• Korean journal of applied entomology
• /
• v.59 no.3
• /
• pp.243-250
• /
• 2020

Two meridic diets, N4 and N6, containing pinto bean, wheat germ, soybean, whole milk and sucrose as main nutrients were developed for rearing Spodoptera frugiperda (Noctuidae) larvae. Six larval instars were observed when neonate larvae were individually raised on these diets in small petri-dishes (ø 50 × 10 mm, 19.6 ㎤) at 25℃ and 15:9 h (light:dark) photoperiod. The average pupation rate of 97.8% on the N4 diet was significantly higher than the rate of 85.6% on N6 diet. The emergence rates were 92.0% on N4 diet and 93.5% on N6 diet, with a non-significant difference. The larval periods were 17.9 and 17.7 days for females, and 18.7 and 18.5 days for males, for N4 and N6 diets, respectively, with non-significant differences between diets and sexes. The pupal periods on both diets were identical (11.1 days for females and 12.8 days for males), despite differences between sexes. The pupal weights of both sexes on N4 diet were identical with a value of 257 mg, whereas those on N6 diet were 256 and 263 mg for females and males, respectively, with a non-significant difference. The longevity of female adults that emerged on N6 diet was 13.8 days and longer than 8.6 days on N4 diet. The pre-oviposition periods were 5.0 and 4.2 days on the N4 and N6 diets, respectively, with a non-significant difference, however, the oviposition period of 6.5 days on N6 diet was longer than the period of 3.9 days on N4 diet. The effective fecundity on N6 diet was 1,392 eggs (maximum 1,776) and was higher than that of 942 eggs (maximum 1,694) on N4 diet, with a non-significant difference. The egg hatching rates on N4 and N6 diets were 79.2 and 79.8%, and egg periods were 3.0 and 2.9 days, respectively, with non-significant differences.

• Korean journal of applied entomology
• /
• v.61 no.3
• /
• pp.423-434
• /
• 2022

The two previously developed artificial diets (N4 and N6) used for rearing Spodoptera frugiperda (Noctuidae) larvae, were selected as highly-fit ones for rearing Mythimna loreyi larvae. Almost all biological characteristics were not significantly different between the colonies reared on the two diets at 25℃ and 15:9 h (light:dark) photoperiod. The developmental periods were 4.9-5.2 days for eggs, and 22.3-23.2 days for larvae. The pupal period and weight were different between the sexes in each diet colony. The pupal periods in females and males showed 12.6-12.8 days and 14.1-14.5 days, respectively. The pupal weights were ca. 345 mg for females and ca. 380 mg for males. The pupation and emergence rates were ca. 91-94%, and ca. 91-95%, respectively, without significant differences between the two colonies. The pre-oviposition and oviposition periods were 3.4 days and 4.7-4.8 days, respectively. The adult longevity was 8.2 days in females and 10.3-12.4 days in males. Total offsprings produced were found to be 724-847 larvae on an average with ca. 1,400 maximum larvae. In the life table analysis, the intrinsic rates of increases (0.1181 for N4 and 0.1253 for N6) were not significantly different between the two colonies. Individual differences in the larval instar number 5 and 6 were found within a diet colony. The ratios of 5-instar larvae were ca. 22% in N4 colony and ca. 7% in N6 colony. The larval period of 6-instar larvae was longer than that of 5-instar larvae. Width of head capsule in larvae varied from ca. 309 ㎛ for 1st instar to ca. 3,065 ㎛ for 6th instar. Body lengths measured from ca. 2.0 mm for 1st instar to ca. 29.1 mm for 6th instar. Larvae of M. loreyi and M. separata were found at the same time in a maize field during June and July, 2020.

• Korean journal of applied entomology
• /
• v.61 no.3
• /
• pp.409-422
• /
• 2022

Two dominant thrips in hot pepper (Capsicum annuum) cultivating in greenhouses are Frankliniella occidentalis and F. intonsa in Korea. This study investigated their overwintering physiology. These two thrips were freeze-susceptible and suppressed the body freezing temperature by lowering supercooling point (SCP) down to -15~-27℃. However, these SCPs varied among species and developmental stages. SCPs of F. occidentalis were -25.7±0.5℃ for adults, -17.2±0.3℃ for pupae, and -15.0±0.4℃ for larvae. SCPs of F. intonsa were -24.0±1.0℃ for adults, -27.0±0.5℃ for pupae, -17.2±0.8℃ for larvae. Cold injuries of both species occurred at low temperature treatments above SCPs. Thrips mortality increased as the treatment temperature decreased and its exposure period increased. F. occidentalis exhibited higher cold tolerance than F. intonsa. In both species, adults were more cold-tolerant than larvae. Two thrips species exhibited a rapid cold hardening because a pre-exposure to 0℃ for 2 h significantly enhanced the cold tolerance to a lethal cold temperature treatment at -10℃ for 2 h. In addition, a sequential exposure of the thrips to decreasing temperatures made them to be acclimated to low temperatures. To investigate the overwintering sites of the two species, winter monitoring of the thrips was performed at the greenhouses. During winter season (November~February), adults of the two species were not captured in outside of the greenhouses. However, F. occidentalis adults were captured to the traps and observed in weeds within the greenhouses. F. occidentalis adults were also emerged from soil samples obtained from the greenhouses during the winter season. F. intonsa adults did not come out from the soil samples at November and December, but emerged from the soil samples obtained after January. To determine the adult emergence due to diapause development, two thrips species were reared under different photoperiods. Adult development occurred in all photoperiod treatments in F. occidentalis, but did not in F. intonsa especially under short periods. Tomato spotted wilt virus, which is transmitted by these two species, was detected in the weeds infested by the thrips during the winter season. These results suggest that F. occidentalis develops on weeds in the greenhouses while F. intonsa undergoes a diapause in the soil during winter.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.205-225
• /
• 2018

Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.

• Korean Journal of Weed Science
• /
• v.2 no.1
• /
• pp.31-40
• /
• 1982

For the effective control of weeds in mechanically transplanted paddy field weeding effects of naproanide ${\alpha}$-(${\beta}$-naphthoxy) propion anilide], pyrazolate [4-2, 4-dichlorobenzoyl)-1, 3-dimethyl pyrazol-5-yl-p-tolune sulphanate], chlormethoxynil (2, 4-dichloro-phenyl-4-nitro-3-methoxy phenyl ether), SL-49 [1-3dimethyl-4(2, 4dichlorobenzoyl)-5-phenacyloxy pyrazole], ACN (3-chloro-2-amino-l, 4-naphthoquinone) either alone or in combination with butachlor (2-chlor-2, 6-diethyl-N-buthoxymethyl acetanilide) were compared. Pyrazolate and SL-49 were most effective for the control of Sagittaria pygmaea MIQ. and Potomogeton distinctus A. BENN. including most annual weeds. Weeding effect of butachlor alone was very high for annuals, good for Cyperus serotinus ROTTB. and poor for S. pygmaea and P. distinctus. But the weeding effect of the combination of butachlor and pyrazolate was stronger than that of butachlor alone and therefore this mixture was effective for S. pygmaea, P. distinctus and C. serotinus including all the annual weeds. The combination of butachlor and SL-49 showed the same tendency as the combination of butachlor and pyrazolate. Naproanilide was not effective for the control of Echinochlor crusgalli P. BEAUV and less effective for Monochoria vaginalis PRESL, but excellent for S. pygmaea. By mixing butachlor with naproanilide weeding, spectrum for annuals and S. pygmaea was much increased by that for P. distinctus and C. serotinus was not satisfactory. ACN was not satisfactory for the control of all the tested weeds but the weeding effect was increased in general by mixing with butachlor. Chlormethoxynil was excellent for the control of annual weeds but it has no effect on C. serotinus, S. pygmaea and P. distinctus showing some initial controling effect but these weeds regrew afterwards. The weeding activity of ACN increased in combination with butachlor and the residual activity was stronger than that of ACN alone. A light crop injury was found at the initial period after treatments in all treated plots. The yield from all treated plots except those from plots treated with ACN, butachlor and naproanilide were not significantly different from the band weeded plot.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.89-105
• /
• 2014

After emergence of Internet, social media with highly interactive Web 2.0 applications has provided very user friendly means for consumers and companies to communicate with each other. Users have routinely published contents involving their opinions and interests in social media such as blogs, forums, chatting rooms, and discussion boards, and the contents are released real-time in the Internet. For that reason, many researchers and marketers regard social media contents as the source of information for business analytics to develop business insights, and many studies have reported results on mining business intelligence from Social media content. In particular, opinion mining and sentiment analysis, as a technique to extract, classify, understand, and assess the opinions implicit in text contents, are frequently applied into social media content analysis because it emphasizes determining sentiment polarity and extracting authors' opinions. A number of frameworks, methods, techniques and tools have been presented by these researchers. However, we have found some weaknesses from their methods which are often technically complicated and are not sufficiently user-friendly for helping business decisions and planning. In this study, we attempted to formulate a more comprehensive and practical approach to conduct opinion mining with visual deliverables. First, we described the entire cycle of practical opinion mining using Social media content from the initial data gathering stage to the final presentation session. Our proposed approach to opinion mining consists of four phases: collecting, qualifying, analyzing, and visualizing. In the first phase, analysts have to choose target social media. Each target media requires different ways for analysts to gain access. There are open-API, searching tools, DB2DB interface, purchasing contents, and so son. Second phase is pre-processing to generate useful materials for meaningful analysis. If we do not remove garbage data, results of social media analysis will not provide meaningful and useful business insights. To clean social media data, natural language processing techniques should be applied. The next step is the opinion mining phase where the cleansed social media content set is to be analyzed. The qualified data set includes not only user-generated contents but also content identification information such as creation date, author name, user id, content id, hit counts, review or reply, favorite, etc. Depending on the purpose of the analysis, researchers or data analysts can select a suitable mining tool. Topic extraction and buzz analysis are usually related to market trends analysis, while sentiment analysis is utilized to conduct reputation analysis. There are also various applications, such as stock prediction, product recommendation, sales forecasting, and so on. The last phase is visualization and presentation of analysis results. The major focus and purpose of this phase are to explain results of analysis and help users to comprehend its meaning. Therefore, to the extent possible, deliverables from this phase should be made simple, clear and easy to understand, rather than complex and flashy. To illustrate our approach, we conducted a case study on a leading Korean instant noodle company. We targeted the leading company, NS Food, with 66.5% of market share; the firm has kept No. 1 position in the Korean "Ramen" business for several decades. We collected a total of 11,869 pieces of contents including blogs, forum contents and news articles. After collecting social media content data, we generated instant noodle business specific language resources for data manipulation and analysis using natural language processing. In addition, we tried to classify contents in more detail categories such as marketing features, environment, reputation, etc. In those phase, we used free ware software programs such as TM, KoNLP, ggplot2 and plyr packages in R project. As the result, we presented several useful visualization outputs like domain specific lexicons, volume and sentiment graphs, topic word cloud, heat maps, valence tree map, and other visualized images to provide vivid, full-colored examples using open library software packages of the R project. Business actors can quickly detect areas by a swift glance that are weak, strong, positive, negative, quiet or loud. Heat map is able to explain movement of sentiment or volume in categories and time matrix which shows density of color on time periods. Valence tree map, one of the most comprehensive and holistic visualization models, should be very helpful for analysts and decision makers to quickly understand the "big picture" business situation with a hierarchical structure since tree-map can present buzz volume and sentiment with a visualized result in a certain period. This case study offers real-world business insights from market sensing which would demonstrate to practical-minded business users how they can use these types of results for timely decision making in response to on-going changes in the market. We believe our approach can provide practical and reliable guide to opinion mining with visualized results that are immediately useful, not just in food industry but in other industries as well.