• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.4
• /
• pp.88-95
• /
• 2022

Detecting anomalies in human movement is an important task in industrial applications, such as monitoring industrial disasters or accidents and recognizing unauthorized factory intruders. In this paper, we propose an abnormal worker movement detection system based on data stream processing and hierarchical clustering. In the proposed system, Apache Spark is used for streaming the location data of people. A hierarchical clustering-based anomalous trajectory detection algorithm is designed for detecting anomalies in human movement. The algorithm is integrated into Apache Spark for detecting anomalies from location data. Specifically, the location information is streamed to Apache Spark using the message queuing telemetry transport protocol. Then, Apache Spark processes and stores location data in a data frame. When there is a request from a client, the processed data in the data frame is taken and put into the proposed algorithm for detecting anomalies. A real mobility trace of people is used to evaluate the proposed system. The obtained results show that the system has high performance and can be used for a wide range of industrial applications.

• Journal of the Institute of Convergence Signal Processing
• /
• v.14 no.1
• /
• pp.62-69
• /
• 2013

This paper proposes real-time video transmission system by the car-mounted cameras based on MOST Network. Existing vehicles transmit videos by connecting the car-mounted cameras in the form of analog. However, the increase in the number of car-mounted cameras leads to development of the network to connect the cameras. In this paper, DSP is applied to process MPEG 2 encoding/decoding for real-time video transmission in a short period of time. MediaLB is employed to transfer data stream between DSP and MOST network controller. During this procedure, DSP cannot transport data stream directly from MediaLB. Therefore, FPGA is used to deliver data stream transmitting MediaLB to DSP. MediaLB is designed to streamline hardware/software application development for MOST Network and to support all MOST Network data transportation methods. As seen in this paper, the test results verify that real-time video transmission using proposed system operates in a normal matter.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.39 no.5
• /
• pp.86-96
• /
• 1997

The arrangement of small streams in rural area, in the past times, attached importance to the prevention of flood damage through the straightening and lining of streams. Recently, the way of small stream arrangement is introducing the idea of water friendly environment or friendly space. As a result, there has been much concern with water favorable river management model which may lead to control flood. However, it is very difficult to develop a model applicable to all types of rivers, since each river has different flow velocity, flow amount and unique ecological characteristics. In this study, photo processing technique, one of landscape simulation methods, has been adopted because it helps to visually express and comprehensively evaluate pre and post scenery and easily applicable. Some important guideline and technique for the planning of small stream landscape arrangement are mentioned in this study. The simulation system for acquiring water favorable space and arranging landscapes needs to develop database which can forecast various types of landscape. It may also be used for the bases of planning and designing river environment arrangement. Computer aided image processing system enables to make selective planning in river environment arrangement. It may also enables to develop the methods for river environment development, ecology conservation, and multipurpose space utilization. Moreover, it makes economic river arrangement by applying river environment arrangement methods relevant to geographical characteristics. There are some limitations in this study, such as shortage of exact investigation on the stream direction and velocity in landscape arrangement. Continuous monitoring and research may be required to develop techniques through the application of computer graphics and digital image processing.

• The KIPS Transactions:PartD
• /
• v.17D no.6
• /
• pp.453-462
• /
• 2010

The switch from analog to digital broadcast television is extended rapidly. The DTV can offer multiple programming choices, interactive capabilities and so on. Moreover, with the spread of Internet, the information exchange between the communities is increasing, too. These facts lead to the new TV service environment which can offer customized TV programs to personal/community users. This paper proposes a 'Customized Digital TV System for Individuals/Communities based on Data Stream Mining' which can analyze user's pattern of TV watching behavior. Due to the characteristics of TV program data stream and EPG(electronic program guide), the data stream mining methods are employed in the proposed system. When a user is watching DTV, the proposed system can control the surrounding circumstances as using the user behavior profiles. Furthermore, the channel recommendation system on the smart phone environment is proposed to utilize the profiles widely.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.40 no.6
• /
• pp.57-69
• /
• 1998

The creation of favorable water space, in our living circumferential space, is very important factor to offer rural scenery to neighbor residents. We are to introduce stream landscape arrangement technique considering favorable water environment against conventional methods. In this study, the modeling district is Seungdu small stream of Ansung river system in Pyung-Teak city, Kyonggi province, and we carried out stream landscape simulation. The arranging plans of landscape are classified ti three types. The first one is conservation type of ecological environment that can express natural characteristics of stream inherence, raise variety of living things and construct coexisting environment between human beings and the other living things. The secong one is favorable water approach type. The basic object of this type is space construction for easy approach to waterside and increase of comfortable feelings of spectators. The third one is water utilization/flood control management type. In planning of environmentally favorable landscape arrangement, this type is the most important but is likely to be ignored. This type is an arranging plan of stream landscape considering safety. Also, we developed Streams Landscape Simulation System(SLSS). This program can be used for comparison of original landscape image with simulated one. To apply SLSS on the interested stream, landscape simulation that is based on hydraulic characteristics, runoff, flow direction, detailed conditions of basin and ecosystem of stream have to be executed. In this point, developing a stereographical technique of image processing and exact study of applying plan have to be executed continually.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.2
• /
• pp.102-106
• /
• 2011

The transfer capability of HFC (Hybrid Fiber Coax) network is superior to xDSL. HFC network, however, is not suitable for transferring high quality video due to cable model interfaces. For the services of high quality IPIV or VOD, the extra exclusive downstream transfer system is required without upgrading pre-equipped cable modem and service capability. This paper is aimed to develop the extra exclusive downstream transfer system not changing existing cable modem system but providing same quality of services. This system is composed of the extra exclusive downstream IP-cable sender and modem. This sender and modem have 30 Mbps transfer capability and HDTV stream can be served in the Cable TV network using 21 Mbps HDTV transport stream.

• ETRI Journal
• /
• v.44 no.1
• /
• pp.62-72
• /
• 2022

In this study, we propose a multi-GPU-based 8KVR stitching system that operates in real time on both local and cloud machine environments. The proposed system first obtains multiple 4 K video inputs, decodes them, and generates a stitched 8KVR video stream in real time. The generated 8KVR video stream can be downloaded and rendered omnidirectionally in player apps on smartphones, tablets, and head-mounted displays. To speed up processing, we adopt group-of-pictures-based distributed decoding/encoding and buffering with the NV12 format, along with multi-GPU-based parallel processing. Furthermore, we develop several algorithms such as equirectangular projection-based color correction, real-time CG overlay, and object motion-based seam estimation and correction, to improve the stitching quality. From experiments in both local and cloud machine environments, we confirm the feasibility of the proposed 8KVR stitching system with stitching speed of up to 83.7 fps for six-channel and 62.7 fps for eight-channel inputs. In addition, in an 8KVR live streaming test on the 5G MEC/cloud, the proposed system achieves stable performances with 8 K@30 fps in both indoor and outdoor environments, even during motion.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.2
• /
• pp.385-395
• /
• 1999

Video-On-demand system provides electronic video rental services from remote video servers on a broadband communication networks. When we assume some situation that serve the same video stream by batching, each time single video stream became available at server-end side, we face the problem that what video stream to be scheduled at what time instant. Hence, in order to manage the resource bandwidth which is different at each stream, the policy of channel allocation became important factor. In this work, we proposed three type of scheduling policies with queueing, as are cumulative Waiting Time(CWT), Mean Waiting Time(MWT) and Predictable Popular Factor(PPF). While CWT policy is good for popular video, MWT policy was good for non-popular video. Also, we know that PPT policy has some fairness for average wait time and reneging rate of user requests.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.4
• /
• pp.575-580
• /
• 2018

This paper discusses system for real-time monitoring of patient waiting time in hospitals based on open-source platform. It is necessary to make use of open-source projects to develop a high-performance stream processing system, which analyzes and processes stream data in real time, with less cost. The Hadoop ecosystem is a well-known big data processing platform consisting of numerous open-source subprojects. This paper first defines several requirements for the monitoring system, and selects a few projects from the Hadoop ecosystem that are suited to meet the requirements. Then, the paper proposes system architecture and a detailed module design using Apache Spark, Apache Kafka, and so on. The proposed system can reduce development costs by using open-source projects and by acquiring data from legacy hospital information system. High-performance and fault-tolerance of the system can also be achieved through distributed processing.

• The Journal of Korean Institute of Information Technology
• /
• v.16 no.12
• /
• pp.1-11
• /
• 2018

Recently, the volume of online shopping market continues to be fast-growing, that is important to provide customized service based on customer behavior evaluation analysis. The existing systems only provide analysis data on the profiles and behaviors of the consumers, and there is a limit to the processing in real time due to disk based mining. There are problems of accuracy and system performance problems to apply existing systems to web services that require real-time processing and analysis. Therefore, The system proposed in this paper analyzes the web click log streams generated in real time to calculate the concentration level of specific products and finds interested customers which are likely to purchase the products, and provides and intensive promotions to interested customers. And we verify the efficiency and accuracy of the proposed system.