• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1726-1748
• /
• 2024

Trajectory planning is vital for autonomous systems like robotics and UAVs, as it determines optimal, safe paths considering physical limitations, environmental factors, and agent interactions. Recent advancements in trajectory planning and future location prediction stem from rapid progress in machine learning and optimization algorithms. In this paper, we proposed a novel framework for Spatial-temporal transformer-based feed-forward neural networks (STTFFNs). From the traffic flow local area point of view, skip-gram model is trained on trajectory data to generate embeddings that capture the high-level features of different trajectories. These embeddings can then be used as input to a transformer-based trajectory planning model, which can generate trajectories for new objects based on the embeddings of similar trajectories in the training data. In the next step, distant regions, we embedded feedforward network is responsible for generating the distant trajectories by taking as input a set of features that represent the object's current state and historical data. One advantage of using feedforward networks for distant trajectory planning is their ability to capture long-term dependencies in the data. In the final step of forecasting for future locations, the encoder and decoder are crucial parts of the proposed technique. Spatial destinations are encoded utilizing location-based social networks(LBSN) based on visiting semantic locations. The model has been specially trained to forecast future locations using precise longitude and latitude values. Following rigorous testing on two real-world datasets, Porto and Manhattan, it was discovered that the model outperformed a prediction accuracy of 8.7% previous state-of-the-art methods.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.8
• /
• pp.367-373
• /
• 2024

The growth of mobile devices and network infrastructure has brought significant changes to the music industry. Online streaming services has allowed music consumption without constraints of time and space, leading to increased consumer engagement in music creation and sharing activities, resulting in a vast accumulation of music data. In this study, we define metadata as "song sentences" by using a user's playlist. To calculate similarity, we embedded them into a high-dimensional vector space using skip-gram with negative sampling algorithm. Performance eva luation results indicated that the recommended music algorithm, utilizing singers, genres, composers, lyricists, arrangers, eras, seasons, emotions, and tag lists, exhibited the highest performance. Unlike conventional recommendation methods based on users' behavioral data, our approach relies on the inherent information of the tracks themselves, potentially addressing the cold start problem and minimizing filter bubble phenomena, thus providing a more convenient music listening experience.

• Applied Microscopy
• /
• v.36 no.1
• /
• pp.7-16
• /
• 2006

A new remote access system for a 1.3 MV high voltage electron microscope has been developed. Almost all essential functions for HVEM operation, huck as stage control, specimen tilting, TV camera selection and image recording, are successfully embedded into this prototype of the remote system. Particularly, this system permits perfect and precise operation of the goniometer and also controls the high resolution digital camera via simple Web browsers. Transmission of control signals and communication with the microscope is accomplished via the global ring network for advanced applications development (GLORIAD). This fact makes it possible to realize virtual laboratory to carry out practical national and international HVEM collaboration by using the present system

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.5
• /
• pp.335-340
• /
• 2013

This paper has designed and realized educational ZigBee equipment befitting to the USN environment. In addition, this study has enabled users to exercise operation process for software technology education and to propose software design methods in the process in the USN environment through practice equipment for ZigBee education. As for the development environment of system, Atmega128 process of Atmel is used for CPU; AVR compiler for the debugging environment; C language for firmware development language; and C++ for application program. The system operation process is initiated by coordinator's sensing information reading order from the hyper terminal through a server through the Internet or directly connected; and then delivering it to a terminating device by using ZigBee technology. The terminating device delivers various sensing information to the coordinator which delivers it to a server through the Internet or to a HYPER terminal directly connected to the coordinator. As for the educational course, it is about practices on such ZigBee operation process and relevant programing skills. Regarding it, the communication between coordinator and terminating device is designed by utilizing physical layer of ZigBee protocol, MAC layer and network layer while the communication between server and coordinator is designed by proposing an independent protocol on TCP/IP socket and the protocol processing procedure during sensing data delivery is verified by interpretation.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.51-57
• /
• 2023

Smart mirror is an IoT device that attaches a display and an embedded computer to the mirror and provides various information to the user along with the mirror function. This paper presents performance evaluation of the CoMirror system as an extension of the previous research in which proposed and implemented the CoMirror system that connects Smart Mirrors using a network. First, the login performance utilizing face recognition was evaluated. As result of the performance evaluation, it was concluded that the 40 face images are most suitable for face learning and only one face image is most suitable for face recognition for login. Second, as a result of evaluating the message transmission time, the average time was 0.5 seconds for text, 0.63 seconds for audio, and 2.9 seconds for images. Third, as a result of measuring a video communication performance, the average setup time for video communication was 1.8 seconds and the average video reception time was 1.9 seconds. Finally, according to the performance evaluation results, we conclude that the CoMirror system has high practicality.

• Journal of IKEEE
• /
• v.17 no.4
• /
• pp.407-417
• /
• 2013

In this paper, a reconfigurable peripheral unit for LED lighting communication is presented. Embedded lighting devices require various communication protocols. Usually, serial communication protocols and lighting control communication protocols such as DALI, DMX512, UART, SPI, IrDA, etc. are used in lighting devices. When the requirements of communication protocols are satisfied with separate IPs, the cost and the power consumption can considerably increase. We propose a reconfigurable communication peripheral unit which uses analysis of signal formats of the protocols. The gate count of the reconfigurable peripheral unit uses only 57% of the gate count of the separate implementation. Also, in this paper, a mapping table based DALI-ZigBee interfacing method for flexible lighting network configurations is proposed. Using this method, various DALI-ZigBee network systems can be easily set up. An LED lighting system platform is implemented to verify the operation of the DALI-ZigBee interfacing method. The reconfigurable peripheral unit and the DALI-ZigBee interfacing method can be efficiently used to implement various wired/wireless lighting communication systems.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.5
• /
• pp.467-474
• /
• 2019

In this paper, we propose a novel method to improve FPS while maintaining the accuracy of YOLO v2 model in NVIDIA Jetson TX1. In general, in order to reduce the amount of computation, a conversion to an integer operation or reducing the depth of a network have been used. However, the accuracy of recognition can be deteriorated. So, we use methods to reduce computation and memory consumption through adjustment of the filter size and integrated computation of the network The first method is to replace the $3{\times}3$ filter with a $1{\times}1$ filter, which reduces the number of parameters to one-ninth. The second method is to reduce the amount of computation through CBR (Convolution-Add Bias-Relu) among the inference acceleration functions of TensorRT, and the last method is to reduce memory consumption by integrating repeated layers using TensorRT. For the simulation results, although the accuracy is decreased by 1% compared to the existing YOLO v2 model, the FPS has been improved from the existing 3.9 FPS to 11 FPS.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.5
• /
• pp.847-857
• /
• 2020

As IoT equipment is commercialized, Bluetooth or wireless networks will be built into general living devices such as IP cameras, door locks, cars and TVs. Security for IoT equipment is becoming more important because IoT equipment shares a lot of information through the network and collects personal information and operates the system. In addition, web-based attacks and application attacks currently account for a significant portion of cyber threats, and security experts are analyzing the vulnerabilities of cyber attacks through manual analysis to secure them. However, since it is virtually impossible to analyze vulnerabilities with only manual analysis, researchers studying system security are currently working on automated vulnerability detection systems, and Firm-AFL, published recently in USENIX, proposed a system by conducting a study on fuzzing processing speed and efficiency using a coverage-based fuzzer. However, the existing tools were focused on the fuzzing processing speed of the firmware, and as a result, they did not find any vulnerability in various paths. In this paper, we propose IoTFirmFuzz, which finds more paths, resolves constraints, and discovers more crashes by strengthening the mutation process to find vulnerabilities in various paths not found in existing tools.

• The KIPS Transactions:PartC
• /
• v.15C no.4
• /
• pp.297-302
• /
• 2008

In case of display a lot of information from mobile devices, those systems are being developed that display the information from mobile devices on remote devices such as TV using the mobile devices as remote controllers because it is difficult to display a lot of information on mobile devices due to their limited bandwidth and small screen sizes. A lot of cost is required to design and develop interfaces for these systems corresponding to each of remote display devices. In this paper, a mobile environment based remote display system for displays at real times is proposed for continuous monitoring of status data for unique 'Mote IDs'. Also, remote data are collected and monitored through sensor network devices such as ZigbeX by applying status perception based remote displays at real times through processing ubiquitous computing environment data, and remote display applications at real times are implemented through PDA wireless mobiles. The system proposed in this paper consists of a PDA for remote display and control, mote embedded applications programming for data collections and radio frequency, server modules to analyze and process collected data and virtual prototyping for monitoring and controls by virtual machines. The result of the implementations indicates that this system not only provides a good mobility from a human oriented viewpoint and a good usability of accesses to information but also transmits data efficiently.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.121-127
• /
• 2022

Smart mirror is an IoT device that attaches a display and an embedded computer to the mirror and provides various information to the useer along with the mirror function. This paper went beyond the form of dealing with smart mirrors only stand alone device the provide information to users, and constructed a network in which smart mirrors are connected, and proposed and implemented a CoMirror system that allows users to talk and share information with other smart mirror users. The CoMirror system has a structure in which several CoMirror clients are connected on one CoMirror server. The CoMirror client consists of Raspberry Pi, a mirror film, a touch pad, a display device, an web camera, etc. The server has functions such as face learning and recognition, user management, a relay role for exchanging messages between clients, and setting up for video call. Users can communicate with other CoMirror users via the server, such as text, image, and audio messages, as well as 1:1 video call.