Young Im Cho

Integrating of Data Using the Hadoop and R

Abstract The article offers a data integration model, which must be supported by a unified view of disparate data sources, management of integrity constraints, management of data manipulation and query executing operations, matching data from various sources, the ability to expand and set up new data sources. The proposed approach is the integration of Hadoop-based data and R, which is popular for processing statistical information. Hadoop database contains libraries, Distributed File System (HDFS), and resource management platform and implements a version of the MapReduce programming model for processing large-scale data. This model allows us to integrate various data sources at any level, by setting arbitrary links between circuit elements, constraints and operations.

Application of multi-agent control systems in energy-efficient intelligent building

The features provide the required comfort multizone buildings by using the power management multiagent system and comforts. This management system covers all controlled areas of the building and, if necessary, ensures the highest possible overall comfort in a building with a decrease in available electric power. The aim of this work is to develop a comfort control system multispectral building.

Smart Building Climate Control Considering Indoor and Outdoor Parameters

Heating, ventilation, and air conditioning (HVAC systems) account for the majority of the energy used in buildings. Consequently, any business has the potential to realize significant cost savings by improving control of HVAC operations and increase the efficiency of the system it uses. Using a highly efficient HVAC equipment can lead to significant energy and emissions savings. The entire structure of the building in combination with the enhanced comfort zone can produce a much greater savings. Extended comfort includes the use of concepts such as providing a warm, but drier air using a desiccant dehumidification in the summer, or the colder air from the warm walls of windows and warm in winter. In addition, high efficiency HVAC can provide enhanced thermal comfort for people, as well as to contribute to the improvement of environmental quality in the room. The paper explores thermal process and the affecting parameters, and introduce fuzzy logic based energy consumption model based on controlling of HVAC devices.

Intelligent UAV in smart cities using IoT

The concept of a Smart City is becoming an increasingly important research area around the world. The amount of information collected and the number of stationary sensors, surveillance cameras and other devices that need to be places in a smart city is so vast that using a mobile platform to replace them can reduce the cost in both energy and resources. This paper proposes an open source intelligent IoT platform that would allow implementation of various Smart City services such as: smart home, smart unmanned aerial vehicle, smart energy grid, smart transportation systems and other possible future services that will evolve along with the consumer demand. A smart platform is enabled by Machine-to-Machine communications and multi-agent system architecture. Such a platform will allow solving multiple issues with the smart city implementation such as scalability, integration and interoperation of different IoT services and networks that are run on different hardware. We discuss the structure of such a platform.

A Prediction Model Based on Relevance Vector Machine and Granularity Analysis

In this paper, a yield prediction model based on relevance vector machine (RVM) and a granular computing model (quotient space theory) is presented. With a granular computing model, massive and complex meteorological data can be analyzed at different layers of different grain sizes, and new meteorological feature data sets can be formed in this way. In order to forecast the crop yield, a grey model is introduced to label the training sample data sets, which also can be used for computing the tendency yield. An RVM algorithm is introduced as the classification model for meteorological data mining. Experiments on data sets from the real world using this model show an advantage in terms of yield prediction compared with other models.

Analysis and Development of Agent Architecture for Pest Control Systems

Abstract While developing the control system process in which robot performing various operations it is essential observance of many limitations. Currently, there are technological capabilities to take into account many factors in the estimating of the large amount of calculations associated with the existing of factors and constraints. It is known that there are many factors occur at random during the execution of operations. To solve the explicit and implicit factors it is necessary to improve the architecture of existing system. In this paper we analysis previously developed MAS, focusing on its architecture and its agents. As the result of analysis there found main indicators of MAS in terms of their structures, actions, parameters, type, number and purpose. Described the agent forming procedure, where it is carries out movements in a predetermined pattern. During the execution of tasks agent is in an environment, where it is meet different obstacles in form, type and level of complexity. Also we considered several obstacles avoidance algorithms. Presented architecture of the agents will be used in the multi-agent based pest control systems, which will be used in agriculture.

Multi-Agent Based Anti-Locust Territory Protection System☆

Abstract Locust invasion still remains danger to crops and vast unused fields in certain parts of the world. This problem is also relevant to Kazakhstan. Every year the government allocates 16 million USD to control locusts’ population, and prevent damages that they cause after its intrusion. The aim of this paper is to define the concept of developing an anti-locust multi-agent territory protection system (ALMATPS), which consists of heterogeneous robots such as unmanned aerial vehicles (UAV), ground robots (GR) or unmanned ground vehicles (UGV) (there is no different between these two terms, both can be used). These heterogeneous robots collaborate with each to achieve the main goal using the agent based modeling (ABM).

Development of Visibility Expectation System Based on Machine Learning

Visibility impairment is maximum definitely defined because the formation of haze that obscures the clarity, shade, texture, and form of what’s visible through the atmosphere. It’s far a complex phenomenon inspired via some of the emissions and air pollutants and tormented by some of the herbal factors which include temperature, humidity, meteorology, time and sunlight. The aim of the research is that to estimate weather visibility using machine learning techniques. We use images taken from CCTV cameras as inputs and deep convolutional neural network model to predict results. We implemented Java based GUI application that can flexibly operate all operations in real-time. Users are also able to use a specially built web page to estimate visibility that a built-in machine learning (ML) model gives an opportunity to the user to get results. In this paper, we will detail explain regarding an architecture of the ML model, System Structure, and other essential details.

Intelligent smart city platform

Smart City platform have been developed in the city and national level. From Smart City, IoT is an important means to resolve current issues. Technical elements of the IoT is sensing, wired and wireless communications, network, service interfaces, big data, security etc. Usually, Machine-to-Machine communications (M2M) is a phenomenon that has been proceeding quietly in the background. Current international standard was presented as a reference model in One M2M which is leading IoT. The four areas are IoT service-centric platform, data-centric platform, connectivity-centric platform, and device platform. To avoid creation of competing M2M standards the 7 standards developing organizations, that publish telecom standards: TTC, ARIB (Japan), ATIS, TIA (USA), TTA (Korea) CCSA (China), ETSI (Europe) started the OneM2M Global Initiative to develop one globally agreed M2M Specification with initial focus on Service Layer. OneM2M aims to consolidate current M2M Service Layer standards activities such as ETSI TC M2M (Europe), TIA TR-50 (USA) and CCSA TC 10 (China), and to reduce standardization overlap and confusion and provide ongoing standards support to enhance interoperability, reduce market fragmentation, and improve security and reliability. (Ref: http://www.eclipse.org/proposals/technology.om2m/). However, there is no international standardized IoT platform including data, service, connectivity and device, what is more there is no clear national standardized platform satisfy the reference model that is presented by oneM2M institute which is a leading organization to establish an international IoT standardized platform. In this seminar, I am going to talk about some topics like following: IoT and Smart City basic, IoT International platform focusing on OneM2M reference model, components and model description for IoT platform. Thank you.

Development of Query Transformation Method by Cost Optimization

The transformation time among queries in the database management system (DBMS) is responsible for the execution time of users’ queries, because a conventional DBMS does not consider the transformation cost when queries are transformed for execution. To reduce the transformation time (cost reduction) during execution, we propose an optimal query transformation method by exploring queries from a cost-based point of view. This cost-based point of view means considering the cost whenever queries are transformed for execution. Toward that end, we explore and compare set off heuristic, linear, and exhaustive costbased transformations. Further, we describe practical methods of cost-based transformation integration and some query transformation problems. Our results show that, some cost-based transformations significantly improve query execution time. For instance, linear and heuristic transformed queries work 43% and 74% better than exhaustive queries.