• Title/Summary/Keyword: group and individual

Search Result 3,467, Processing Time 0.04 seconds

A New Short Growth-Duration Rice Cultivar, "Keumo 3" (소득작물 전후작용 단기성 벼 품종 "금오3호")

  • Kang, Jong-Rae;Lee, Jong-Hee;Kwack, Do-Yeon;Lee, Jeom-Sik;Park, No-Bong;Ha, Woon-Gu;Park, Dong-Soo;Yeo, Un-Sang;Lim, Sang-Jong;Oh, Byeong-Geun
    • Korean Journal of Breeding Science
    • /
    • v.41 no.3
    • /
    • pp.292-298
    • /
    • 2009
  • A new rice cultivar "Keumo 3" was developed for adopting under double cropping system with after or before cash crop cultivation. It was selected from the cross-combination between YR17202 $F_2$/Shinkeumobyeo//YR15727-B-B-B-102. The parent, YR17202 $F_2$ individual plant, was used for tolerance to lodging, it derived from a cross between Nonganbyeo/Shinkeumobyeo. Nonganbyeo is well known to lodging tolerance cultivar, as well as biotic stress, because it was developed by crossing with Tongil type. And the YR15727-B-B-B-102 line used as another parent with short growth duration, likewise highly resistance to rice blast disease. The pedigree derived from the cross-combination YR17202 $F_2$/Shinkeumobyeo//YR15727-B-B-B-102 were generated to $F_7$, and a best line among them named as Milyang 201. After a series of yield trials, including local adaptability test conducted throughout the peninsular of Korea, Milyang 201 was registered with the name of "Keumo 3" in 2005. The cultivar belongs to a early maturing group and heads 4 days earlier than Keumobyeo, a standard cultivar. It has short culm, and less spikelet number per panicle than Keumobyeo. However, its milled rice yield grown under extremely late transplanting time, 10. July, over the 3 local sites for 2003-2005 years, averaged 4,48 MT/ha, which is 6% higher than the standard, Keumobyeo. "Keumo 3" has showed a durable resistance to leaf blast disease during fourteen blast nurseries screening covered from south to north in Korea for 2003-2007 years. And it was confirmed harbours pi-zt, a durable blast resistance gene. Moreover it was incompatible with 19 blast isolates under artificial inoculation, except one isolate, K1101. Additionally, "Keumo 3" exhibits resistance to $K_1$, $K_2$ and $K_3$ of bacterial blight pathogen, as well as strip virus disease resistance, and moderate resistance to dwarf virus disease. Consequently, the new rice cultivar "Keumo 3" would be well adopted where a bio stress makes a big problem annually.

Organic acidemias in Korea - Eight years experience of organic acid analysis - (유기산혈증-유기산 분석 8년의 정리)

  • Bang, Jun Suck;Lim, Si Hong;Lee, Kyung Hwa;Bae, Eun Joo;Park, Won Il;Lee, Hong Jin
    • Clinical and Experimental Pediatrics
    • /
    • v.49 no.3
    • /
    • pp.258-267
    • /
    • 2006
  • Purpose : We have done this retrospective study to know the relative incidence and clinical manifestations of organic acidopathies in Korea during 8 years(from Jul. 1997 to May 2005). This results of organic acid analysis of 1,787 patients were compared with the results of organic acid analysis that were published three years ago. Methods : The results of quantitative organic acid analysis of samples of 1788 patients, referred from Jul. 1997 to May 2005, were analyzed retrospectively according to four age group(-2 mon, 3 mon-2 years, 3-12 years) and major clinical manifestations. Quantification of 83 organic acids was done with gas chromatography and mass spectometry. Results : We diagnosed 470 patients with 27 diseases of organic acid metabolism during this study period. Diseases found more than 10 cases are cytosolic 3-ketothiolase deficiency, mitochondrial respiratory chain disorders, PDHC deficiency, mitochondrial 3-ketothiolase deficiency, glutaric aciduria type II, biotinidase deficiency, methylmalonic aciduria and propionic aciduria. Other diseases were diagnosed in less than 10 cases. Conclusion : Though the incidence of individual organic acidemia is low, the overall incidence of organic acidemia as a whole seems to be relatively high in Korea. Compared with the results of organic acid analysis that were reported three years ago, we couldn't find a new disease and the difference of the relative incidences of high incident diseases. We were apprehensive of the errors that was owing to the short study period(3 years), but the relative incidences of our study(8 years) were similar to the results of organic acid analysis that were reported three years ago.

A Study on Reputation as Corporate Asset (기업자산으로서의 기업명성가치 연구: 국내 4개 기업 슈퍼브랜드와 기업명성, 미디어 이용간 관련성을 중심으로)

  • Lee, Cheol-Han;Cha, Hee-Won
    • Korean journal of communication and information
    • /
    • v.30
    • /
    • pp.203-237
    • /
    • 2005
  • The purpose of this study is to find a model that can measure the public relations programs based on the assumption that the public relations should aim to lift the corporate reputation. It is a trend that corporate's activities are to be measured from the standpoint of cost-benefit efficiency. However, public relations fields in Korea is left behind this trend because the fields lack in sophisticated model. In order to fill this gap, the researchers introduce the reputation measurement model that can calculate individual corporate public relations programs. In addition, this reputation model Is applied to Korean companies with the expectation of producing a PR index which ran be used to measure the reputation as corporate asset, or superbrand. This study examines the effects of superbrand on consumers according to the media use. Based on the expert group interviews and surveys on consumers, the factors of reputation are drawn. These factors contribute to find reputation model and measurement index which are again applied to measure the Korean companies' public relations programs. Using superbrand as dependent variables and managing abilities, corporate responsibility, corporate communication, and product/employee quality, this study seeks to find which factor specifically attribute to lift corporate reputation. Results show that each factor influences the corporate reputation positively. In addition, the researchers find that media use is moderately related to the superbrand building process in cognitive dimension.

  • PDF

Diagnostic Ability of Tc-99m MIBI SPECT in Coronary Artery Diseases is not Affected by the Degree of Exercise (운동 정도와 무관한 Tc-99m Methoxyisobutyl Isonitrile 심근관류 스캔의 진단능)

  • Lee, Jae-Tae;Kim, Jong-Soo;Chun, Kyung-Ah;Lee, Sang-Woo;Kang, Do-Young;Cho, Yong-Keun;Chae, Shung-Chull;Lee, Kyu-Bo
    • The Korean Journal of Nuclear Medicine
    • /
    • v.33 no.1
    • /
    • pp.40-48
    • /
    • 1999
  • Purpose: The sensitivity of ST-depression in the electrocardiogram during exercise is influenced by the level of efforts. However, unlike the prevalence of ST-depression on exercise ECG, the degree of exercise is reported to do not influence the diagnostic ability of myocardial perfusion scan. Furthermore, the relation between the prevalence of myocardial ischemia and effort is still controversial. We evaluated the effect of the degree of exercise on the ability of SPECT imaging to detect coronary artery stenosis. Materials and Methods: The patient population was comprised of 111 patients (73 men and 38 women, mean age 56 years) who underwent an exercise test in conjunction with Tc-99m MIBI and cardiac catheterization within 3 months apart each other. The degree of exercise was classified into four groups according to the percentage of maximal predicted heart rate. The sensitivity and specificity was compared between each group. Results: The overall diagnostic sensitivity was significantly higher with Tc-99m MIBI SPECT than exercise ECG. The specificity was not significantly different between two tests. Sensitivity and specificity of Tc-99m MIBI was not different between four groups. Sensitivity for individual coronary stenosis seemed to be lower in subjects who had premature termination of exercise due to early appearance of ST depression. Conclusion: These results suggest that the overall diagnostic sensitivity of Tc-99m MIBI myocardial perfusion SPECT is not significantly affected by the degree of exercise in stable patients undergoing symptom-limited treadmill exercise testing. Myocardial perfusion SPECT imaging should be added to routine exercise stress testing for the detection of coronary artery disease.

  • PDF

Research on the Factors that Affect Consumption Behaviors of Ethnic Food Restaurants (외국음식전문점 이용행동에 영향을 미치는 요인에 관한 연구)

  • Jung, Hyung-Shik;Kim, Young-Shim
    • CRM연구
    • /
    • v.2 no.2
    • /
    • pp.1-19
    • /
    • 2009
  • In an attempt to explore the consumption behaviors of customers regarding ethnic food restaurants the present study examined the effects of consumer characteristics, accessibility of ethnic food restaurants, product characteristics, and social factors on the customer behavior towards ethnic food restaurants, and further investigated the causal relationship between the customer behavior and his or her intent to reuse. A questionnaire survey was conducted approximately for a month with domestic consumers who had tried foreign cuisines. A total of 230 questionnaires were distributed and 215 questionnaires were collected, of which 210 were used in the final analysis excluding five due to inadequate responses. The finding of the study were as follows. First, of the consumers' lifestyles category the gourmet oriented did not yield significant effect on subjective norm or other consumption behavior, whereas the trend oriented had noticeable influence on both factors. Second, while consumers' diversity-seeking characteristic did not affect subjective norm, it affected consumption behavior of ethic food restaurants. The results seem to indicate that the diversity-seeking characteristic is more to one's individual attributes, rather than being influenced by others. Third, ethnic food restaurant's consumption accessibilities strongly influenced the subjective norm, suggesting that in using the ethnic food restaurants, the more convenient the accessibility is, the higher the possibility of use from influenced reference group. However, when consumers previously had not been exposed to ethnic cuisines, convenient accessibility was not able to overcome the barriers of consumer reluctance, nor directly shape positive behaviors. Fourth, while national uniqueness of ethnic food did not affect subjective norm, the uniqueness did have positive impact on consumption behavior of foreign ethnic food restaurants. Fifth, consumer's subjective norm positively influenced both consumption behavior of ethnic food restaurants and their intent for future use. Lastly, consumption behavior toward foreign ethnic food restaurants positively influenced consumer's intent for future use, indicating that it would be most imperative and effective to first help reinforce positive attitude in oder to encourage a more use of ethnic food restaurants.

  • PDF

Identification of Domesticated Silkworm Varieties Using a Whole Genome Single Nucleotide Polymorphisms-based Decision Tree (전장유전체 SNP 기반 decision tree를 이용한 누에 품종 판별)

  • Park, Jong Woo;Park, Jeong Sun;Jeong, Chan Young;Kwon, Hyeok Gyu;Kang, Sang Kuk;Kim, Seong-Wan;Kim, Nam-Suk;Kim, Kee Young;Kim, Iksoo
    • Journal of Life Science
    • /
    • v.32 no.12
    • /
    • pp.947-955
    • /
    • 2022
  • Silkworms, which have recently shown promise as functional health foods, show functional differences between varieties; therefore, the need for variety identification is emerging. In this study, we analyzed the whole silkworm genome to identify 10 unique silkworm varieties (Baekhwang, Baekok, Daebaek, Daebak, Daehwang, Goldensilk, Hansaeng, Joohwang, Kumkang, and Kumok) using single nucleotide polymorphisms (SNP) present in the genome as biomarkers. In addition, nine SNPs were selected to discriminate between varieties by selecting SNPs specific to each variety. We subsequently created a decision tree capable of cross-verifying each variety and classifying the varieties through sequential analysis. Restriction fragment length polymorphism (RFLP) was used for SNP867 and SNP9183 to differentiate between the varieties of Daehwang and Goldensilk and between Kumkang and Daebak, respectively. A tetra-primer amplification refractory (T-ARMS) mutation was used to analyze the remaining SNPs. As a result, we could isolate the same group or select an individual variety using the nine unique SNPs from SNP780 to SNP9183. Furthermore, nucleotide sequence analysis for the region confirmed that the alleles were identical. In conclusion, our results show that combining SNP analysis of the whole silkworm genome with the decision tree is of high value as a discriminative marker for classifying silkworm varieties.

Prevalence of Orthostatic Dysregulation in Elementary School Students and Frequency of Individual Symptoms (학동기 아동의 Orthostatic Dysregulation의 유병률과 임상증상의 빈도에 대한 연구)

  • Yang, Eun Seok;Kim, Eun-Young;Moon, Kyoung-Rae;Park, Sang Kee;Park, Young Bong;Rho, Young Il
    • Clinical and Experimental Pediatrics
    • /
    • v.48 no.2
    • /
    • pp.138-142
    • /
    • 2005
  • Purpose : The purpose of the present study was to access the prevalence of orthostatic dysregulation(OD) and the frequency of each category for major and minor criteria among elementary school students using the OD questionnaire. Methods : We carried out inquiry by questionnaire as to the frequency of OD among two elementary schools with 725 students, 10 to 12 years of age, residing in Gwangju, Korea. The questionnaire was made according to criteria proposed by the Japan OD Study Group. Results : Of the 725 students(male 390; female 335) questioned, the OD was found in 338 students (53.5 percent). Prevalence of OD in males(59.2 percent) was significantly higher than in females(46.8 percent)(P<0.05). Palpitation with slight exercise(95.9 percent) was the most frequent major symptom. Headaches(85.8 percent) were the most frequent minor symptom among cases of OD. Conclusion : The prevalence of OD in elementary school students in this study(53.5 percent) was higher than in other studies. Contrary to studies from other countries, the male to female ratio was reversed. Because the diagnostic criteria seem to be dependent on subjective reporting of the symptoms, a newer diagnostic system based on more objective findings should be established.

Study on the effect of small and medium-sized businesses being selected as suitable business types, on the franchise industry (중소기업적합업종선정이 프랜차이즈산업에 미치는 영향에 관한 연구)

  • Kang, Chang-Dong;Shin, Geon-Chel;Jang, Jae Nam
    • Journal of Distribution Research
    • /
    • v.17 no.5
    • /
    • pp.1-23
    • /
    • 2012
  • The conflict between major corporations and small and medium-sized businesses is being aggravated, the trickle down effect is not working properly, and, as the controversy surrounding the effectiveness of the business limiting system continues to swirl, the plan proposed to protect the business domain of small and medium-sized businesses, resolve polarization between these businesses and large corporations, and protect small family run stores is the suitable business type designation system for small and medium-sized businesses. The current status of carrying out this system of selecting suitable business types among small and medium-sized businesses involves receiving applications for 234 items among the suitable business types and items from small and medium-sized businesses in manufacturing, and then selecting the items of the consultative group by analyzing and investigating the actual conditions. Suitable business type designation in the service industry will involve designation with priority on business types that are experiencing social conflict. Three major classifications of the service industry, related to the livelihood of small and medium-sized businesses, will be first designated, and subsequently this will be expanded sequentially. However, there is the concern that when designated as a suitable business type or item, this will hinder the growth motive for small to medium-sized businesses, and designation all cause decrease in consumer welfare. Also it is highly likely that it will operate as a prior regulation, cause side-effects by limiting competition systematically, and also be in violation against the main regulations of the FTA system. Moreover, it is pointed out that the system does not sufficiently reflect reverse discrimination factor against large corporations. Because conflict between small to medium sized businesses and large corporations results from the expansion of corporations to the service industry, which is unrelated to their key industry, it is necessary to introduce an advanced contract method like a master franchise or local franchise system and to develop local small to medium sized businesses through a franchise system to protect these businesses and dealers. However, this method may have an effect that contributes to stronger competitiveness of small to medium sized franchise businesses by advancing their competitiveness and operational methods a step further, but also has many negative aspects. First, as revealed by the Ministry of Knowledge Economy, the franchise industry is contributing to the strengthening of competitiveness through the economy of scale by organizing existing individual proprietors and increasing the success rate of new businesses. It is also revealed to be a response measure by the government to stabilize the economy of ordinary people and is emphasized as a 'useful way' to revitalize the service industry and improve the competitiveness of individual proprietors, and has been involved in contributions to creating jobs and expanding the domestic market by providing various services to consumers. From this viewpoint, franchises fit the purpose of the suitable business type system and is not something that is against it. Second, designation as a suitable business type may decrease investment for overseas expansion, R&D, and food safety, as well negatively affect the expansion of overseas corporations that have entered the domestic market, due to the contraction and low morale of large domestic franchise corporations that have competitiveness internationally. Also because domestic franchise businesses are hard pressed to secure competitiveness with multinational overseas franchise corporations that are operating in Korea, the system may cause difficulty for domestic franchise businesses in securing international competitiveness and also may result in reverse discrimination against these overseas franchise corporations. Third, the designation of suitable business type and item can limit the opportunity of selection for consumers who have up to now used those products and can cause a negative effect that reduces consumer welfare. Also, because there is the possibility that the range of consumer selection may be reduced when a few small to medium size businesses monopolize the market, by causing reverse discrimination between these businesses, the role of determining the utility of products must be left ot the consumer not the government. Lastly, it is desirable that this is carried out with the supplementation of deficient parts in the future, because fair trade is already secured with the enforcement of the franchise trade law and the best trade standard of the Fair Trade Commission. Overlapping regulations by the suitable business type designation is an excessive restriction in the franchise industry. Now, it is necessary to establish in the domestic franchise industry an environment where a global franchise corporation, which spreads Korean culture around the world, is capable of growing, and the active support by the government is needed. Therefore, systems that do not consider the process or background of the growth of franchise businesses and harm these businesses for the sole reason of them being large corporations must be removed. The inhibition of growth to franchise enterprises may decrease the sales of franchise stores, in some cases even bankrupt them, as well as cause other problems. Therefore the suitable business type system should not hinder large corporations, and as both small dealers and small to medium size businesses both aim at improving competitiveness and combined growth, large corporations, small dealers and small to medium sized businesses, based on their mutual cooperation, should not include franchise corporations that continue business relations with them in this system.

  • PDF

Research on the Relation between Musculoskeletal symptoms and Diagnosis using Moire Topography among Workers at an Automobile Manufacturing Plant (자동차회사 근로자를 대상으로 한 근골격계 자각증상과 moire 영상 진단과의 관계 연구)

  • Chun Eun-Joo;Lee Young-Gil;Jahng Doo-Sub;Lee Ki-Nam;Song Yung-Sun
    • Journal of Society of Preventive Korean Medicine
    • /
    • v.5 no.2
    • /
    • pp.69-92
    • /
    • 2001
  • The purposes of this study were to offer foundation making more certain standards of musculoskeletal disorder diagnosis, We researched musculoskeletal symptoms degrees, frequencies, and cares and then examined relation between musculoskeletal symptoms and diagnosis of musculoskeletal conditions using moire topography among workers at an automobile manufacturing plant. Therefore we propose the possibility of moire topography as diagnosing utilities of musculoskeletal disorders. Methods: This study was to examine the general characteristics, complaints of musculoskeletal symptoms, and work-related musculoskeletal disorder rates of cervicobrachial and lumbar area by survey among 435 workers at an automobile manufacturing plant and then to show each frequency and percentage, In the diagnosis using moire topography, we studied pain control necessity of cervicobrachial and lumbar area, 435 subjects were classified by 5 levels: A(no symptoms), B(need management), C(need treatment) and then more divided by B1(light symptoms)/B2(heavy symptoms), C1(light symptoms)/C2(heavy symptoms), And musculoskeletal areas were divided by 2 parts, cervicobrachial area(neck, shoulder, arm&elbow, and wrist&hand) and lumbar area, Then, frequency and percentage of each musculoskeletal areas(cervicobrachial and lumbar area) were appeared. At last, Pearson's chi-square test analysis was utilized to observe the relation between diagnosis using moire topography and general characteristics and the relation between diagnosis using moire topography and work-related complaint of musculoskeletal symptoms of cervicobrachial and lumbar area, Results: The subjects employed for this research were categorized into; by gender, all of them were males(l00%): by age, under 35 years 12 %, 36-40 years 56.3%, 41-45 years 26.3 %, and above 46 years 5.3% with 36-40 years accounting for most of it. By living location, owned houses represented 69.7%, rented houses 23.4%, monthly-rented 1.6%, the others 5.3%; by education, middle school and lower represented 3.0%, high school 89.4%, and junior college and higher 7.6% with high school occupying most of the group. By marital status, married represented 95.2%, unmarried 4.1%, and the others 0.7% with most of them married; by alcohol, drinking represented 81.8% and non-drinking 18.2%; by smoking status, smoking represented 53.6%, non-smoking 46.4% with no big difference between them. By working time(hours/week), below 50 represented 26.9%, 50-60 67.6%, above 60 5.5%; by working time(hours/day), below 9 represented 21.6%, 10-12 73.1%, above 13 5.3%; by job tenure(years), below 10 represented 25.1%, 11-15 54.3%, 16-20 15.2%, above 21 5.5%. By personal income per year, below 30 million won represented 11.0%, 30-40 84.8%, above 40 4.1%; by sleeping hours, below 6 hours represented 26.7%, 7-8 hours 69.9%, above 9 hours 3.4%. Complaint rates of musculoskeletal symptoms and work-related musculoskeletal disorder rates were 63.9% and 54.9% with shoulder area occupying most of both them. By pain degree of musculoskeletal symptoms, shoulder area represented $2.73{\pm}0.84$, lumbar area $2.66{\pm}0.86$, wrist and hand area $2.59{\pm}0.86$, neck area $2.55{\pm}0.74$, and arm and elbow area $2.48{\pm}0.71$. By cares about musculoskeletal symptoms, taking medication or care represented 34.4%-46.7%, absence or leave 15.4%-28.7%, and job transfer 6.3%-11.5%. So experienced cases more than one thing among cares about musculoskeletal symptoms represented 39.6%-54%. In the diagnosis using moire topography, pain control necessity of cervicobrachial area was shown below; A(no symptoms) 20.7%, B1(need management/light symptoms) 64.6%, B2(need management/heavy symptoms) 11.5%, C1(need treatment/light symptoms) 3.0%, C2(need treatment/heavy symptoms) 0.2%. By lumbar area, A(no symptoms) 8.7%, B1(need management/light symptoms) 52.2%, B2(need management/heavy symptoms) 30.3%, C1(need treatment/light symptoms) 8.7%, C2(need treatment/heavy symptoms) was none. In the relation between pain control necessity and general characteristics, age(P=0.013), education(P=0.000), and job tenure(P=0.012) with pain control necessity showed differences with significance. The relation between pain control necessity and complaint of musculoskeletal symptoms of cervicobrachial and lumbar area showed no difference with significance; in cervicobrachial area represented P=0.708, lumbar area P=0.318 Conclusions: This study for musculoskeletal symptoms on workers at automobile manufacturing plant showed that complaint rates of musculoskeletal symptoms for cervicobrachial and lumbar area were so high, 63.9%. But Pearson's chi-square test analysis was utilized to study the relation between musculoskeletal symptoms and the diagnosis using moire topography, showed no differences with significance. They have no differences with significance, but the prevalence rates of diagnosis using moire topography for cervicobrachial and lumbar area were more higher than complaint rates of musculoskeletal symptoms; complaint rates of musculoskeletal symptoms were 52.4%, 34.5% and the diagnosis using moire topography were 79.3%, 91.3% for cervicobrachial and lumbar area. The results of this study indicate that the diagnosis using moire topography can find weak musculoskeletal disorders that an individual can not feel, not be judged work-related musculoskeletal disease. Therefore, this study has an important meaning that diagnosis using moire topography can predict and control own physical condition complete musculoskeletal disorders beforehand, since oriental medicine theory considers that prevention is important.

  • PDF

A Deep Learning Based Approach to Recognizing Accompanying Status of Smartphone Users Using Multimodal Data (스마트폰 다종 데이터를 활용한 딥러닝 기반의 사용자 동행 상태 인식)

  • Kim, Kilho;Choi, Sangwoo;Chae, Moon-jung;Park, Heewoong;Lee, Jaehong;Park, Jonghun
    • Journal of Intelligence and Information Systems
    • /
    • v.25 no.1
    • /
    • pp.163-177
    • /
    • 2019
  • As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.