• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.349-358
• /
• 2021

Recently, a method of finding the attention area or localization area for an object of an image using CAM (Class Activation Map)[1] has been variously carried out as a study of WSOL (Weakly Supervised Object Localization). The attention area extraction from the object heat map using CAM has a disadvantage in that it cannot find the entire area of the object by focusing mainly on the part where the features are most concentrated in the object. To improve this, using CAM and Selective Search[6] together, we first expand the attention area in the heat map, and a Gaussian smoothing is applied to the extended area to generate retraining data. Finally we train the data to expand the attention area of the objects. The proposed method requires retraining only once, and the search time to find an localization area is greatly reduced since the selective search is not needed in this stage. Through the experiment, the attention area was expanded from the existing CAM heat maps, and in the calculation of IOU (Intersection of Union) with the ground truth for the bounding box of the expanded attention area, about 58% was improved compared to the existing CAM.

• The KIPS Transactions:PartC
• /
• v.16C no.5
• /
• pp.645-652
• /
• 2009

Location-based service providing the customized information or service according to the user's location has attracted a lot of attention from the mobile communication industry. The service is realized by means of several building blocks, a localization scheme, service platform, application and service. The localization scheme figures out a moving target's position through measuring and processing a wireless signal. In this paper, we propose an adaptive localization scheme in an indoor localization system based on IEEE 802.15.4 standard. In order to enhance the localization accuracy, the proposed scheme selects the best reference points and adaptively reflects the changes of propagation environments of a moving target to approximate distances between the target and the reference points in RSS(Received Signal Strength) based localization system using triangulation. Through the implementation of the localization system, we verify the performance of the proposed scheme in terms of the localization accuracy.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.49 no.4
• /
• pp.90-101
• /
• 2012

The landmark selection is crucial to successful perform in SLAM(Simultaneous Localization and Mapping) with a mono camera. Especially, in unknown environment, automatic landmark selection is needed since there is no advance information about landmark. In this paper, proposed visual attention system which modeled human's vision system will be used in order to select landmark automatically. The edge feature is one of the most important element for attention in previous visual attention system. However, when the edge feature is used in complicated indoor area, the response of complicated area disappears, and between flat surfaces are getting higher. Also, computation cost increases occurs due to the growth of the dimensionality since it uses the responses for 4 directions. This paper suggests to use a corner feature in order to solve or prevent the problems mentioned above. Using a corner feature can also increase the accuracy of data association by concentrating on area which is more complicated and informative in indoor environments. Finally, this paper will prove that visual attention system based on corner feature can be more effective in SLAM compared to previous method by experiment.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.439-448
• /
• 2021

Driver negligence accounts for the largest proportion of the causes of traffic accidents, and research to detect them is continuously being conducted. This paper proposes a method to accurately detect a distracted driver and localize the most characteristic parts of the driver. The proposed method hierarchically constructs a CNN basic model that classifies 10 classes based on CAM in order to detect driver distration and 4 subclass models for detailed classification of classes having a confusing or common feature area in this model. The classification result output from each model can be considered as a new feature indicating the degree of matching with the CNN feature maps, and the accuracy of classification is improved by horizontally combining and learning them. In addition, by combining the heat map results reflecting the classification results of the basic and detailed classification models, the characteristic areas of attention in the image are found. The proposed method obtained an accuracy of 95.14% in an experiment using the State Farm data set, which is 2.94% higher than the 92.2%, which is the highest accuracy among the results using this data set. Also, it was confirmed by the experiment that more meaningful and accurate attention areas were found than the results of the attention area found when only the basic model was used.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.4
• /
• pp.269-277
• /
• 2007

Wireless sensor network system is expected to get high attention in research for now and future owing to the advanced hardware development technology and its various applicabilities. Among variety of sensor network systems, the seashore and marine sensor network, which are extended to get sampling of marine resources, environmental monitoring to prevent disaster and to be applied to the area of sea route guidance. For these marine applications to be available, however, the provision of precise location information of every sensor nodes is essential. In this paper, the sequential localization algorithm for obtaining the location information of marine sensor nodes. The sequential localization is done with the utilization of a small number of beacon nodes along the seashore and gets the location of nodes by controling the sequences of localization and also minimizes the error accumulation. The key idea of this algorithm for localization is that the localization priority of each sensor nodes is determined by the number of reference nodes' information. This sequential algorithm shows the improved error performance and also provide the increased coverage of marine sensor network by enabling the maximum localization of sensor nodes as possible.

• Korean Journal of Biological Psychiatry
• /
• v.23 no.3
• /
• pp.89-101
• /
• 2016

Transcranial magnetic stimulation (TMS) is a safe, noninvasive and useful technique for exploring brain function. Especially, for the study of cognition, the technique can modulate a cognitive performance if the targeted area is engaged, because TMS has an effect on cortical network. The effect of TMS can vary depending on the frequency, intensity, and timing of stimulation. In this paper, we review the studies with TMS targeting various regions for evaluation of cognitive function. Cognitive functions, such as attention, working memory, semantic decision, discrimination and social cognition can be improved or deteriorated according to TMS stimulation protocols. Furthermore, potential therapeutic applications of TMS, including therapy in a variety of illness and research into cortical localization, are discussed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.47-49
• /
• 2022

Robot navigation has seen a major improvement since the the rediscovery of the potential of Artificial Intelligence (AI) and the attention it has garnered in research circles. A notable achievement in the area was Deep Learning (DL) application in computer vision with outstanding daily life applications such as face-recognition, object detection, and more. However, robotics in general still depend on human inputs in certain areas such as localization, navigation, etc. In this paper, we propose a study case of robot navigation based on deep reinforcement technology. We look into the benefits of switching from traditional ROS-based navigation algorithms towards machine learning approaches and methods. We describe the state-of-the-art technology by introducing the concepts of Reinforcement Learning (RL), Deep Learning (DL) and DRL before before focusing on visual navigation based on DRL. The case study preludes further real life deployment in which mobile navigational agent learns to navigate unbeknownst areas.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1907-1928
• /
• 2024

In recent years, multi-focus image fusion has emerged as a prominent area of research, with transformers gaining recognition in the field of image processing. Current approaches encounter challenges such as boundary artifacts, loss of detailed information, and inaccurate localization of focused regions, leading to suboptimal fusion outcomes necessitating subsequent post-processing interventions. To address these issues, this paper introduces a novel multi-focus image fusion technique leveraging the Swin Transformer architecture. This method integrates a frequency layer utilizing Wavelet Transform, enhancing performance in comparison to conventional Swin Transformer configurations. Additionally, to mitigate the deficiency of local detail information within the attention mechanism, Convolutional Neural Networks (CNN) are incorporated to enhance region recognition accuracy. Comparative evaluations of various fusion methods across three datasets were conducted in the paper. The experimental findings demonstrate that the proposed model outperformed existing techniques, yielding superior quality in the resultant fused images.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.5
• /
• pp.2201-2204
• /
• 2014

Russian rates for melanoma incidence and mortality are relatively low as compared to some other white populations but the tumor is of increasing importance. In this paper, data are based on a retrospective descriptive analysis of melanoma epidemiology and clinicopathological characteristics in Krasnoyarsk Territory belonging to the Siberian Federal District of the Russian Federation. The age-adjusted incidence and mortality rates for the period 1996-2009 were determined with subsequent retrospective analysis of clinicopathological data of 103 primary melanoma cases. Our results showed that incidence and mortality rates in the region under consideration match the Russian national trends and correspond to epidemiological data of the countries of Eastern Europe. Stratification of melanoma cases by age, sex, clinicopathological state and localization revealed a prevalence of lesions on the trunk and lower extremities. Most melanomas diagnosed were of superficial spreading type and the third Clark's level of tumor invasion and stage II according to AJCC. In spite of comparatively low rates of incidence and mortality the trend to increase of melanoma cases in the region under consideration obviously calls for more attention and further investigation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.5
• /
• pp.1881-1903
• /
• 2015

With the fast-developing of mobile terminals, positioning techniques based on fingerprinting method draws attention from many researchers even world famous companies. To conquer some shortcomings of the existing fingerprinting systems and further improve its performance, we propose a radio map building and updating technique, which is able to customize the spatial and temporal dependency of radio maps. The method includes indoor propagation and penetration modeling and the analysis of human traffic. Based on the combination of Ray-Tracing Algorithm, Finite-Different Time-Domain and Rough Set Theory, the approach of indoor propagation modeling accurately represents the spatial dependency of the radio map. In terms of temporal dependency, we specifically study the factor of moving people in the interest area. With measurement and statistics, the factor of human traffic is introduced as the temporal updating component. We improve our existing indoor positioning system with the proposed building and updating method, and compare the localization accuracy. The results show that the enhanced system can conquer the influence caused by moving people, and maintain the confidence probability stable during week, which enhance the actual availability and robustness of fingerprinting-based indoor positioning system.