Hyunjoong Kang

An in-depth analysis on traffic flooding attacks detection and system using data mining techniques

Recently, as network traffic flooding attack such as DoS and DDoS have posed devastating threats on network services, rapid detection, and semantic analysis are the major concern for secure and reliable network services. In addition, in a recent issue of the safety and comfort of vehicles and communication technologies for service is required. We propose a traffic flooding attack detection and an in-depth analysis system that uses data mining techniques. In this paper we (1) designed and implemented a system that detects traffic flooding attacks. Then, it executes classification by attack type and it uses SNMP MIB information based on C4.5 algorithm; (2) conducted a semantic interpretation that extracts and analyzes the rules of execution mechanism that are additionally provided by C4.5; (3) performed an in-depth analysis on the attack patterns and useful knowledge inherent in their data by type, utilizing association rule mining. Classification by attack and attack type based on C4.5 and association rules, automatic rule extraction and semantic in-depth interpretation, which are proposed in this paper, provide a positive possibility to add momentum towards the development of new methodologies for intrusion detection systems as well as to support establishing policies for intrusion detection and response systems.

A conceptual device-rank based resource sharing and collaboration of smart things

Lately, inspired by Internet of Things (IoT), the era of connected everything is coming. But still, things hardly show the manner to share resources on it and self-configuration method to compose collaboration of smart things. Moreover, it is not easy to harmonize things of related action with added or removed devices to aid process being conducted by human or services of applications. In this paper, we propose a concept for supporting a collaboration augmentation of devices used in the IoT. The Device-Rank for the augmenting collaboration of things proposed in this paper is a technology used to rate IoT things based on diverse elements such as the frequency with which users use individual things, the distances to users or service objects, the network QoS, the performance of the things, and their operation histories, such that the resultant information can be used by a cloud-based platform or device itself to calculate the Device-Rank information. This Device-Rank is expected to be accumulated and updated by things or a platform, and exchanged between things such that things can more actively collaborate with other things or services and augment the Device-Rank with the passing of time.

Dynamic greenhouse supplemental light source control with wireless sensor network

The key factors for the good quality and productivity of crop growth in green house are monitoring and controlling. Most study focuses on the effect of each light source while optimal light adjustment has rarely been investigated. In this paper, we suggest new generation of greenhouse monitoring & controlling system based on dynamic supplemental light source control with wireless sensor. And also, we provide method on how to control light source more optimally using cumulative light data. Through the six-month of control and experiment in Damyang testbed, we demonstrate the growth analysis by the effect on the dynamic supplemental light control.

A Study on Image Processing Based Leaf Area Measurement

Leaf parameters are the most important information for making cultivation method in productive, studies of plant growth element. In this paper, we introduce the image processing method of homography in leaf area estimation. In leaf area image processing steps for leaf area estimation, the first step for measuring is image capturing and frame storing so that the required leaf sample can be acquired. When the leaf is being captured, leaf is put on a white paper with a square reference marker. Leaf is placed in parallel with square marker. The second step is image preprocessing for changing color space and removing noise. The third step is extracting maker area and calculating size from the image frame. The marker has shape of square and diameter of square is 1centimeter. The last step is leaf area extracting and calculation.

Augmented ontology by handshaking with machine learning

Artificial intelligence products are already around us and will be emerging dramatically a lot in near future. Artificial intelligence is all about data analysis. When it comes to data analysis, there are two representative techniques: machine learning and semantic technology. They stand on the other side from where to begin analysis. Simply speaking, machine learning is based on the data while semantic technology relies on human domain knowledge (human learning). What if collected data are insufficient to reflect whole phenomenon? This is a limitation of machine learning. What if circumstance changes a lot as time goes by? Manual rule updating by experts is not a good solution in that circumstance. Based on these observations, we investigate two approaches and find a good solution which maximizes the advantages of both techniques and mitigates the limitations of them. This paper suggests a novel integration idea to compensate each technology with the other: that is semantic filtering. This paper includes a toy semantic modelling and a machine learning algorithm implementation to realize the proposed concept, semantic filtering.

Dynamic crop field analysis using mobile sensor node

Recently, various IT technologies are utilized to support crop growth management. In farming field, dynamic data analysis while moving is cost efficient tool to farmer. Unlike previous works that not support dynamic analysis, mobile devices need to acquire the most recent data from nearest sensor for efficient processing in mobile device. In this paper, we designed the dynamic crop field analysis methods using mobile sensor node. Using the mobile sensor node, field analysis such as trend, correlation and summary has become more efficient by using dynamic data search and comparing. We implement mobile sensor node and dynamic field analysis application on Win Mobile 6 PDA and evaluated the usefulness in large scale outdoor test-bed of a vineyard in Napa valley.

A Design of IoT Based Agricultural Zone Management System

The IoT (Internet of Things) is a technology that enables the continuous communication between things or between things and humans. The IoT is expected to be applied to various industry fields in our society, thereby changing our lives to be more effective and productive. Agricultural IT technology, which apply IT technologies to agriculture, improves the quality of crops and provides the production and distribution information to consumers. As a result, such technologies are expected to realize the generation of high added values such as improved productivity, efficiency, and product quality across the whole process for agricultural products from production to distribution to consumption. This study suggests a system that can help growers more effectively manage and optimize the growing environments by realizing various information exchanges through a system that enables more flexible and intelligent cultivation and management with logically grouping and managing agricultural production environments based on the IoT technology.

PAGE: Answering Graph Pattern Queries via Knowledge Graph Embedding.

Answering graph pattern queries have been highly dependent on a technique—i.e., subgraph matching, however, this approach is ineffective when knowledge graphs include incorrect or incomplete information. In this paper, we present a method called \(\mathtt {PAGE}\) that answers graph pattern queries via knowledge graph embedding methods. \(\mathtt {PAGE}\) computes the energy (or uncertainty) of candidate answers with the learned embeddings and chooses the lower-energy candidates as answers. Our method has the two advantages: (1) \(\mathtt {PAGE}\) is able to find latent answers hard to be found via subgraph matching and (2) presents a robust metric that enables us to compute the plausibility of an answer. In evaluations with two popular knowledge graphs, Freebase and NELL, \(\mathtt {PAGE}\) demonstrated the performance increase by up to 28% compared to baseline KGE methods.

The method of providing dynamic IP management function in a gateway for IoE

This paper is about the gateway that supports the Dynamic IP management function. To be specific, this paper shows the way how management system finds out IP address of the gateway in order to make communication available when the gateway that provides IoE service in the mobile communications network obtains Dynamic IP.

A design of IoT device similarity vector based workflow management system

Nowadays, versatile IoT Devices are connected through the Internet and provide numerous dynamic services. However, until now, these kinds of services are just following established service or application rules. For this reason, an application cannot deal with a condition when rule is not previously set. Additionally, rules should be renewed by reflecting each condition, and software should be re-developed which are costly and time-consuming. To address this issue, we suggest a machine learning and semantic information based IoT devices management system.