• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4065-4083
• /
• 2021

Super-resolution can improve the clarity of low-resolution (LR) images, which can increase the accuracy of high-level compute vision tasks. Portable devices have low computing power and storage performance. Large-scale neural network super-resolution methods are not suitable for portable devices. In order to save the computational cost and the number of parameters, Lightweight image processing method can improve the processing speed of portable devices. Therefore, we propose the Enhanced Information Multiple Distillation Network (EIMDN) to adapt lower delay and cost. The EIMDN takes feedback mechanism as the framework and obtains low level features through high level features. Further, we replace the feature extraction convolution operation in Information Multiple Distillation Block (IMDB), with Ghost module, and propose the Enhanced Information Multiple Distillation Block (EIMDB) to reduce the amount of calculation and the number of parameters. Finally, coordinate attention (CA) is used at the end of IMDB and EIMDB to enhance the important information extraction from Spaces and channels. Experimental results show that our proposed can achieve convergence faster with fewer parameters and computation, compared with other lightweight super-resolution methods. Under the condition of higher peak signal-to-noise ratio (PSNR) and higher structural similarity (SSIM), the performance of network reconstruction image texture and target contour is significantly improved.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2003.11a
• /
• pp.239-250
• /
• 2003

In this research, we propose a hybrid group decision support mechanism (H-GDSM) based on Fuzzy AHP (Analytic Hierarchy Process) and FCM (Fuzzy Cognitive Map). The AHP elicits a corresponding priority vector interpreting the preferred information among the decision makers. Corresponding vector was composed of the pairwise comparison values of a set of objects. Since pairwise comparison values are the judgments obtained from an appropriate semantic scale. However, AHP couldn't represent the causal relationship among information, which were used by decision makers. In contrast to AHP, FCM could represent the causal relationship among variables or information. Therefore, FCMs were successfully developed and used in several ill-structured domains, such as strategic decision-making, policy making, and simulations. Nonetheless, many researchers used subjective and voluntary inputs to simulate the FCM. As a result of subjective inputs, it couldn't avoid the rebukes of businessman. To overcome these limitations, we incorporated the Fuzzy membership functions, AHP and FCM into a H-GDSM. In contrast to current AHP methods and FCMs, the H-GDSM method developed herein could concurrently tackle the pairwise comparison involving causal relationships under a group decision-making environment. The strengths and contributions of our mechanism were 1) handling of qualitative knowledge and causal relationships, 2) extraction of objective input value to simulate the FCM, 3) multi-phase group decision support based on H-GDSM. To validate our proposed mechanism we developed a simple prototype system to support negotiation-based decisions in electronic commerce (EC).

• Journal of the Korean Chemical Society
• /
• v.19 no.5
• /
• pp.343-350
• /
• 1975

About 20${\sim}$100${\mu}g$ iridium have been extracted quantitatively as stannous-chloro Complex from aqueous solution by Alamine-336, a high molecular weight tertiary amine, dissolved in benzene. The extractability was confirmed by radioactive tracer of iridium-192. The spectrophotometric measurements of the extracted species at 322.5 nm indicate the feasibility of this method to be used as an analytical procedure for the determination of micro amount of iridium. An anion model of stannous-chloro complex of iridium has been postulated to account for the extraction mechanism.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.196-201
• /
• 2004

In biometric and biomedical applications, a special transporting mechanism must be designed for the ${\mu}$TAS (micro total analysis system) to move samples and reagents through the microchannels that connect the unit procedure components in the system. An important issue for this miniaturization and integration is microfluid management technique, i.e., microfluid transportation, metering, and mixing. In view of this, this study presents an optimal fuzzy sliding-mode control (OFSMC) design based on the 8051 microprocessor and implementation of a complete microfluidic manipulated system implementation of biochip system with a pneumatic pumping actuator, a feedback-signal photodiodes and flowmeter. The new microfluid management technique successfully improved the efficiency of molecular biology reaction by increasing the velocity of the target nucleic acid molecules, which increases the effective collision into the probe molecules as the target molecules flow back and forth. Therefore, this hybridization chip was able to increase hybridization signal 6-fold and reduce non-specific target-probe binding and background noises within 30 minutes, as compared to conventional hybridization methods, which may take from 4 hours to overnight. In addition, the new technique was also used in DNA extraction. When serum existed in the fluid, the extraction efficiency of immobilized beads with solution flowing back and forth was 88-fold higher than that of free-beads.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.6
• /
• pp.1857-1862
• /
• 2016

Human activity recognition using depth information is an emerging and challenging technology in computer vision due to its considerable attention by many practical applications such as smart home/office system, personal health care and 3D video games. This paper presents a novel framework of 3D human body detection, tracking and recognition from depth video sequences using spatiotemporal features and modified HMM. To detect human silhouette, raw depth data is examined to extract human silhouette by considering spatial continuity and constraints of human motion information. While, frame differentiation is used to track human movements. Features extraction mechanism consists of spatial depth shape features and temporal joints features are used to improve classification performance. Both of these features are fused together to recognize different activities using the modified hidden Markov model (M-HMM). The proposed approach is evaluated on two challenging depth video datasets. Moreover, our system has significant abilities to handle subject's body parts rotation and body parts missing which provide major contributions in human activity recognition.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.4
• /
• pp.238-245
• /
• 2016

Inverters are considered the basic building blocks of industrial electrical drive systems that are widely used for various applications; however, the failure of electronic switches mainly affects the constancy of these inverters. For safe and reliable operation of an electrical drive system, faults in power electronic switches must be detected by an efficient system that is capable of identifying the type of faults. In this paper, an open switch fault identification technique for a three-phase inverter is presented. Single, double, and triple switching faults can be diagnosed using this method. The detection mechanism is based on stator current analysis. Discrete wavelet transform (DWT) using Daubechies is performed on the Clarke transformed (-) stator current and features are extracted from the wavelets. An artificial neural network is then used for the detection and identification of faults. To prove the feasibility of this method, a Simulink model of the DWT-based feature extraction scheme using a neural network for the proposed fault detection system in a three-phase inverter with an induction motor is briefly discussed with simulation results. The simulation results show that the designed system can detect faults quite efficiently, with the ability to differentiate between single and multiple switching faults.

• Journal of Korean Society of Transportation
• /
• v.14 no.3
• /
• pp.45-59
• /
• 1996

The shortest path algorithm for route guidance is implicitly required not only to support geometrical variations of transportation network such as U-TURN or P-TURN but to efficiency search reasonable routes in searching mechanism. The purpose of this paper is to integrate such two requirements ; that is, to allow U-TURN and P-TURN possibilities and to cut down searching time in locating routes between two points (origin and destination) in networks. We also propose a new type of link searching algorithm which can solve the limitation of vine building algorithm at consecutively left-turn prohibited intersections. The test site is a block of Gangnam road network that has some left-turn prohibited and allowed U-TURN intersections. Four models have been identified to be comparatively analyzed in terms of searching efficiency. The Models are as follows : (i) Model 1 - Link Searching Dijkstra Algorithm without Searching Area Extraction (SAE) ; (ii) Model 2 - Link Searching Dijkstra Algorithm with SAE ; (iii) Model 3 - Link Searching Bidirectional Dijkstra Algorithm without SAE ; and (iv) Model 4 - Link Searching Bidirectional Dijkstra Algorithm with SAE. The results of comparative evaluation show that Model 4 can effectively find optimum path faster than any other models as expected. Some discussions and future research agenda have been presented in the light of dynamic route guidance application of the urban ATIS.

• Journal of the Korean Society of Safety
• /
• v.16 no.1
• /
• pp.88-93
• /
• 2001

This study discusses frequency analysis based on autoregressive (AR) time series model, and process characterization in orthogonal cutting of a fiber-matrix composite materials. A sparsely distributed idealized composite material, namely a glass reinforced polyester (GFRP) was used as workpiece. Analysis method employs a force sensor and the signals from the sensor are processed using AR time series model. The resulting pattern vectors of AR coefficients are then passed to the feature extraction block. Inside the feature extraction block, only those features that are most sensitive to different types of cutting mechanisms are selected. The experimental correlations between the different chip formation mechanisms and AR model coefficients are established.

• Journal of Information Processing Systems
• /
• v.5 no.2
• /
• pp.77-86
• /
• 2009

In this paper, we propose a framework for the real-time monitoring of wireless biosensors. This is a scalable platform that requires minimum human interaction during set-up and monitoring. Its main components include a biosensor, a smart gateway to automatically set up the body area network, a mechanism for delivering data to an Internet monitoring server, and automatic data collection, profiling and feature extraction from bio-potentials. Such a system could increase the quality of life and significantly lower healthcare costs for everyone in general, and for the elderly and those with disabilities in particular.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.5
• /
• pp.1856-1869
• /
• 2015

This paper addresses the issues of 3D human activity detection, tracking and recognition from RGB-D video sequences using a feature structured framework. During human tracking and activity recognition, initially, dense depth images are captured using depth camera. In order to track human silhouettes, we considered spatial/temporal continuity, constraints of human motion information and compute centroids of each activity based on chain coding mechanism and centroids point extraction. In body skin joints features, we estimate human body skin color to identify human body parts (i.e., head, hands, and feet) likely to extract joint points information. These joints points are further processed as feature extraction process including distance position features and centroid distance features. Lastly, self-organized maps are used to recognize different activities. Experimental results demonstrate that the proposed method is reliable and efficient in recognizing human poses at different realistic scenes. The proposed system should be applicable to different consumer application systems such as healthcare system, video surveillance system and indoor monitoring systems which track and recognize different activities of multiple users.