• Asian-Australasian Journal of Animal Sciences
• /
• v.17 no.6
• /
• pp.777-783
• /
• 2004

Samples of 13 species of forest tree leaves fed to livestock in the semi-hilly arid zone of Punjab State in India were collected at 30 d interval for 12 months, in order to assess their nutritional worth for livestock. The ground samples were pooled for 4 different seasons viz. dry hot, hot humid, fall and winter. The chemical composition irrespective of the season revealed that CP content varied between 8.9 (Carrisa) to 22.0% (Leucaena). Globulin was the major protein fraction in most of the leaves. The lowest concentration of cell wall constituents was observed in Morus alba and Grewea. The leaves in general became fiberous and lignified during winter and fall as compared to summer season. The leaves of Grewea, Morus alba, Leucaena, Carrisa and Acacia were rich in Ca, P and most of the trace elements. The total phenolics ranged between 1.88% (Azardirachta) to 15.82% (Acacia). The leaves of Acacia had the highest concentration of hydrolysable tannins (14.6%) whereas that of Carrisa had that of condensed tannins (5.9%). The condensed tannins (more than 3%) were negatively correlated to the digestibility of dry matter (DM), neutral detergent fiber (NDF) and crude protein (CP). The digestion kinetic parameters for DM, NDF and CP revealed that leaves of Morus alba, Zizyphus and Ehretia had highest insoluble but potentially degradable fraction. The minimum rumen fill values also revealed that leaves of Grewea, Azardirachta, Morus, Ehretia and Leucaena had great potential for voluntary DM intake. The leaves of Ougeinia, Malha, Dodenia and Carrisa had significantly higher rumen fill value indicating poor potential for voluntary DM intake. Season did not have any significant impact on digestion kinetic parameters except that most of the leaves had low potentially degradable fraction, which was degraded at slow rate during winter. It was concluded that the leaves of Morus, Ehretia, Grewea and Leucaena had great potential as livestock feed, while feeding of Ougeinia, Malha and Dodonea leaves should be avoided.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.12
• /
• pp.9-16
• /
• 2019

The goal of this study is to propose an efficient model for recognizing and classifying tree images to measure the accuracy that can be applied to smart devices during class. From the 2009 revised textbook to the 2015 revised textbook, the learning objective to the fourth-grade science textbook of elementary schools was added to the plant recognition utilizing smart devices. In this study, we compared the recognition rates of trees before and after retraining using a pre-trained inception V3 model, which is the support of the Google Inception V3. In terms of tree recognition, it can distinguish several features, including shapes, bark, leaves, flowers, and fruits that may lead to the recognition rate. Furthermore, if all the leaves of trees may fall during winter, it may challenge to identify the type of tree, as only the bark of the tree will remain some leaves. Therefore, the effective tree classification model is presented through the combination of the images by tree type and the method of combining the model for the accuracy of each tree type. I hope that this model will apply to smart devices used in educational settings.

• Korean Journal of Computational Design and Engineering
• /
• v.3 no.1
• /
• pp.57-67
• /
• 1998

Genetic programming (GP) is an extension of a genetic algoriths paradigm, deals with tree structures representing computer programs as individuals. In recent, there have been many research activities on applications of GP to various engineering problems including system identification, data mining, function approximation, and so forth. However, standard GP suffers from the lack of the estimation techniques for numerical parameters of the GP tree that is an essential element in treating various engineering applications involving real-valued function approximations. Unlike the other research activities, where nonlinear optimization methods are employed, I adopt the use of a weighted linear associative memory for estimation of these parameters under GP algorithm. This approach can significantly reduce computational cost while the reasonable accurate value for parameters can be obtained. Due to the fact that the GP algorithm is likely to fall into a local minimum, the GP algorithm often fails to generate the tree with the desired accuracy. This motivates to devise a group of additive genetic programming trees (GAGPT) which consists of a primary tree and a set of auxiliary trees. The output of the GAGPT is the summation of outputs of the primary tree and all auxiliary trees. The addition of auxiliary trees makes it possible to improve both the teaming and generalization capability of the GAGPT, since the auxiliary tree evolves toward refining the quality of the GAGPT by optimizing its fitness function. The effectiveness of this approach is verified by applying the GAGPT to the estimation of the principal dimensions of bulk cargo ships and engine torque of the passenger car.

• Korean Journal of Environmental Agriculture
• /
• v.37 no.2
• /
• pp.87-96
• /
• 2018

BACKGROUND: The vigorous shoot growth in upper part of apple tree canopy leads to poor fruit quality and flower bud formation in lower part of canopy. So, this study was conducted to develop the proper control method about the shoot growth in upper part of apple tree canopy. METHODS AND RESULTS: Trunks of 'Fuji'/M9 apple trees were cut (back pruned) to 2.5 m in tree height on 11 February (dormant) or 12 April (full bloom). Naphthalene acetic acid (NAA) was applied at 2.0% to cut surface when trunk was pruned. Prohexadione-calcium (Pro-Ca) was sprayed at 250 mg/L above 2.0 m in tree height at 23 April (petal fall). The NAA or Pro-Ca application after trunk was pruned at dormant (TR-2 and TR-3) significantly reduced shoot growth in upper part of canopy compared with the control (tree was only pruned at dormant, TR-1), but the percent of shoots showing the secondary growth of TR-3 was higher over 2 times than that of TR-2. The reduction of shoot growth in upper part of canopy by TR-2 and TR-3 increased the fruit red color from the lower part in the treating year and blooming of the lower part in the following year. CONCLUSION: Applying 2.0% NAA to cut surface of pruned apple trunk at dormant was the most effective way for stabilization of the tree vigor in upper part of the canopy in a high density apple orchard.

• 한국방재학회:학술대회논문집
• /
• 2008.02a
• /
• pp.149-152
• /
• 2008

This study is the result between the variation of fuel moisture and the risk of forest fire through measuring the change of moisture containing ratio on-site and its average analysis for fallen leaves layer, humus layer, and soil layer in the forest. The measurement was performed on six days from the day after a rainfall. The fuel moisture on-site was measured on the day when the accumulated rainfall was above 5.0mm, and the measurements was 2 times in spring and 1 time in fall. From the pine forest which were distributed around Samcheok and Donghae in Kangwondo, three regions were selected by loose, medium, and dense forest density, and the fuel moisture was measured on fallen leaves layer, humus layer, and soil layer in the forest. for six days from the day after a rainfall. The study showed that the moisture containing ratio converged on 3 - 4 days in spring and fall for fallen leaves layer, and the convergence was made more than six days in spring and fall for the humus layer. In the other case of soil layer, the variation of moisture containing ratio after rainfall was not distinguishable regardless of season.

• Proceedings of the KAIS Fall Conference
• /
• 2010.05a
• /
• pp.424-427
• /
• 2010

정보화 사회로의 진입이 본격화 되면서 사회의 전반적인 분야에 걸쳐 다양한 용도로 컴퓨터 시스템이 사용되고 있다. 그에 따라 데이터의 방대한 양적 팽창이 이루어졌고, 이러한 데이터를 유용한 정보와 지식으로 바꿔야 하는 필요성들이 생겨났다. 이에 데이터 마이닝이라는 개념이 등장했고 현재 점점 더 많은 분야에서 사용되고 있고 다양한 각도에서 활발한 연구가 진행되고 있다. 현재 어장의 예측 방법은 주관적인 경험에 대부분 의존하고 객관적인 신뢰성이 떨어진다. 이에 본 논문은 데이터 마이닝 기법을 적용하여 데이터베이스의 정보를 이용해 어종별로 가장 빈번하게 이용되어지는 어장을 선별해 주는 기법을 제안한다.

• Proceedings of the KAIS Fall Conference
• /
• 2009.12a
• /
• pp.432-435
• /
• 2009

음악 레코딩 산업에서 5.1 서라운드 사운드 프로덕션은 이미 전 세계적으로 우리 실생활에 널리 사용 되어 왔다. 많은 음악 엔지니어들은 과거보다 더욱 진보된 사운드를 위해 다양한 기술적 시도를 하고있다. 본 논문은 현재 사용되고 있거나 개발 중에 있는 Sony/Philips, Fukada Tree, 그리고 Hamasaki Square 등 여러 종류의 서라운드 마이크로폰 테크닉을 분석하고, 다양한 악기 사용에 따라 달라지는 결과를 분석하여 서라운드 사운드 프러덕션에서 보다 효율적인 접근법을 모색하기 위한 연구이다.

• Proceedings of the KAIS Fall Conference
• /
• 2010.05a
• /
• pp.436-439
• /
• 2010

본 논문에서는 Ubiquitous Computing 환경 하에서 이종 시스템 간의 통합을 위한 데이터 관리 기법 모델을 제안하였다. 이종 시스템 간의 통합이 이루어지면 방대한 양의 데이터를 모든 시스템이 공유해야 하기 때문에 무분별한 데이터의 중복과 저장으로 인해 프로세스의 데이터 처리 성능 및 데이터 무결성을 보장받지 못 하는 등의 문제점이 발생한다. 이를 보완하기 위해 Minimal cost Spanning tree의 원리를 적용하여 시스템 통합에 따른 데이터 처리 및 무결성 문제 해결을 위한 메커니즘을 제시하고자 한다.

• International journal of advanced smart convergence
• /
• v.13 no.1
• /
• pp.212-220
• /
• 2024

When a typhoon or natural disaster occurs, a significant number of orchard fruits fall. This has a great impact on the income of farmers. In this paper, we introduce an AI-based method to enhance low-quality raw images. Specifically, we focus on apple images, which are being used as AI training data. In this paper, we utilize both a basic program and an artificial intelligence model to conduct a general image process that determines the number of apples in an apple tree image. Our objective is to evaluate high and low performance based on the close proximity of the result to the actual number. The artificial intelligence models utilized in this study include the Convolutional Neural Network (CNN), VGG16, and RandomForest models, as well as a model utilizing traditional image processing techniques. The study found that 49 red apple fruits out of a total of 87 were identified in the apple tree image, resulting in a 62% hit rate after the general image process. The VGG16 model identified 61, corresponding to 88%, while the RandomForest model identified 32, corresponding to 83%. The CNN model identified 54, resulting in a 95% confirmation rate. Therefore, we aim to select an artificial intelligence model with outstanding performance and use a real-time object separation method employing artificial function and image processing techniques to identify orchard fruits. This application can notably enhance the income and convenience of orchard farmers.

• Physical Therapy Korea
• /
• v.28 no.2
• /
• pp.123-131
• /
• 2021

Background: Only 2% of falls in older adults result in serious injuries (i.e., hip fracture). Therefore, it is important to differentiate injurious versus non-injurious falls, which is critical to develop effective interventions for injury prevention. Objects: The purpose of this study was to a. extract the best features of surface electromyography (sEMG) for classification of injurious falls, and b. find a best model provided by data mining techniques using the extracted features. Methods: Twenty young adults self-initiated falls and landed sideways. Falling trials were consisted of three initial fall directions (forward, sideways, or backward) and three knee positions at the time of hip impact (the impacting-side knee contacted the other knee ("knee together") or the mat ("knee on mat"), or neither the other knee nor the mat was contacted by the impacting-side knee ("free knee"). Falls involved "backward initial fall direction" or "free knee" were defined as "injurious falls" as suggested from previous studies. Nine features were extracted from sEMG signals of four hip muscles during a fall, including integral of absolute value (IAV), Wilson amplitude (WAMP), zero crossing (ZC), number of turns (NT), mean of amplitude (MA), root mean square (RMS), average amplitude change (AAC), difference absolute standard deviation value (DASDV). The decision tree and support vector machine (SVM) were used to classify the injurious falls. Results: For the initial fall direction, accuracy of the best model (SVM with a DASDV) was 48%. For the knee position, accuracy of the best model (SVM with an AAC) was 49%. Furthermore, there was no model that has sensitivity and specificity of 80% or greater. Conclusion: Our results suggest that the classification model built upon the sEMG features of the four hip muscles are not effective to classify injurious falls. Future studies should consider other data mining techniques with different muscles.