• Journal of Biomedical Engineering Research
• /
• v.43 no.6
• /
• pp.441-447
• /
• 2022

In this paper, we propose a pill identification model using engraved text feature and image feature such as shape and color, and compare it with an identification model that does not use engraved text feature to verify the possibility of improving identification performance by improving recognition rate of the engraved text. The data consisted of 100 classes and used 10 images per class. The engraved text feature was acquired through Keras OCR based on deep learning and 1D CNN, and the image feature was acquired through 2D CNN. According to the identification results, the accuracy of the text recognition model was 90%. The accuracy of the comparative model and the proposed model was 91.9% and 97.6%. The accuracy, precision, recall, and F1-score of the proposed model were better than those of the comparative model in terms of statistical significance. As a result, we confirmed that the expansion of the range of feature improved the performance of the identification model.

• Clinical Endoscopy
• /
• v.57 no.1
• /
• pp.73-81
• /
• 2024

Background/Aims: Upper gastrointestinal bleeding (UGIB) is a life-threatening condition that necessitates early identification and intervention and is associated with substantial morbidity, mortality, and socioeconomic burden. However, several diagnostic challenges remain regarding risk stratification and the optimal timing of endoscopy. The PillSense System is a noninvasive device developed to detect blood in patients with UGIB in real time. This study aimed to assess the safety and performance characteristics of PillSense using a simulated bleeding model. Methods: A preclinical study was performed using an in vivo porcine model (14 animals). Fourteen PillSense capsules were endoscopically placed in the stomach and blood was injected into the stomach to simulate bleeding. The safety and sensitivity of blood detection and pill excretion were also investigated. Results: All the sensors successfully detected the presence or absence of blood. The minimum threshold was 9% blood concentration, with additional detection of increasing concentrations of up to 22.5% blood. All the sensors passed naturally through the gastrointestinal tract. Conclusions: This study demonstrated the ability of the PillSense System sensor to detect UGIB across a wide range of blood concentrations. This ingestible device detects UGIB in real time and has the potential to be an effective tool to supplement the current standard of care. These favorable results will be further investigated in future clinical studies.

• BMB Reports
• /
• v.29 no.1
• /
• pp.11-16
• /
• 1996

The present study showed that receptor-mediated activation of rabbit kidney proximal tubule cells by angiotensin II, the $Ca^{2+}$ ionophore A23187, or the protein kinase C activator phorbol myristate acetate (PMA) all stimulated phospholipase D (PLD). This was demonstrated by the increased formation of phosphatidic acid, and in the presence of 0.5% ethanol, phosphatidylethanol (PEt) accumulation. Angiotensin II leads to a rapid increase in phosphatidic acid and diacylglycerol, and phosphatidic acid formation preceeded the formation of diacylglycerol. This result suggests that some phosphatidic acid seems to be formed directly from phosphatidylcholine hydrolyzed by Pill. On the other hand, EGTA substantially attenuated angiotensin II and A23187-induced PEt formation, and when the cells were pretreated with verapamil angiotensin II-induced Pill activation was completely abolished. These results provide the evidence that calcium ion influx is essential for the agonist-induced Pill activation. In addition, staurosporine, an inhibitor of protein kinase C, strongly inhibited PMA-induced PEt formation, but was ineffective on angiotensin II-induced PEt accumulation. $GTP{\gamma}S$ also stimulates PEt formation in digitonin-permeabilized cells, but pretreatment of the cells with pertussis toxin failed to suppress angiotensin II-induced PEt formation. From these results, we conclude that in the rabbit kidney proximal tubule cells the mechanisms of angiotensin II- and PMA-induced Pill activation are different from each other and mediated via a pertussis toxin-insensitive trimeric G protein.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2007.11a
• /
• pp.226.2-226.2
• /
• 2007

• Korean Journal of Pharmacognosy
• /
• v.40 no.2
• /
• pp.155-160
• /
• 2009

The reference herbal extracts and their identification methods by Korean Pharmacopoeia IX were established based on the organic solvent extracts to detect their marker compounds. However, most of herbal medicine decoctions in the market are prepared with water as extracting solvent. As the reference herbal extracts and their identification methods are not appropriate for the practical test, new preparation of alternative reference herbal extracts and their identification test methods are essential for the correction of test methods and identification of herbal drugs. Three novel identification test methods were developed for Evodiae Fructus, Cimicifugae Rhizoma and Aurantii Fructus Immaturus. Total 10 reference herbal extracts and their identification methods were optimized for Ephedrae Herba, Schisandrae Fructus, Curcuma longae Rhizoma, Citri Unshius Pericarpium, Puerariae Radix, Corni Fructus, and Cinnamomi Cortex.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.2
• /
• pp.215-221
• /
• 2006

This paper is concerned with the control of multiple nonlinearities included in a humanoid robot system. A humanoid robot has some problems such as the structural instability, which leads to consider the control of multiple nonlinearities caused by driver parts as well as gear reducer. Saturation and backlash are typical examples of nonlinearities in the system. The conventional algorithms of backlash control were fuzzy algorithm, disturbance observer and neural network, etc. However, it is not easy to control the system by employing only single algorithm since the system usually includes multiple nonlinearities. In this paper, a switching Pill is considered for a control of saturation and a dual feedback algorithm is proposed for a backlash control. To implement the above algorithms, the system identification is firstly performed for the minimization of the difference between the results of simulation and experiment, and then the switching Pill gains are determined using genetic algorithm with some heuristic approach. The performance of the switching Pill controller for saturation and the dual feedback for backlash control is investigated through the simulation. Finally, it is shown that the implemented control system has good results and can be applied to the real humanoid robot system ISHURO.

• Korean Journal of Environmental Biology
• /
• v.24 no.2 s.62
• /
• pp.160-165
• /
• 2006

The purpose of this study was to ascertain the prey composition and utilization of the Eurasian otter, Lutra lutra, in the ecosystem conservation region of the Seomjin River. The study was conducted for a 12-month period from March 2003 to February 2004 by spraints analysis and an investigation using artificial holts. We found seasonal variation in the number of spraints and composition of prey items. Fish were the main prey items throughout the period (82%), and other prey items included birds (14%), amphibians (2%) and arthropods (1%). In addition to prey identification, we investigated habitat utilization by otters through spraints distribution. The traces of otters were discovered in five of the six total artificial holts. However, the utilization of the artificial holts in the study area seemed to be limited as evidenced by the low frequency of traces in the holts.

• Journal of Plant Biotechnology
• /
• v.35 no.2
• /
• pp.163-167
• /
• 2008

Adventitious buds appeared within 2 weeks on the base of the petiole explants and increased for two months. A maximum of regeneration (15.6%) was obtained on the medium containing $1.5\;{\mu}M$ TDZ in combination with $1\;{\mu}M$ IBA. To know which explants are the best for the induction of regeneration, three explants such as leaf, petiole and leaf-petiole were used. Among the explant types, the leaf-petiole explant was significantly more effective than leaf and petiole for promoting adventitious shoots, with leaf-petiole inducing at the highest regeneration frequency (33.7%). The regeneration frequency of adventitious shoots in the leaf-petiole explants was significantly affected by leaf size and the position of explants. The leaf-petiole smaller than 5 mm leaf in width was induced at the highest regeneration frequency (68.9%). The smaller leaf sizes, the greater regeneration frequency. Also when the leaves are nearer to the shoot tip, the regeneration frequency is higher. When the rooted micro-shoots were transferred to the soil after growing for 6 weeks in the media, the survival rate was 90%.

• The Korean Journal of Pesticide Science
• /
• v.13 no.4
• /
• pp.332-335
• /
• 2009

Rhizo-bacteria were isolated from organic-farming soils to select antagonistic agent for controlling citrus melanose disease. Among several antagonistic bacteria, KB-401 effectively inhibited mycelial growth of several plant fungal pathogens, including the pathogen of citrus melanose, Diaporthe citri. KB-401 also inhibited spore germination of the fungal pathogen. The tip of germ tube was swollen when conidia of D. citri were co-culture with KB-401 in PD broth amended 1% glucose. KB-401 was identified as Bacillus subtilis through the investigation for physiological characters and the analysis of nucleotide sequences of 16S rDNA.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.1010-1011
• /
• 2013

In this paper, we have developed a system for identifying pills and providing their information by image processing to assist the health care of the elderly. A wide variety of pills can lead to the difficulty of distinguishing for the elderly at home and results in unusage and abandonment of the pills. To resolve this problem, we obtain images from a camera of a smart phone, extract features such as shape, line and color by image processing, classify pills, and provide information including the name, effect and directions for the usage of the pills.