• Journal of Multimedia Information System
• /
• v.7 no.1
• /
• pp.1-10
• /
• 2020

The image analysis is an important and predominant task for classifying the different parts of the image. The analysis of complex image analysis like histopathological define a crucial factor in oncology due to its ability to help pathologists for interpretation of images and therefore various feature extraction techniques have been evolved from time to time for such analysis. Although deep reinforcement learning is a new and emerging technique but very less effort has been made to compare the deep learning and deep reinforcement learning for image analysis. The paper highlights how both techniques differ in feature extraction from complex images and discusses the potential pros and cons. The use of Convolution Neural Network (CNN) in image segmentation, detection and diagnosis of tumour, feature extraction is important but there are several challenges that need to be overcome before Deep Learning can be applied to digital pathology. The one being is the availability of sufficient training examples for medical image datasets, feature extraction from whole area of the image, ground truth localized annotations, adversarial effects of input representations and extremely large size of the digital pathological slides (in gigabytes).Even though formulating Histopathological Image Analysis (HIA) as Multi Instance Learning (MIL) problem is a remarkable step where histopathological image is divided into high resolution patches to make predictions for the patch and then combining them for overall slide predictions but it suffers from loss of contextual and spatial information. In such cases the deep reinforcement learning techniques can be used to learn feature from the limited data without losing contextual and spatial information.

• CELLMED
• /
• v.10 no.1
• /
• pp.7.1-7.6
• /
• 2020

Plants produce a wide range of active principles, making them a rich source of different types of medicines. Without any knowledge of the phytoconstituents or active principles the medicinal plants itself or in the form of polyherbal formulations, were used by all society of human being from ancient times for prevention and cure of disease, but most of the traditional formulations including the formulation of Ayurveda and Unani have not been scientifically validated in order to establish the pharmacopoeial standards to improve the efficacy. Globally, the people become conscious that uses of synthetic drugs for a long period is not safe; the trend of medical society at large is looking at alternatives from natural, safe sources to combat diseases. Due to this comprehension, it has been increased the demand for plant-derived medicine, and on the other side, it is extremely important to standardize the polyherbal formulations and validate them scientifically to improve their safety and efficacy. The polyherbal Unani formulation Safuf-e-Muallif is widely used and recommended in Unani system of medicine (USM) as a spermatogenic agent, semen thickening agent, etc. to treat sexual disorders viz. premature ejaculation, nocturnal emission, etc. The study mainly deals with phytochemical screening for the detection of nature of phytoconstituents and analytical technique like High-performance thin-layer chromatography (HPTLC) for developing fingerprint of Safuf-e-Muallif revealing specific identities of the drug. The phytochemical screening and HPTLC fingerprint profile for SM reported here may be used as a reference standard for quality control purpose in future.

• Journal of Korea Multimedia Society
• /
• v.15 no.8
• /
• pp.1017-1030
• /
• 2012

Most watermarking schemes for video contents protection have been studied to increase watermark's robustness and invisibility against such compressions and many kinds of signal processing after embedding copyright information to the original contents. This paper proposes an active watermarking that infect watermark to contents in the video decoding process using embedded infectious watermark and control signals from a video encoder side. To achieve this algorithm, we design a kernel based watermarking in video encoder side that is possible to recover the original contents and watermark in watermark detection procedure perfectly. And then, by reversible de-watermarking in video decoder side, we design the active watermark infection method using detected watermark and control signal. This means that our system can provide secure re-distributions of video contents without any quality degration and watermark bit error against transcoding or re-encoding processing. By experimental results, we confirmed that the embedded watermark was infected by video contents and codec perfectly without any declines of compression ratio and video quality.

• Journal of Advanced Navigation Technology
• /
• v.18 no.6
• /
• pp.533-540
• /
• 2014

We propose an age estimation-based smart digital signage for the next-generation airport service. The proposed system can recognize the face of the customer so that it can display the selective information. Using a webcam, the system captures the face of the customer and estimates the age of the customer by calculating the wrinkle density of the face and applying bayesian classifier. The developed age estimation method is tested with a face database for the performance evaluation. We expect the new digital signage may improve the satisfaction of customers of the airport business.

• Journal of Navigation and Port Research
• /
• v.32 no.3
• /
• pp.215-221
• /
• 2008

Dynamic characteristics of a structure, i.e., natural frequency and mode shape, have been widely using as an input data in the area of structural integrity or health monitoring which combined with the damage evaluation and structural system identification techniques. It is very difficult, however, to get those information by the conventional modal analysis method from large structures, such as the offshore structure or the long-span bridge, since the source of vibration is not available. In this paper, a method to obtain the frequencies and the mode shapes of a large span truss structure using only acceleration responses is studied. The calculation procedures to obtain acceleration responses and frequency response functions are provided utilizing a numerical model of the truss, and the process to extract natural frequencies and mode shapes from the modal analysis is cleary explained. The extracted mode shapes by proposed method are compared with those from eigenvalue analysis for the estimation of accuracy. The validity of the mode shapes is also demonstrated using an existing damage detection technique for the truss structure by simulated damage cases.

• Progress in Medical Physics
• /
• v.27 no.3
• /
• pp.162-168
• /
• 2016

Proton therapy is increasingly being actively used in the treatment of cancer. In contrast to photons, protons have the potential advantage of delivering higher doses to the cancerous tissue and lower doses to the surrounding normal tissue. However, a range shifter is needed to degrade the beam energy in order to apply the pencil beam scanning technique to tumors located close to the minimum range. The secondary neutrons are produced in the beam path including within the patient's body as a result of nuclear interactions. Therefore, unintended side effects may possibly occur. The research related to the secondary neutrons generated during proton therapy has been presented in a variety of studies worldwide, since 2007. In this study, we measured the magnitude of the secondary neutron dose depending on the location of the detector and the use of a range shifter at the beam nozzle of the proton scanning mode, which was recently installed. In addition, the production of secondary neutrons was measured and estimated as a function of the distance between the isocenter and detector. The neutron dose was measured using WENDI-II (Wide Energy Neutron Detection Instruments) and a Plastic Water phantom; a Zebra dosimeter and 4-cm-thick range shifter were also employed as a phantom. In conclusion, we need to consider the secondary neutron dose at proton scanning facilities to employ the range shifter reasonably and effectively.

• KSBB Journal
• /
• v.14 no.3
• /
• pp.384-388
• /
• 1999

We have used high pH anion-exchange chromatography to analyze low level (below $20{\mu}M$) $\alpha$-D-glucose-1-phosphate (G-1-P) that can be used as a cytostatic compound, an antibiotic, and immunosuppressive drug. Our chromatographic method afforded excellent peak resolution and seletivity for glucose-6-phosphate and various maltooligosaccharides as well as G-1-P. The pulsed amperometric detector yielded linear response on G-1-P ranging from 2 - $20{\mu}M$, giving slope of $4.8{\times}10^4$(peak area/${\mu}M$). The detection limit was $2{\mu}M$. This method was applied to the purification of thermophilic $\alpha$-glucan phosphorylase from Thermus caldophilus. The technique will be extremely useful in future studies concerning carbohydrate metabolism in living organisms.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.2A
• /
• pp.147-156
• /
• 2004

This paper presents an implementation and performance analysis of an access channel decoder which exploits a diversity gain due to the independent magnitude of received signals energy at each of antenna elements of a smart antenna BTS (Base-station Transceiver Subsystem) operating in CDMA2000 1X signal environment. Proposed access channel decoder consists of a searcher supporting 4 fingers, Walsh demodulator, and demodulator controller. They have been implemented with 5 of 1 million-gate FPGA's (Field Programmable Gate Array) Altera's APEX EP20K1000EBC652 and TMS320C6203 DSP (digital signal processing). The objective of the proposed access channel decoders is to enhance the data retrieval at co]1-site during the access period, for which the optimal weight vector of the smart antenna BTS is not available. Through experimental tests, we confirmed that the proposed access channel decoder exploitng the diversity technique outperforms the conventional one, which is based on a single antenna channel, in terms of detection probability of access probe, access channel failure probability, and $E_{b/}$ $N_{o}$ in Walsh demodulator.r.r.

• KIISE Transactions on Computing Practices
• /
• v.21 no.2
• /
• pp.109-114
• /
• 2015

This paper presents a computational model on the transfer of airborne fine particles to analyze the similarities and influences among the 25 districts in Seoul by quantifying a time series data collected from each district. The properties of each district are driven with the model of a time series of the fine particle concentrations, and the calculation of edge-based weights are carried out with the transfer entropies between all pairs of the districts. We applied a modularity-based graph clustering technique to detect the communities among the 25 districts. The result indicates the discovered clusters correspond to a high transfer-entropy group among the communities with geographical adjacency or high in-between traffic volumes. We believe that this approach can be further extended to the discovery of significant flows of other indicators causing environmental pollution.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.1
• /
• pp.35-45
• /
• 2007

The log data collected from mobile devices contains diverse meaningful and practical personal information. However, this information is usually ignored because of its limitation of memory capacity, computation power and analysis. We propose a novel method that detects landmarks of meaningful information for users by analyzing the log data in distributed modules to overcome the problems of mobile environment. The proposed method adopts Bayesian probabilistic approach to enhance the inference accuracy under the uncertain environments. The new cooperative modularization technique divides Bayesian network into modules to compute efficiently with limited resources. Experiments with artificial data and real data indicate that the result with artificial data is amount to about 84% precision rate and about 76% recall rate, and that including partial matching with real data is about 89% hitting rate.