• Journal of Korea Multimedia Society
• /
• v.3 no.1
• /
• pp.77-90
• /
• 2000

Real-Time verification is a procedure that verifies the correctness of specification related to requirement in time as well as in logic. One serious problem encountered in the verification task is that the state space grows exponentially owing to the unboundedness of time, which is termed the state space explosion problem. In this paper, we propose a real-time verification technique checking the correctness of specification by showing that a system model described in timed automata is equivalent to the characteristic of system property specified in timed modal-mu calculus. For this, we propose a local model checking method based on the value of the formula in initial state with constructing product graph concerned to only the nodes needed for verification process. Since this method does not search for every state of system model, the state space is reduced drastically so that the proposed method can be applied effectively to real-time system verification.

• Archives of design research
• /
• v.17 no.3
• /
• pp.373-382
• /
• 2004

Video protocol analysis is a popular and effective technique in many research disciplines including industrial design and HCI for understanding the interactions between people, and between people and machines. Analysing and transcribing video recordings is, however, notoriously time consuming, and a variety of single-user computer based tools have been developed to ease the task. This paper examines collaborative video analysis. The motivation for groupware tools for video analysis is described, and the desirable features of such tools are identified. The following section reviews related work on video analysis and on single-user video analysis tools. The review is used to derive a set of design goals for collaborative video analysis tools. We then detail prototype's user interface, its collaborative facilities, and its implementation. The preliminary evaluation is described prior the conclusions which identify directions for further work.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.31 no.3
• /
• pp.287-295
• /
• 1995

fishing boat is a specialized vessel which is intended to perform certain well defined tasks. Its size, deck-layout, carrying capacity and equipment are all related to its function in carrying out its planned operations. Therefore the process of fishing boat design is inherently combined with optimization of the design variables called the economic optimization criteria. Optimization then is a process in which minimum value of weight or cost is established through evaluation of consecutive designs in which one or more design parameters are varied. This paper is to study the basic-design of Stow-net fishing vessel in the Mok-Po region. The main task is developed the preliminary design model of engineering economic system in order to use optimization techniques from operation research the design problem needs to be expressed in terms of objective function and numerous constrains like : speed, fish hold capacity, fishing range, displacement and weight, ratio of main dimensions, etc. The objective function represents the criterion which is NPV such as the ratio of revene/cost. When using computers of limited capacity like P/C, the developed basic-design model of the economic optimization procedure must be simplified to V, Cb, L/B, Dv, Db and less than 15 constraint equations. The main conclusions of this study have attempted to show that economic considerations are essential in Stow-net fishing vessel basic design and operations, and that techno-economic evaluation is an important tool for the design of Stow-net fishing vessel in 69ton and 79ton.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.793-798
• /
• 2012

In this paper, we explored the new method for extracting feature from the electroencephalography (EEG) signal based on linear regression technique with the orthonormal polynomial bases. At first, EEG signals from electrodes around motor cortex were selected and were filtered in both spatial and temporal filter using band pass filter for alpha and beta rhymic band which considered related to the synchronization and desynchonization of firing neurons population during motor imagery task. Signal from epoch length 1s were fitted into linear regression with Legendre polynomials bases and extract the linear regression weight as final features. We compared our feature to the state of art feature, power band feature in binary classification using support vector machine (SVM) with 5-fold cross validations for comparing the classification accuracy. The result showed that our proposed method improved the classification accuracy 5.44% in average of all subject over power band features in individual subject study and 84.5% of classification accuracy with forward feature selection improvement.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1011-1016
• /
• 2020

Rapid change in network topology in high-speed VANET(: Vehicular Ad Hoc Network) is an important task for routing protocol design. Selecting the next hop relay node that affects the performance of the routing protocol is a difficult process. The disadvantages of AODV(: Ad Hoc On-Demand Distance Vector) related to VANET are end-to-end delay and packet loss. This paper proposes the AAODV (Advanced AODV) technique to reduce the number of RREQ (: Route Request) and RREP (: Route Reply) messages by modifying the AODV routing protocol and adding direction parameters and 2-step filtering. It can be seen that the proposed AAODV reduces packet loss and minimizes the effect of direction parameters, thereby increasing packet delivery rate and reducing end-to-end delay.

• The Korean Journal of Applied Statistics
• /
• v.35 no.1
• /
• pp.161-175
• /
• 2022

Oscillatory magnetic fields produced in the brain due to neuronal activity can be measured by the sensor. Magnetoencephalography (MEG) is a non-invasive technique to record such neuronal activity due to excellent temporal and fair amount of spatial resolution, which gives information about the brain's functional activity. Potential utilization of high spatial resolution in MEG is likely to provide information related to in-depth brain functioning and underlying factors responsible for changes in neuronal waves in some diseases under resting state or task state. This review is a comprehensive report to introduce statistical models from MEG data including graphical network modelling. It is also meaningful to note that statisticians should play an important role in the brain science field.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.17-26
• /
• 2022

Sensor Nodes play a major role to monitor and sense the variations in physical space in various real-time application scenarios. These nodes are powered by limited battery resources and replacing those resource is highly tedious task along with this it increases implementation cost. Thus, maintaining a good network lifespan is amongst the utmost important challenge in this field of WSN. Currently, energy efficient routing techniques are considered as promising solution to prolong the network lifespan where multi-hop communications are performed by identifying the most energy efficient path. However, the existing scheme suffer from performance related issues. To solve the issues of existing techniques, a novel hybrid technique by merging particle swarm optimization and game theory model is presented. The PSO helps to obtain the efficient number of cluster and Cluster Head selection whereas game theory aids in finding the best optimized path from source to destination by utilizing a path selection probability approach. This probability is obtained by using conditional probability to compute payoff for agents. When compared to current strategies, the experimental study demonstrates that the proposed GTPSO strategy outperforms them.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.271-281
• /
• 2022

Manual seed classification challenges can be overcome using a reliable and autonomous seed purity identification and classification technique. It is a highly practical and commercially important requirement of the agricultural industry. Researchers can create a new data mining method with improved accuracy using current machine learning and artificial intelligence approaches. Seed classification can help with quality making, seed quality controller, and impurity identification. Seeds have traditionally been classified based on characteristics such as colour, shape, and texture. Generally, this is done by experts by visually examining each model, which is a very time-consuming and tedious task. This approach is simple to automate, making seed sorting far more efficient than manually inspecting them. Computer vision technologies based on machine learning (ML), symmetry, and, more specifically, convolutional neural networks (CNNs) have been widely used in related fields, resulting in greater labour efficiency in many cases. To sort a sample of 3000 seeds, KNN, SVM, CNN and CNN-SVM hybrid classification algorithms were used. A model that uses advanced deep learning techniques to categorise some well-known seeds is included in the proposed hybrid system. In most cases, the CNN-SVM model outperformed the comparable SVM and CNN models, demonstrating the effectiveness of utilising CNN-SVM to evaluate data. The findings of this research revealed that CNN-SVM could be used to analyse data with promising results. Future study should look into more seed kinds to expand the use of CNN-SVMs in data processing.

• Journal of Soil and Groundwater Environment
• /
• v.28 no.spc
• /
• pp.18-39
• /
• 2023

Rapid development of geophysical exploration and hydrogeologic monitoring techniques has yielded remarkable increase of datasets related to groundwater systems. Increased number of datasets contribute to understanding of general aquifer characteristics such as groundwater yield and flow, but understanding of complex heterogenous aquifers system is still a challenging task. Recently, applications of data science technique have become popular in the fields of geophysical explorations and monitoring, and such attempts are also extended in the groundwater field. This work reviewed current status and advancement in utilization of data science in groundwater field. The application of data science techniques facilitates effective and realistic analyses of aquifer system, and allows accurate prediction of aquifer system change in response to extreme climate events. Due to such benefits, data science techniques have become an effective tool to establish more sustainable groundwater management systems. It is expected that the techniques will further strengthen the theoretical framework in groundwater management to cope with upcoming challenges and limitations.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.541-543
• /
• 2022

In recent years, retinal disorders have become a serious health concern. Retinal disorders develop slowly and without obvious signs. To avoid vision deterioration, early detection and treatment are critical. Optical coherence tomography (OCT) is a non-invasive and non-contact medical imaging technique used to acquire informative and high-resolution image of retinal area and underlying layers. Disease signs are difficult to detect because OCT images have many areas which are not related to any disease. In this paper, we present a deep learning-based method to perform multi-label classification on a long-tailed OCT dataset. Our method first extracts the region of interest and then performs the classification task. We achieve 98% accuracy, 92% sensitivity, and 99% specificity on our private OCT dataset. Using the heatmap generated from trained convolutional neural network, our method is more robust and explainable than previous approaches because it focuses on areas that contain disease signs.