• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.75-81
• /
• 2024

In this paper, we proposes a method for real-time processing of inter-floor noise problems by embedding TinyML, which includes a deep learning model, into ultra-low-power systems. The reason this method is feasible is because of lightweight deep learning model technology, which allows even systems with small computing resources to perform inference autonomously. The conventional method proposed to solve inter-floor noise problems was to send data collected from sensors to a server for analysis and processing. However, this centralized processing method has issues with high costs, complexity, and difficulty in real-time processing. In this paper, we address these limitations by employing On-Sensor AI using TinyML. The method presented in this paper is simple to install, cost-effective, and capable of processing problems in real-time.

• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• pp.443-451
• /
• 2023

Machine Learning has introduced many solutions in data science, but its application in IoT faces significant challenges, due to the limitations in memory size and processing capability of constrained devices. In this paper we design an automatic gamma radiation detection and identification embedded system that exploits the power of TinyML in a SiPM micro radiation sensor leveraging the Edge Impulse platform. The model is trained using real gamma source data enhanced by software augmentation algorithms. Tests show high accuracy in real time processing. This design has promising applications in general-purpose radiation detection and identification, nuclear safety, medical diagnosis and it is also amenable for deployment in small satellites.

• Electronics and Telecommunications Trends
• /
• v.37 no.5
• /
• pp.44-53
• /
• 2022

The Internet of Things (IoT) is growing exponentially, with the number of IoT devices multiplying annually. Accordingly, the paradigm is changing from cloud computing to edge computing and even tiny edge computing because of the low latency and cost reduction. Machine learning is also shifting its role from the cloud to edge or tiny edge according to the paradigm shift. However, the fragmented and resource-constrained features of IoT devices have limited the development of artificial intelligence applications. Edge MLaaS (Machine Learning as-a-Service) has been studied to easily and quickly adopt machine learning to products and overcome the device limitations. This paper briefly summarizes what Edge MLaaS is and what element of research it requires.

• International journal of advanced smart convergence
• /
• v.10 no.1
• /
• pp.56-61
• /
• 2021

Neighbor path selection is to pre-select alternate routes in case geographically correlated failures occur simultaneously on the communication network. Conventional heuristic-based algorithms no longer improve solutions because they cannot sufficiently utilize historical failure information. We present a novel solution model for neighbor path selection by using machine learning technique. Our proposed machine learning neighbor path selection (ML-NPS) model is composed of five modules- random graph generation, data set creation, machine learning modeling, neighbor path prediction, and path information acquisition. It is implemented by Python with Keras on Tensorflow and executed on the tiny computer, Raspberry PI 4B. Performance evaluations via numerical simulation show that the neighbor path communication success probability of our model is better than that of the conventional heuristic by 26% on the average.

• Journal of the Korean Chemical Society
• /
• v.35 no.4
• /
• pp.355-361
• /
• 1991

The separative preconcentration of trace mercury[Hg(II)] in a water sample was studied by a coprecipitation flotation technique. The trace Hg(II) was precipitated together with Ce(OH)$_3$ by adding 3.0 ml of 0.1M Ce$^{3+}$ solution to 1,000 ml of water sample and adjusting pH to 11.0 with 1.0M NaOH solution. The hydrophobic precipitate[Ce(OH)$_3$-Hg(OH)$_2$], which was formed by adding 2.0 ml of 0.1${\%}$ ethanolic sodium oleate solution, were floated on the surface with an aid of tiny nitrogen gas bubbles. The floated materials were quatitatively collected in a suction flask and dissolved with 5.0 ml of 2.0M HNO$_3$. The solution was marked to 25.00 ml with a deionized water. The content of Hg(II) was determined by cold vapor atomic absorption spectrophotometry. Any interferences of concomitants such as Ag$^+$, Br$^-$, I$^- $, etc. were not observed on the whole procedure. The analytical result showed that Hg(II) found in the wastewater of Seochang Campus, Korea University was 1.98 ng/ml with the relative standard deviation of 3.6${\%}$. And recoveries of Hg(II) in the wastewater into which 1.0 ng/ml and 2.0 ng/ml were added were 95${\%}$ and 91${\%}$, respectively. From such results, this procedure could be concluded to be tolerably accurate and reproducible for the determination of trace mercury in a water sample.

• Journal of the Korean Chemical Society
• /
• v.35 no.4
• /
• pp.389-396
• /
• 1991

The pre-concentration and determination of ultratrace arsenic in water samples was studied by the precipitate flotation technique. The arsenic in 1.0l of water sample, in which all suspended materials were filtered out, was coprecipitated together with La(OH)$_3$ precipitates at pH 8.5${\pm}$0.1. After the precipitate was made to be hydrophobic by adding mixed surfactant of 1 : 8 mole ratio of sodium oleate and sodium dodecyl sulfate, it was floated with the aid of tiny bubbles of nitrogen gas in a flotation cell. The floated precipitate was quantitatively collected on a micropore glass filter by the suction, dissolved with small volume of 1.0M sulfuric acid, and accurately diluted to 25.00ml with a de-ionized water. Total arsenic was spectrophotometrically determinated by forming silver diethyldithiocarbamate complex of arsine generated from arsenic in the concentrated solution. The calibration curve was linear up to 20ng/ml in the original solution. Analytical results showed that contents of arsenic in a campus wastewater and a river water were 8.2ng/ml and l.0ng/ml, respectively, and their recoveries were 93${\%}$ and 90${\%}$ in water samples which a given amount of arsenic was added into. From above result, it could be concluded that this method was applicable to the determination of arsenic in various kinds of water at low ng/ml levels.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.490-493
• /
• 2021

This paper proposes an embedded system that detects mask and face recognition based on a microprocessor instead of Nvidia Jetson Board what is popular development kit. We use a class of efficient models called Mobilenets for mobile and embedded vision applications. MobileNets are based on a streamlined architechture that uses depthwise separable convolutions to build light weight deep neural networks. The device used a Maix development board with CNN hardware acceleration function, and the training model used MobileNet_V2 based SSD(Single Shot Multibox Detector) optimized for mobile devices. To make training model, 7553 face data from Kaggle are used. As a result of test dataset, the AUC (Area Under The Curve) value is as high as 0.98.

• Proceedings of the KSLP Conference
• /
• 2003.11a
• /
• pp.181-181
• /
• 2003

Objectives : Vocal fold augmentation using injectable material is an easy and simple operation. This study is to evaluate the histology of minced and injected autologous auricular cartilage and fat graft in the augmentation of unilateral vocal fold paralysis using a canine model for two years. Study Design : A prospective study with the contralateral side of the larynx used as the control Methods : Twelve dogs were operated. At first, a piece of auricular cartilage was harvested from ear and minced into tiny chips with a scalpel and scissors. And also, a piece of fat tissue was harvested from inguinal area and minced into tiny chips with a scalpel and scissors. The minced cartilage and fat-paste (0.2ml) was injected using a pressure syringe into the paralyzed thyroarytenoid muscle under direct laryngoscopy. Two animals were sacrificed at 3 days, three at 3 weeks. two at 3 months. one at 6 months, one at 12 months, three at 24 months. Each dog underwent laryngectomy and serial coronal sections of paraffin blocks from the posterior part of the vocal fold were made. Result : There was no significant complication perioperatively and during follow-up. There was acute inflammatory findings in the graft at 3 days and 3 weeks. Only a very small proportion of the injected cartilage was absorbed due to the degenerative change and the overall volume was preserved even when the cells died out. The injected cartilage remained in the larynx until 24 months. Conclusion : The autologous cartilage implant using auricular cartilage was the ideal vocal cord augmentative material for the treatment of glottic incompetence.

• Proceedings of the KSLP Conference
• /
• 2003.11a
• /
• pp.180-180
• /
• 2003

Objectives : Vocal fold augmentation by injectable material under direct visual control is an easy and simple operation. However, when autologous fat or bovine collagen is used, resorption creates a problem. And autologous fascia is debating about absorption now days. This study is to evaluate the histology of minced and injected autologous auricular cartilage and fat graft in the augmentation of unilateral vocal fold paralysis using a canine model. Methods : Nine dogs were operated. At first, a piece of auricular cartilage was harvested from ear and minced into tiny chips with a scalpel. And also, a piece of fat tissue was harvested from inguinal area and minced into tiny chips with a scalpel. Cutting off a section of the recurrent nerve paralyzed the right vocal fold. The minced cartilage and fat-paste (0.2ml) was injected using a pressure syringe into the paralyzed thyroarytenoid muscle under direct laryngoscopy. Two animals were sacrificed at 3 days, three at 3 weeks, two at 3 months, one at 6 months, one at 12 months. Each dog underwent laryngectomy and serial coronal sections of paraffin blocks from the posterior part of the vocal fold were made. Results : There was no significant complication perioperatively and during follow-up. There was acute inflammatory findings in the graft at 3 days and 3 weeks. The injected cartilage remained in the larynx until 12 months. Conclusion : The autologous auricular cartilage graft is well tolerated and may be very effective material for volumetric augmentation on paralyzed vocal cord.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.5 no.2
• /
• pp.45-49
• /
• 1972

The following are some results obtained from a series of experiments in rotifer culture and its usage for the food of tiny fish fry: 1, Outdoor concrete ponds, each being $16m^2$, were used to culture the rotifers, Brachionus calyciflorus, and Filinia longiseta. Brachionus calyciflorus usually attained the population of about 100 individuals per ml of pond water. Dipterex was usually applied to control Daphni,a and other crustaceans that generally appear and feed on rotifers. A concentration of 0.16 to 0.2 ppm in the pond water was sufficiently effective to control these natural enimies of rotifers. Poultry dung was very effectively used to multiplicate rotifers. The fertilization ratio was about 8 kg each pond with 30cm depth of water. 2. The tiny rotifer, Filinia longiseta attained a very high population density of about 1,000 individuals per ml of pond water, but they were very sensitive to dipterex, and for this aspect future investigation may be needed. 3. In the outdoor ponds, the multiplication of rotifers significantly decreased when the water temperature falls to about $20^{\circ}C$ in autumn. 4. In the laboratory room, unicellular planktonic algae such as Scenedesmus or Chlorella, as the food of rotifers, were collected from the outdoor ponds by dipping them together with water, and were effectively used for the culture of Brachionus calyciflorus. If the planktonic algae are cultured in specially designed containers, the sun-light would be the most effective means as the source of light. 5. Brachionus calyciflorus cultured in the outdoor ponds by the dipterex controlled method was highly efficient to rear the early fry of marble gourami. The dipterex content mixed in the water to control the crustacean emmies of rotifers sieved no harm to the gourami fish fry.