• Journal of Korean Society of Forest Science
• /
• v.98 no.2
• /
• pp.197-202
• /
• 2009

We studied bird communities among in rice field (46 plots), short grallland (47plot), and tall grass mixed shrub (21 plots) during dry season, January 2007 in Boeung Prek Lapouv (BPL) Important Bird Area, Mekong Delta, Cambodia using the point-count method. Water depth, vegetation height and shrub density were significantly different among the three study areas. We recorded, 60 bird species, of which 13 differed significantly among habitats. Landbirds such as Grey-breasted Prinia (Prinia hodgsonii) and Oliver-black Sunbird (Nectarinia jugularis) were much more abundant (P<0.0001) in the tall grass mixed shrub, whereas the Sarus Crane (Grus antigone), herons and egrets were more abundant in the short grass (P<0.05). Bird species richness and species abundances were not significantly different among habitats. Bird species diversity (H') was higher in grasslands than in rice fields. Mosaic habitat matrix, such as rice field, short grass, and tall grass mixed shrub, should be maintained for the extend and quality of wetlands, and the prevailing human-land use patterns, appear adequate and conductive for waterbirds in the Mekong Delta, Cambodia.

• Journal of Wetlands Research
• /
• v.7 no.4
• /
• pp.89-95
• /
• 2005

Understanding of routes of migratory birds are important subject for conservation of avifauna. Korea Demilitarized zone (DMZ) is considered as one of the most important stopover for migratory birds that pass in the Korean peninsula. This region has been known internationally as an excellent nature preservation areas since 1953. Rare and endangered animal species such as leopards (Pathera pardus) and Siberian tigers (Panthera tigris) have increased in population. Furthermore this areas provide home for endangered migratory birds including white-naped (Grus vipio) and red-crowned cranes (G. japonensis). Recent satellite-tracked crane species has shown the importance and linkages between a small number of habitat sites in DMZ. White-naped cranes were satellite tracked 9 individuals spent 27-78% of their time in Panmunjum and 10-75% in Cheolwon. This signifies the rich feeding sites with relatively little disturbance thus making the DMZ extremely valuable as a stopover.

• Journal of Technology Innovation
• /
• v.14 no.3
• /
• pp.117-154
• /
• 2006

This research examines performance evaluatees' opinions regarding the current institutional performance evaluation systems of Government S&T Research Institutes (GRIs). Under the current evaluation systems, twenty GRIs are grouped into three Research Groups and each Group has its own evaluation systems. One problem of the current institutional evaluation systems is that the systems cannot reflect individual GRIs' characteristics. The following methods are used. First, based on four perspectives of Kaplan & Norton(1992)'s Balanced Scorecard(BSC) model, six perspectives appropriate to GRUs' characteristics are derived. Second, experts classify current performance evaluation measures into the six perspectives. This enables different evaluation systems of three GRI Research Groups to be compared under the same evaluation measures. Third, GRIs' evaluatees are asked to allocate appropriate weights on the performance measures. Evaluatees' weights of a GRI are compared with average weights of the related Group. Finally in every BSC's perspective, GRIs that have extraordinarily over-scored or under-scored weights are analyzed in terms of GRIs' missions, customers, capability of human resources, etc. In the Basic Research Group, the Korea Basic Science Institute is deviated in the financial perspective and the strategic direction perspectives. In the Public Research Group, Korea Institute of Construction Technology is significantly different from other GRIs in three perspectives. Five out of eight GRIs in the Industrial Research Group, GRIs are significantly different each other in several perspectives. It could be concluded that the current institutional evaluation systems are least appropriate in measuring performance of the GRIs of the Industrial Research Group.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.19 no.12
• /
• pp.21-27
• /
• 2020

Lithium-ion batteries are the heart of energy-storing devices and electric vehicles. Owing to their superior qualities, such as high capacity and energy efficiency, they have become quite popular, resulting in an increased demand for failure/damage prevention and useable life maximization. To prevent failure in Lithium-ion batteries, improve their reliability, and ensure productivity, prognosticative measures such as condition monitoring through sensors, condition assessment for failure detection, and remaining useful life prediction through data-driven prognostics and health management approaches have become important topics for research. In this study, the residual useful life of Lithium-ion batteries was predicted using two efficient artificial recurrent neural networks-ong short-term memory (LSTM) and gated recurrent unit (GRU). The proposed approaches were compared for prognostics accuracy and cost-efficiency. It was determined that LSTM showed slightly higher accuracy, whereas GRUs have a computational advantage.

• Journal of Korea Multimedia Society
• /
• v.25 no.9
• /
• pp.1257-1265
• /
• 2022

Recognition of sign language is challenging due to the occlusion of hands, accuracy of hand gestures, and high computational costs. In recent years, deep learning techniques have made significant advances in this field. Although these methods are larger and more complex, they cannot manage long-term sequential data and lack the ability to capture useful information through efficient information processing with faster convergence. In order to overcome these challenges, we propose a word-level sign language recognition (SLR) system that combines a real-time human pose detection library with the minimized version of the gated recurrent unit (GRU) model. Each gate unit is optimized by discarding the depth-weighted reset gate in GRU cells and considering only current input. Furthermore, we use sigmoid rather than hyperbolic tangent activation in standard GRUs due to performance loss associated with the former in deeper networks. Experimental results demonstrate that our pose-based optimized GRU (Pose-OGRU) outperforms the standard GRU model in terms of prediction accuracy, convergency, and information processing capability.

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.47-54
• /
• 2023

For Bengali music emotion classification, deep learning models, particularly CNN and RNN are frequently used. But previous researches had the flaws of low accuracy and overfitting problem. In this research, attention-based Conv1D and BiGRU model is designed for music emotion classification and comparative experimentation shows that the proposed model is classifying emotions more accurate. We have proposed a Conv1D and Bi-GRU with the attention-based model for emotion classification of our Bengali music dataset. The model integrates attention-based. Wav preprocessing makes use of MFCCs. To reduce the dimensionality of the feature space, contextual features were extracted from two Conv1D layers. In order to solve the overfitting problems, dropouts are utilized. Two bidirectional GRUs networks are used to update previous and future emotion representation of the output from the Conv1D layers. Two BiGRU layers are conntected to an attention mechanism to give various MFCC feature vectors more attention. Moreover, the attention mechanism has increased the accuracy of the proposed classification model. The vector is finally classified into four emotion classes: Angry, Happy, Relax, Sad; using a dense, fully connected layer with softmax activation. The proposed Conv1D+BiGRU+Attention model is efficient at classifying emotions in the Bengali music dataset than baseline methods. For our Bengali music dataset, the performance of our proposed model is 95%.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• v.4 no.2
• /
• pp.79-85
• /
• 2023

The Tibetan Plateau is home to the only alpine crane species, the black-necked crane (Grus nigricollis). Conservation efforts are severely hampered by a lack of knowledge on the spatial distribution and breeding habitats of this species. The ecological niche modeling framework used to predict the spatial distribution of this species, based on the maximum entropy and occurrence record data, allowed us to generate a species-specific spatial distribution map in Ladakh, Trans-Himalaya, India. The model was created by assimilating species occurrence data from 486 geographical sites with 24 topographic and bioclimatic variables. Fourteen variables helped forecast the distribution of black-necked cranes by 96.2%. The area under the curve score for the model training data was high (0.98), indicating the accuracy and predictive performance of the model. Of the total study area, the areas with high and moderate habitat suitability for black-necked cranes were anticipated to be 8,156 km² and 6,759 km², respectively. The area with high habitat suitability within the protected areas was 5,335 km². The spatial distribution predicted using our model showed that the majority of speculated conservation areas bordered the existing protected areas of the Changthang Wildlife Sanctuary. Hence, we believe, that by increasing the current study area, we can account for these gaps in conservation areas, more effectively.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.12
• /
• pp.2520-2527
• /
• 2015

Position information is important to carry out military operations. In general, GPS is used to estimate position. However, GPS is vulnerable to jamming due to the low received signal strength, therefore GPS can be easily jammed. The relative navigation is an auxiliary navigation system defined in JTIDS. When GPS is jammed, the relative navigation requires ground reference units on the ground to operate accurately. If the ground reference unit does not exist, nodes operated by the relative navigation depend on the inertial navigation system to identify their position. However, this positioning scheme based on only INS causes accumulative position error, therefore the nodes cannot identify their position accurately for a long time. In this paper, we propose an alternative to reduce position error generated by depending inertial navigation system. In order to verify that the performance of proposed scheme is better than that of the existing scheme, various simulations are conducted.

• Ocean and Polar Research
• /
• v.24 no.1
• /
• pp.115-121
• /
• 2002

Yubu Island is located within the estuary of the Geum River, South Chungcheong Province $(35^{\circ}59'N,\;126^{\circ}36'E)$, Korea. The island is surrounded by a broad and sandy mudflat, which is typical in the west coast of Korea, and is located 4km off from Gunsan City. Less than 100 humans live on the island, occupying 30 houses. After we discovered that this island was a very important waterbird habitat especially for the East Asian subspecies of the Eurasian oystercatcher, Haematopus ostralegus osculans. Waterbirds were monitored once every month from August 1999 to July 2000. The highest number of oystercatchers counted was 3,200 in December 1999, and the birds seemed to remain in the area continuously from September to next February. About 200 breeding and non-breeding birds remained during the breeding season. In August, early migrants returned to the island, with the number reaching 1,060 individuals. This island is also very important for other waterbirds. Endangered or significant species occurring at this site, and their maximum counts were: chinese egret Egretta eulophotes (5), black-faced spoonbill Platalea minor (17), brant Branta bernicla (1), common shelduck Tadorna tadorna (8,000), hooded crane Grus monacha (2), spoon-billed sandpiper Ewynorhynchus pygmeus (7), dunlin Calidris alpina (6,500), great knot Calidris tenuirostris (24,000), far eastern curlew Numenius madagascariensis (2,500), spotted greenshank Tringa guttifer (4) and Saunders's gull Larus saundersi (1,200). During the 12 month survey period, we observed 52 waterbird species and the total of the maximum counts for the separate species was 73,308, implying that perhaps 150,000 birds could be using the immediate area, if a turnover rate of 2 was assumed.

• Korean Journal of Environment and Ecology
• /
• v.16 no.4
• /
• pp.487-497
• /
• 2003

Some literatures for the avifauna of Baekdudaegan from Jirisan to Deokusan were reviewed. A total of 136 species belong to 45 families, 15 orders was listed. Of which, 132 species were recorded in Jirisan National Park, 63 species were in Hamyang area,46 species were Jangsu area, and 63 species were in Deokyusan National Park. Status of migrants of these birds were classified as follows: 42 species of residents,40 species of summer visitors,31 species of winter visitors, and 23 species of passage migrants. Legal protected birds were listed 23 species including 15 protected species and 14 natural monument species. Of them, only three species, Accipiter soloensis, A. nisus, Falco tinnunculus were widely distributed. And the others, Aix gatericuzata, Perms apivorus, Accipiter gentilis, A. gularis, Buteo logopus, B. buteo, Circus cyaneus, Falco columbarius, Grus vipio, Bubo bubo, Asio otus, Otus scops,0. bakkamoenu, Ninox scutuznta, Strix aluco, Dryocopus martius, Dendrocopos nanus , Pitta brachyura, Galerida cristnta, Terpsiphone atyocauduta were showed restricted distribution. Therefore, it is considered that careful consideration should be given to these conservation measures.