• Journal of Information Processing Systems
• /
• v.12 no.4
• /
• pp.644-660
• /
• 2016

The real-time detection of malware remains an open issue, since most of the existing approaches for malware categorization focus on improving the accuracy rather than the detection time. Therefore, finding a proper balance between these two characteristics is very important, especially for such sensitive systems. In this paper, we present a fast portable executable (PE) malware detection system, which is based on the analysis of the set of Application Programming Interfaces (APIs) called by a program and some technical PE features (TPFs). We used an efficient feature selection method, which first selects the most relevant APIs and TPFs using the chi-square ($KHI^2$) measure, and then the Phi (${\varphi}$) coefficient was used to classify the features in different subsets, based on their relevance. We evaluated our method using different classifiers trained on different combinations of feature subsets. We obtained very satisfying results with more than 98% accuracy. Our system is adequate for real-time detection since it is able to categorize a file (Malware or Benign) in 0.09 seconds.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.10
• /
• pp.2797-2808
• /
• 1999

Timing Constraint Petri Nets(TCPN) extend petri nets by adding timing constraints, it is provide a formal method for the modeling and analysis of real-time system. A real-time schedulability analysis decide that a set of concurrent processes will always meet its deadline. In this paper, we present TCPN model for real-time system include timing constraints and propose a schedulability analysis algorithm using them. Also, When the TCPN model is unscheduleable under the imposed timing constraints, we propose a recovery technique that will be scheduleable by the system specification modifying or timing constraints relaxing in the optimized time.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.227-241
• /
• 2021

Object detection techniques based on deep learning such as YOLO have high detection performance and precision in a single channel video stream. In order to expand to multiple channel object detection in real-time, however, high-performance hardware is required. In this paper, we propose a novel back-end server framework, a real-time AI vision platform (RAVIP), which can extend the object detection function from single channel to simultaneous multi-channels, which can work well even in low-end server hardware. RAVIP assembles appropriate component modules from the RODEM (real-time object detection module) Base to create per-channel instances for each channel, enabling efficient parallelization of object detection instances on limited hardware resources through continuous monitoring with respect to resource utilization. Through practical experiments, RAVIP shows that it is possible to optimize CPU, GPU, and memory utilization while performing object detection service in a multi-channel situation. In addition, it has been proven that RAVIP can provide object detection services with 25 FPS for all 16 channels at the same time.

• The KIPS Transactions:PartA
• /
• v.16A no.5
• /
• pp.307-318
• /
• 2009

Modeling and rendering of atmospheric phenomena such as clouds is one of most difficult research themes in the field of computer graphics, mainly due to its complexity, huge volume, ubiquitousness, etc. In this paper, we represent a system for real-time modeling and rendering of clouds, mainly aiming at the computer games and flight simulation applications. Our implementation generates various kinds of clouds including cirrus, stratus, and cumulus, through intuitive real-timeuser interactions. Then, additional details are automatically attached to them, using our own methods based on meta-balls or hierarchical spherical particles. After processing multiple scattering and anisotropic scattering, resulting particles are rendered into billboards, to finally achieve real-time processing.

• Korea Information Processing Society Review
• /
• v.12 no.4
• /
• pp.114-125
• /
• 2005

• Journal of IKEEE
• /
• v.5 no.2 s.9
• /
• pp.164-173
• /
• 2001

In this paper, we have designed and implemented a new hard embedded real-time system to satisfy hard real-time constraints in moving independently. Real-time kernel should be small size, fast and predictable. Because of the great variety of demands on real time scheduling, a real time kernel should also include a flexible and re-programmable task scheduling discipline. In this paper, we present that real-time applications should be split into small and simple parts with hard real-time constraints. To satisfy these properties, we designed real-time kernel and general kernel, that have their different properties. In real-time tasks, interrupt processing should be run. In general kernel, non real time tasks or general tasks are run. The efficiency of the proposed hard embedded real-time system is shown by comparison results for performance of the proposal real time kernel with both RT-Linux and QNX.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.3
• /
• pp.992-999
• /
• 2000

Textile dimension inspection is one of the basic issues in the textile dyeing and finishing industry. And also, it a plays an important role in the quality control of total fabric products. In this paper, we implement a real-time textile dimension inspection system which detects various real defects, defects positions of textile and the density of textiles. The proposed method consists of textile density measurement algorithms with zone-occurrence features from subband image which detect various types of real defects. The performance of the proposed method is tested with a number of real textile samples with 10 types of defects and three basic structures of textile. By the dimension inspection of textile at continuous stages in the fabrication process, it is possible to measure the density of textile up to 150m/min and to detect the defect of textile at real time within $\pm$1% error percentages. And also it can be monitored the condition of textile throughout at all the significant working process and can be improved textile quality.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.3
• /
• pp.57-62
• /
• 2000

In recent, the innovative improvement of a internet and computing environment make users desire the capability of processing information in real time. In this paper we implement a PC-to-PC real time multi-user communication system on the internet environment using the efficient algorithm for a real time processing and the MFEG-4 CELP codec which can be used for a low bit-rate coding from 6 to 24kbps. The implemented system produces a compressed bit-streams with the MPEG-4 CEU Mode-I 18200bps mode. There is 5 frames for a package and 1 frame has 160 samples. We can use this system to communicate with 4 users simultaneously in real time. The system is designed and examined on the Windows operating system.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.2
• /
• pp.507-519
• /
• 2000

n this paper, we implement the real-time scheduler which performs extended schedulability testing, to reconfigure Mach kernel in which Real-Time scheduling is possible. for this purpose, first, we propose the configuration factors according to requirements of Real-Time operation systems and we analyze a Real-time scheduling algorithm. Second, for the reconfiguration of Mach kernel, we propose the modified data structure through the analysis of Mach kernel environments and scheduling. Third, we suggest the extended scheduling method by analyzing conventional Real-Time scheduling policies. Fourth, we implement the scheduler which executes tasks according to the Earliest-Deadline-First scheduling and the Rate Monotonic scheduling.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.79-84
• /
• 2023

Apache Spark, which provides the fastest processing speed among recent distributed and parallel processing technologies, provides real-time functions and machine learning functions. Although official documentation guides for these functions are provided, a method for fusion of functions to predict a specific value in real time is not provided. Therefore, in this paper, we conducted a study to predict the value of data in real time by fusion of these functions. The overall configuration is collected by downloading stock price data provided by the Python programming language. And it creates a model of regression analysis through the machine learning function, and predicts the adjusted closing price among the stock price data in real time by fusing the real-time streaming function with the machine learning function.