• International Journal of Computer Science & Network Security
• /
• v.24 no.4
• /
• pp.67-76
• /
• 2024

Diabetic retinopathy is a threatening complication of diabetes, caused by damaged blood vessels of light sensitive areas of retina. DR leads to total or partial blindness if left untreated. DR does not give any symptoms at early stages so earlier detection of DR is a big challenge for proper treatment of diseases. With advancement of technology various computer-aided diagnostic programs using image processing and machine learning approaches are designed for early detection of DR so that proper treatment can be provided to the patients for preventing its harmful effects. Now a day machine learning techniques are widely applied for image processing. These techniques also provide amazing result in this field also. In this paper we discuss various machine learning and deep learning based techniques developed for automatic detection of Diabetic Retinopathy.

• Journal of the Korean Physical Society
• /
• v.73 no.10
• /
• pp.1529-1534
• /
• 2018

We used in-situ synchrotron X-ray scattering to investigate phase transformations of octahedral tilted monoclinic $SrRuO_3$ (MSRO) and tetragonal SRO (TSRO) thin films on $SrTiO_3$ (STO) substrates. The octahedral tilted MSRO thin films were highly crystalline and the monoclinic distortion angle was $0.45^{\circ}$. The phase transition temperature from the MSRO to TSRO phase occurred at approximately $200^{\circ}C$ as a second order transition. Conversely, no phase transformations of the TSRO thin film occurred within the range from RT to $250^{\circ}C$. The octahedral $RuO_6$ rotation was strongly affected by the phase transformation in the SRO thin films.

• Structural Engineering and Mechanics
• /
• v.73 no.3
• /
• pp.339-351
• /
• 2020

Earthquakes are natural disasters that cause serious social disruptions and economic losses. In particular, they have a significant impact on critical lifeline infrastructure such as urban water transmission networks. Therefore, it is important to predict network performance and provide an alternative that minimizes the damage by considering the factors affecting lifeline structures. This paper proposes a probabilistic reliability approach for post-hazard flow analysis of a water transmission network according to earthquake magnitude, pipeline deterioration, and interdependency between pumping plants and 154 kV substations. The model is composed of the following three phases: (1) generation of input ground motion considering spatial correlation, (2) updating the revised nodal demands, and (3) calculation of available nodal demands. Accordingly, a computer code was developed to perform the hydraulic analysis and numerical modelling of water facilities. For numerical simulation, an actual water transmission network was considered and the epicenter was determined from historical earthquake data. To evaluate the network performance, flow-based performance indicators such as system serviceability, nodal serviceability, and mean normal status rate were introduced. The results from the proposed approach quantitatively show that the water network is significantly affected by not only the magnitude of the earthquake but the interdependency and pipeline deterioration.

• Journal of Computing Science and Engineering
• /
• v.1 no.1
• /
• pp.31-55
• /
• 2007

Contemporary end-servers and network-routers rely on traffic shaping to deal with server overload and network congestion. Although such traffic shaping provides a means to mitigate the effects of server overload and network congestion, the lack of cooperation between end-servers and network-routers results in waste of network resources. To remedy this problem, we design, implement, and evaluate NetDraino, a novel mechanism that extends the existing queue-management schemes at routers to exploit the link congestion information at downstream end-servers. Specifically, NetDraino distributes the servers' traffic-shaping rules to the congested routers. The routers can then selectively discard those packets-as early as possible-that overloaded downstream servers will eventually drop, thus saving network resources for forwarding in-transit packets destined for non-overloaded servers. The functionality necessary for servers to distribute these filtering rules to routers is implemented within the Linux iptables and iproute2 architectures. Both of our simulation and experimentation results show that NetDraino significantly improves the overall network throughput with minimal overhead.

• Journal of Korean Elementary Science Education
• /
• v.37 no.1
• /
• pp.39-53
• /
• 2018

The purpose of this study was to investigate the conceptual structure of subjects related to matter having pre-service elementary school teachers by applying semantic network analysis (SNA). The analyzed concepts in the subjects of matter were 6 words such as 'atom', 'molecule', 'ion', 'electron', 'matter' and 'particle'. The results of SNA of the concepts are as follows : 1. In the semantic network of 'atom', words having a high betweenness centrality were linked with the words based on both the scientific context and the everyday context. 2. The network of 'molecule' was analyzed to be more organized than the network of the 'atom'. 3. In the network of 'ion', the group of words of the scientific context was distinguished from the group of words of the everyday context. 4. The network of 'electron' was analyzed to be more oriented on electricity and magnetism in the field of physics. 5. In the network of 'matter', the words related to compounds were linked with knowledge of history of science. 6. The network of 'particle' was not structured with words based on particulate nature of matter.

• Genomics & Informatics
• /
• v.13 no.3
• /
• pp.76-80
• /
• 2015

Type 2 diabetes mellitus is a complex metabolic disorder associated with multiple genetic, developmental and environmental factors. The recent advances in gene expression microarray technologies as well as network-based analysis methodologies provide groundbreaking opportunities to study type 2 diabetes mellitus. In the present study, we used previously published gene expression microarray datasets of human skeletal muscle samples collected from 20 insulin sensitive individuals before and after insulin treatment in order to construct insulin-mediated regulatory network. Based on a motif discovery method implemented by iRegulon, a Cytoscape app, we identified 25 candidate regulons, motifs of which were enriched among the promoters of 478 up-regulated genes and 82 down-regulated genes. We then looked for a hierarchical network of the candidate regulators, in such a way that the conditional combination of their expression changes may explain those of their target genes. Using Genomica, a software tool for regulatory network construction, we obtained a hierarchical network of eight regulons that were used to map insulin downstream signaling network. Taken together, the results illustrate the benefits of combining completely different methods such as motif-based regulatory factor discovery and expression level-based construction of regulatory network of their target genes in understanding insulin induced biological processes and signaling pathways.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.10a
• /
• pp.186-189
• /
• 1996

In most of the recent research literature, network performance is expressed in terms of network engineering measures such as delay or loss. These performance measures are important to network owners and operators, but it is believed that user preferences should be the primary consideration which drives the resource allocation scheme. A network is only as valuable as its users perceive it to be. Therefore, it is advocated that the users themselves determine relative traffic priorities. This paper describes the role of feedback in network resource allocation, which could be part of a user-oriented framework for network operation and control. Feedback mechanism can also be used to improve the two types of efficiency in the network; network efficiency and economic efficiency.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.25 no.1
• /
• pp.15-26
• /
• 2000

We consider an open tandem queueing network with population constraint and constant service times. The total number of customers that may be present in the network can not exceed a given value k. Customers arriving at the queueing network when there are more than k customers are forced to walt in an external queue. The arrival process to the queueing network is assumed to be arbitrary. It is known that the queueing network with population constrant and constant service times can be transformed into a simple network involving only two nodes. In this paper, the departure process from the queueing network is examined using this simple network. An approximation can be calculated with accuracy. Finally, validations against simulation data establish the tightness of these.

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.159-168
• /
• 2021

Detecting cyber-attacks using machine learning or deep learning is being studied and applied widely in network intrusion detection systems. We noticed that the application of deep learning algorithms yielded many good results. However, because each deep learning model has different architecture and characteristics with certain advantages and disadvantages, so those deep learning models are only suitable for specific datasets or features. In this paper, in order to optimize the process of detecting cyber-attacks, we propose the idea of building a new deep learning network model based on the association and combination of individual deep learning models. In particular, based on the architecture of 2 deep learning models: Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM), we combine them into a combined deep learning network for detecting cyber-attacks based on network traffic. The experimental results in Section IV.D have demonstrated that our proposal using the CNN-LSTM deep learning model for detecting cyber-attacks based on network traffic is completely correct because the results of this model are much better than some individual deep learning models on all measures.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1997.10a
• /
• pp.138-141
• /
• 1997

In this study, a simulation model is developed to analyze the effects of routing and scale-economy of transmission facilities on the traffic network topology and investment cost changes in a metropolitan telephone network. Computational experiments showed that the wide deployment of bifurcated routing in a dual-homing configuration reduces significantly the traffic network connectivity and the investment cost. Its enhanced version, when combined with the subscriber network cost model, can be used as a prototype cost proxy model for figuring out the access charges in a multi-operator environment.