entities,such as virtual agents,have become more pervasive.Their long-term presence among humans requires the virtual agent’s ability to express appropriate emotions to elicit the necessary empathy from the users.Affective empathy involves behavioral mimicry,a synchronized co-movement between dyadic pairs.However,the characteristics of such synchrony between humans and virtual agents remain unclear in empathic interactions.Our study evaluates the participant’s behavioral synchronization when a virtual agent exhibits an emotional expression congruent with the emotional context through facial expressions,behavioral gestures,and voice.Participants viewed an emotion-eliciting video stimulus(negative or positive)with a virtual agent.The participants then conversed with the virtual agent about the video,such as how the participant felt about the content.The virtual agent expressed emotions congruent with the video or neutral emotion during the dialog.The participants’facial expressions,such as the facial expressive intensity and facial muscle movement,were measured during the dialog using a camera.The results showed the participants’significant behavioral synchronization(i.e.,cosine similarity≥.05)in both the negative and positive emotion conditions,evident in the participant’s facial mimicry with the virtual agent.Additionally,the participants’facial expressions,both movement and intensity,were significantly stronger in the emotional virtual agent than in the neutral virtual agent.In particular,we found that the facial muscle intensity of AU45(Blink)is an effective index to assess the participant’s synchronization that differs by the individual’s empathic capability(low,mid,high).Based on the results,we suggest an appraisal criterion to provide empirical conditions to validate empathic interaction based on the facial expression measures.

关键词： Facial emotion recognition facial expression virtual agent virtual human embodied conversational agent empathy human-computer interaction

Development of hyaluronic acid-based edible film for alleviating dry mouth

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Food Science and Human Wellness 2023年第2期12卷 371-377页

作者： Dong-Keon Kweon Jung-Ah Han Jinwoo Bio Co. Ltd.Yongin 17111Korea Department of Food and Nutrition Sangmyung UniversitySeoul 03016Korea

For alleviating dry mouth symptoms,edible films based on hyaluronic acid(HA)with 3 different m(800,1200 and 2300 kDa)were prepared(800 F,1200 F and 2300 F,respectively),and the properties as well as effectiveness were compared.The concentration of each HA dispersion for film forming was set as 3.0%,1.5%or 1.0%,for the m800,1200 and 2300 kDa,respectively,based on the solubility.The 800 F showed the highest thickness,tensile strength,and water vapor transparency,whereas obtained the lowest transparency and elongation at break among samples.All of the HA films showed safety against microorganism during 28 storage day at 40℃with 60%humidity.The optimum site for film attachment in mouth was the palate,and800 F was the most effective for stimulating saliva secretion,eliciting a 38%increase compared to control(without film),tested by the elderly over 65 years old.By the sensory test,800 F was also the most acceptable.Based on above results,the edible films effectively stimulating saliva secretion could be produced with HA,and the physical,sensory characteristics as well as disintegration times of the film could be controlled by mand the dissolution concentration of HA.

关键词： Edible film Hyaluronic acid Saliva stimulating Tensile strength Thickness

Performance Evaluation of Composite Electrolyte with GQD for All-Solid-State Lithium Batteries

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第1期74卷 55-66页

作者： Sung Won Hwang Dae-Ki Hong Department of System Semiconductor Engineering SangMyung UniversityCheonan-si31066Korea

The use a stabilized lithium structure as cathode material for batteries could be a fundamental alternative in the development of next-generation energy storage devices.However,the lithium structure severely limits battery life causes safety concerns due to the growth of lithium(Li)dendrites during rapid charge/discharge cycles.Solid electrolytes,which are used in highdensity energy storage devices and avoid the instability of liquid electrolytes,can be a promising alternative for next-generation batteries.Nevertheless,poor lithium ion conductivity and structural defects at room temperature have been pointed out as limitations.In this study,through the application of a low-dimensional graphene quantum dot(GQD)layer structure,stable operation characteristics were demonstrated based on Li^(+)ion conductivity and excellent electrochemical performance.Moreover,the device based on the modified graphene quantum dots(GQDs)in solid state exhibited retention properties of 95.3%for 100 cycles at 0.5 C and room temperature(RT).Transmission electronmicroscopy analysis was performed to elucidate the Li^(+)ion action mechanism in the modified GQD/electrolyte heterostructure.The low-dimensional structure of theGQD-based solid electrolyte has provided an important strategy for stably-scalable solid-state lithium battery applications at room temperature.It was demonstrated that lithiated graphene quantum dots(Li-GQDs)inhibit the growth of Li dendrites by regulating the modified Li^(+)ion flux during charge/discharge cycling at current densities of 2.2–5.5 mA cm,acting as a modified Li diffusion heterointerface.A full Li GQDbased device was fabricated to demonstrate the practicality of the modified Li structure using the Li–GQD hetero-interface.This study indicates that the low-dimensional carbon structure in Li–GQDs can be an effective approach for stabilization of solid-state Li matrix architecture.

关键词： Solid-state lithium batteries composite electrolyte quantum dot graphene

Flexible Memristive Devices Based on Graphene Quantum-Dot Nanocomposites

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第8期72卷 3283-3297页

作者： Sung Won Hwang Dae-Ki Hong Department of System Semiconductor Engineering SangMyung UniversityCheonan-si31066Korea

Artificial neural networks(ANNs)are attracting attention for their high performance in various fields,because increasing the network size improves its functioning.Since large-scale neural networks are difficult to implement on custom hardware,a two-dimensional(2D)structure is applied to an ANN in the form of a crossbar.We demonstrate a synapse crossbar device from recent research by applying a memristive system to neuromorphic chips.The system is designed using two-dimensional structures,graphene quantum dots(GQDs)and graphene oxide(GO).Raman spectrum analysis results indicate a D-band of 1421 cm^(−1) that occurs in the disorder;band is expressed as an atomic characteristic of carbon in the sp2 hybridized structure.There is also a G-band of 1518 cm^(−1) that corresponds to the graphite structure.The G bands measured for RGO-GQDs present significant GQD edge-dependent shifts with position.To avoid an abruptly-formed conduction path,effect of barrier layer on graphene/ITO interface was investigated.We confirmed the variation in the nanostructure in the RGO-GQD layers by analyzing them using HR-TEM.After applying a negative bias to the electrode,a crystalline RGO-GQD region formed,which a conductive path.Especially,a synaptic array for a neuromorphic chip with GQDs applied was demonstrated using a crossbar array.

关键词： Memristive devices neuromorphic chip resistive RAM quantum dot graphene

Biomass-derived bifunctional electrocatalysts for oxygen reduction and evolution reaction: A review

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2022年第2期31卷 149-172页

作者： Satpal Singh Sekhon Jaeyoung Lee Jin-Soo Park Future Environment and Energy Research Institute Sangmyung UniversityCheonan 31066Republic of Korea Department of Physics Guru Nanak Dev UniversityAmritsar 143005India Ertl Center for Electrochemistry and Catalysis Gwangju Institute of Science and Technology123 Cheomdangwagi-roBuk-guGwangju 61005Republic of Korea Department of Green Chemical Engineering College of EngineeringSangmyung UniversityCheonan 31066Republic of Korea

Oxygen electrode catalysts are important as inter-conversion of O_(2) and H_(2)O is crucial for energy technologies.However,the sluggish kinetics of oxygen reduction and evolution reactions(ORR and OER)are a hindrance to their scalable production,whereas scarce and costly Pt and Ir/Ru-based catalysts with the highest electrocatalytic activity are commercially unviable.Since good ORR catalysts are not always efficient for OER and vice versa,so bifunctional catalysts on which OER and ORR occurs on the same electrode are very desirable.Alternative catalysts based on heteroatom-doped carbon nanomaterials,though showed good electrocatalytic activity yet their high cost and complex synthesis is not viable for scalable production.To overcome these drawbacks,biomass-derived heteroatom-doped porous carbons have recently emerged as low-cost,earth-abundant,renewable and sustainable environment-friendly materials for bifunctional oxygen catalysts.The tunable morphology,mesoporous structure and high concentration of catalytic active sites of these materials due to heteroatom(N)-doping could further enhance their ORR and OER activity,along with tolerance to methanol crossover and good durability.Thus,biomassderived heteroatom-doped porous carbons with large surface area,rich edge defects,numerous micropores and thin 2 D nanoarchitecture could be suitable as efficient bifunctional oxygen catalysts.In the present article,synthesis,N-doping,ORR/OER mechanism and electrocatalytic performance of biomassderived bifunctional catalysts has been discussed.The selected biomass(chitin,eggs,euonymus japonicas,tobacco,lysine and plant residue)except wood,act as both C and N precursor,resulting in N selfdoping of porous carbons that avoids the use of toxic chemicals,thus making the synthesis a facile and environment-friendly green process.The synthetic strategy could be further optimized to develop future biomass-based N self-doped porous carbons as metal-free high performance bifunctional oxygen catalysts for commercial energy applications

关键词： Bifunctional catalysts Biomass ORR OER N-doping Porous carbons

在线全文

学校读者我要写书评

暂无评论

论冰雪运动对高校校园文化建设的影响

冰雪体育创新研究 2021年第18期 7-8页

作者： ZHANG SIYU Sangmyung University Seoul Korea 03016

冰雪运动作为常见冬季运动项目之一,深受高校学生的喜爱及支持,而引进高校校园后,不仅丰富高校体育的教学内容,更一定程度上活跃其课堂教学氛围。同时,高校学生广泛参与冰雪运动满足强健体魄的要求,促使其机体始终处于良好状态,有利于... 详细信息

冰雪运动作为常见冬季运动项目之一,深受高校学生的喜爱及支持,而引进高校校园后,不仅丰富高校体育的教学内容,更一定程度上活跃其课堂教学氛围。同时,高校学生广泛参与冰雪运动满足强健体魄的要求,促使其机体始终处于良好状态,有利于学生个体长远发展。该文以冰雪运动教学的现状为切入点,分析其对高校校园文化建设的影响,然后提出具体的建设措施,旨在为高校校园文化建设提供有效价值建议。

关键词：冰雪运动高校校园文化建设

在线全文

学校读者我要写书评

暂无评论

独立协会的民族主义与近代国家观(英文)

独立协会的民族主义与近代国家观(英文)

Link-Privacy Preserving Graph Embedding Data Publication with Adversarial Learning

北京论坛（2011）文明的和谐与共同繁荣--传统与现代、变革与转型

作者：朱镇五 Sangmyung University

The Independence Club pursued an autonomous reform program through the union of traditional reform ideas and a gradualism based on the principles of Social Darwinism. Its conception of the modern stat

关键词：

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2022年第2期27卷 244-256页

作者： Kainan Zhang Zhi Tian Zhipeng Cai Daehee Seo the Department of Computer Science Georgia State UniversityAtlantaGA 30303USA the Department of Electrical and Computer Engineering George Mason UniversityFairfaxVA 22030USA the National Center of Excellence in Software Sangmyung UniversitySeoul 03016Republic of Korea

The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph,which is amenable to be adopted in traditional machine learning algorithms in favor of vector representations.Graph embedding methods build an important bridge between social network analysis and data analytics,as social networks naturally generate an unprecedented volume of graph data continuously.Publishing social network data not only brings benefit for public health,disaster response,commercial promotion,and many other applications,but also gives birth to threats that jeopardize each individual’s privacy and security.Unfortunately,most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social networks.To be specific,attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network embedding.In this paper,we propose a novel link-privacy preserved graph embedding framework using adversarial learning,which can reduce adversary’s prediction accuracy on sensitive links,while persevering sufficient non-sensitive information,such as graph topology and node attributes in graph embedding.Extensive experiments are conducted to evaluate the proposed framework using ground truth social network datasets.

关键词： graph embedding privacy preservation adversarial learning