• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.10
• /
• pp.797-802
• /
• 2016

This paper proposes a noble voice recognition method based on an adaptive MFCC and deep learning for embedded systems. To enhance the recognition ratio of the proposed voice recognizer, ambient noise mixed into the voice signal has to be eliminated. However, noise filtering processes, which may damage voice data, diminishes the recognition ratio. In this paper, a filter has been designed for the frequency range within a voice signal, and imposed weights are used to reduce data deterioration. In addition, a deep learning algorithm, which does not require a database in the recognition algorithm, has been adapted for embedded systems, which inherently require small amounts of memory. The experimental results suggest that the proposed deep learning algorithm and HMM voice recognizer, utilizing the proposed adaptive MFCC algorithm, perform better than conventional MFCC algorithms in its recognition ratio within a noisy environment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.2C
• /
• pp.167-172
• /
• 2008

Since a 2-dimensional (2D) bar code can retrieve data and information quickly, it is widely used and recognized as a useful tool for many industrial applications. However, the information capacity of the 2D bar code is still limited. Recently the analog-digital code (AD code), which has the largest storage capacity yet contained in a code, has been developed, thereby expanding the bar code's application range because it overcomes the limitation of data capacity. In this paper, we present the AD code and implement an effective embedded system which can transform text information into voice using the 2D AD code and Text To Speech (TTS). This voice information can also be transmitted to blind people as well as the old by capturing the AD code on paper or in books.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.587-590
• /
• 2008

The Web 2.0 is mean to Web as Platform, as the platform provided various service using a data on webs by opening information. That is, it leads to the sharing and participation of information among internet users. In this paper, we research web technology for embedded computers which be supplied data and services to implement Ubiquitous computing. Therefore, we designed Open API service platform used the embedded system for the sharing and opening of web 2.0 trends. This designed platform is provided to internet users with various services and information in real-time.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.5
• /
• pp.1-10
• /
• 2008

In this paper, we discuss the development of an integrated HMI system based on OPC(OLE for Process Control) to control and monitor an automation equipment in the diverse environment. We implement an embedded OPC server according to the OPC standard which is proposed as the communication standard mechanism in the process control field, and design the interface module in which the output data of the OPC server can be connected to various HMI environment such as the local application, intranet client and Web page. This paper will be contributed in the HMI system implementation for the ubiquitous environment because it is possible to make remote control on the network and Web monitoring as well as the connection and data exchange of heterogeneous equipments by applying to various control systems.

• Journal of Korea Multimedia Society
• /
• v.25 no.4
• /
• pp.583-599
• /
• 2022

Although the object detection accuracy with a single image has been significantly improved with the advance of deep learning techniques, the detection accuracy for pig monitoring is challenged by occlusion problems due to a complex structure of a pig room such as food facility. These detection difficulties with a single image can be mitigated by using a video data. In this research, we propose a method in pig detection for video monitoring environment with a static camera. That is, by using both image processing and deep learning techniques, we can recognize a complex structure of a pig room and this information of the pig room can be utilized for improving the detection accuracy of pigs in the monitored pig room. Furthermore, we reduce the execution time overhead by applying a pruning technique for real-time video monitoring on an embedded board. Based on the experiment results with a video data set obtained from a commercial pig farm, we confirmed that the pigs could be detected more accurately in real-time, even on an embedded board.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.122-125
• /
• 2005

Data collection system is now widely used. This system is divided by embedded system and communication module. And data collection system in the remote area is using Satellite communication. So, data collection system is complicated and expensive. This paper proposes stabilization and cheapness of remote data collection system in dusty. The system can be composed simply through third party Satellite Communication programming of terminal including embedded system. Finally, collected data is transmitted to multi-user through web agent.

• Journal of the Korea Society for Simulation
• /
• v.27 no.2
• /
• pp.61-69
• /
• 2018

As the technology of information and communication has developed over recent years, an embedded system is applied in multiple industries and becomes more complicated. For this reason, embedded system development cost and time are also increased. For decreasing the cost and time, this paper suggests requirement evaluation method for concurrent development of an embedded system based on Discrete Event System(DEVS) Formalism. This paper proposes a method of describing the requirements specification in the form of DEVS atomic model. Also, the paper proposes the evaluator model that compares evaluation target system and the requirements model that is an implementation of requirement specification and proposes the evaluation method using them. In addition, we propose a method to utilize the requirement model created for requirements evaluation in the concurrent development process of the embedded system. As the case study, this paper proceeds requirement evaluation of Kinect depth data processing system.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.1
• /
• pp.63-74
• /
• 2005

The telematics device, which is a typical embedded system on the transportation or vehicle, requires the embedded spatial DBMS based on RTOS (Real Time Operating System) for processing the huge spatial data in real time. This spatial DBMS can be developed very easily by SQL3 functions of the ORDBMS such as UDT (user-defined type) and UDF (user-defined function). However, developing index suitable for the embedded spatial DBMS is very difficult. This is due to the fact that there is no built-in SQL3 functions to construct spatial indexes. In this study, we compare and analyze both Generalized Search Tree and Relational Indexing methods which are suggested as common ways of developing User-Defined Indexes nowadays. Two implementations of R-Tree based on each method were done and region query performance test results were evaluated for suggesting a suitable indexing method of an embedded spatial DBMS, especially for telematics devices.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.42 no.8 s.338
• /
• pp.27-34
• /
• 2005

In this paper, FPGA It/w and S/W Embedded system for LDM remote control is implemented. XScale CPU is used on developed system and in communcation ethenet and serial is used. CPU interface with H/W LDM rotation and to drive LDM FPGA logic is implemented, to transmit LDM data from long distance command packet is composed, for S/W Embedded linux is used to design linux device driver and linux application program. This S/W is run by module so by loading this module to linu)( file system it can do any movement. Also by compiling Embedded linux to the system it can lower the price of the system. By using this H/W and S/W theory it can be used on any other embedded system.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.8
• /
• pp.229-234
• /
• 2020

This paper presents the design and the implementation of CRESTIVE-DX, a concolic testing tool that distribute the concolic testing process over the embedded target system and the host system for efficient test generation of a target embedded program. CRESTIVE-DX conducts the execution of a target program on the target embedded system to consider possible machine-dependent behaviors of a target program execution, and conducts machine-independent parts, such as search-strategy heuristics, constraint solving, on host systems with high-speed computation unit, and coordinates their concurrent executions. CRESTIVE-DX is implemented by extending an existing concolic testing tool for C programs CREST. We conducted experiments with a test bed that consists of an embedded target system in the Arm Cortex A54 architecture and host systems in the x86-64 architecture. The results of experiments with Unix utility programs Grep, Busybox Awk, and Busybox Ed show that test input generation of CRESTIVE-DX is 1.59 to 2.64 times faster than that of CREST.