• Title/Summary/Keyword: detecting system

Search Result 3,010, Processing Time 0.032 seconds

Genetic Relationship and Characteristics Using Microsatellite DNA Loci in Horse Breeds. (Microsatellite DNA를 이용한 말 집단의 유전적 특성 및 유연 관계)

  • Cho, Gil-Jae
    • Journal of Life Science
    • /
    • v.17 no.5 s.85
    • /
    • pp.699-705
    • /
    • 2007
  • The present study was conducted to investigate the genetic characteristic and to establish the parentage verification system of the Korean native horse(KNH). A total number of 192 horses from six horse breeds including the KNH were genotyped using 17 microsatellite loci. This method consisted of multiplexing PCR procedure. The number of alleles per locus varied from 5 to 10 with a mean value of 7.35 in KNH. The expected heterozygosity and observed heterozygosity were ranged from 0.387 to 0.841(mean 0.702) and from 0.429 to 0.905(mean 0.703), respectively. The total exclusion probability of 17 microsatellite loci was 0.9999. Of the 17 markers, AHT4, AHT5, CA425, HMS2, HMS3, HTG10, LEX3 and VHL20 marker have relatively high PIC value(>0.7). This study found that there were specific alleles, P allele at AHT5, Q allele and R allele at ASB23, H allele at CA425, S allele at HMS3, J allele at HTG10 and J allele at LEX3 marker in KNH when compared with other horse populations. Also, the results showed two distinct clusters: the Korean native horse cluster(Korean native horse, Mongolian horse), and the European cluster(Jeju racing horse, Thoroughbred horse). These results present basic information for detecting the genetic markers of the KNH, and has high potential for parentage verification and individual identification of the KNH.

Analysis of Heavy Metals in $[^{201}Tl]$TICI Injection Using Polarography (폴라로그래피를 이용한 $[^{201}Tl]$염화탈륨 주사액의 중금속 분석)

  • Chun, Kwon-Soo;Suh, Yong-Sup;Yang, Seung-Dae;Ahn, Soon-Hyuk;Kim, Sang-Wook;Choi, Kang-Hyuk;Lee, Dong-Hoon;Lim, Sang-Moo;Yu, Kook-Hyun
    • The Korean Journal of Nuclear Medicine
    • /
    • v.34 no.4
    • /
    • pp.336-343
    • /
    • 2000
  • Purpose: Thallous-201 chloride produced at Korea Cancer Center Hospital(KCCH) is used in detecting cardiovascular disease and cancer. Thallium impurity can cause emesis, catharsis and nausea, so the presence of thallium and other metal impurities should be determined. According to USP and KP, their amounts must be less than 2 ppm in thallium and 5 ppm in total. In this study, the detection method of trace amounts of metal impurities in $[^{201}Tl]$TICI injection with polarography was optimized without environmental contamination. Materials and Methods: For the detection of metal impurities, Osteryoung Square Wave Stripping Voltammetry method was used in Bio-Analytical System (BAS) 50W polarograph. The voltammetry was composed of Dropping Mercury Electrode (DME) as a working electrode, Ag/AgCl as a reference electrode and Pt wire as a counter electrode. Square wave stripping method, which makes use of formation and deformation of amalgam, was adopted to determine the metal impurities, and pH 7 phosphate buffer was used as supporting electrolyte. Results: Tl, Cu and Pb in thallous-201 chloride solution were detected by scanning from 300 mV to -800 mV Calibration curves were made by using $TINO_3,\;CuSO_4\;and\;Pb(NO_3){_2}$ as standard solutions. Tl was confirmed at -450 mV peak potential and Cu at -50 mV Less than 2 ppm of Tl and Cu was detected and Pb was not detected in KCCH-produced thallous-201 chloride injection. Conclusion: Detection limit of thallium and copper is approximately 50 ppb with this method. As a result of this experiment, thallium and other metal impurities in thallous-201 chloride injection, produced at Korea Cancer Center Hospital, are in the regulation of USP and KP Polarograph could be applied for the determination of metal impurities in the quality control of radiopharmaceuticals conveniently without environmental contamination.

  • PDF

Analysis of Genetic Polymorphism by Bloodtyping in Jeju Horse (혈액형에 의한 제주말의 유전적 다형성 분석)

  • Cho Gil-Jae
    • Journal of Life Science
    • /
    • v.15 no.6 s.73
    • /
    • pp.972-978
    • /
    • 2005
  • The present study was carried out to investigate the blood markers of Jeju horses. The redcell cypes (blood groups) and blood protein types (biochemical polymorphisms) were tested from 102 Jeju horses by serological and electrophoretc procedure, and their phenotypes and gene frequencies were estimated. The blood group and biochemical polymorphism phenotypes observed with high frequency were $A^{af}\;(27.45\%$), $C^{a}\;(99.02\%$), $K^{-}\;(97.06\%$), $U^{a}\;(62.75\%$), $P^{b}\;(36.27\%$), $Q^{c}\;(47.06\%$), $D^{cgm/dghm}\;(13.73\%$), $D^{adn/cgm}\;(9.80\%$), $D^{ad/cgm}$\;(8.82\%$), $D^{dghm/dghm}(7.84\%$), $D^{cgm/cgm}(7.84\%$), $AL^{B}\;(48.04\%$), $GC^{F}\;(99.02\%$), $AlB^{K}\;(97.06\%$), $ES^{FI}\;(36.27\%$), $TF^{F2}\;(25.49\%$), $HB^{B1}\;(45.10\%$), and $PGD^{F}\;(86.27\%$) in Jeju horses, respectively. Alleles observed with high gene frequency were $A^{af}$ (0.3726), $A^{C}$ (0.2647), $C^{-}$ (0.5050), $K^{-}$ (0.9853), $U^{-}$ (0.6863), $P^{b}$ (0.4657), $Q^{c}$ (0.5294), $D^{cgm}$ (0.3039), $HB^{B1}$(0.6863), $PGD^{F}$ (0.9265), $AL^{B}$ (0.6912), $ALB^{K}$ (0.9852), $GC^{F}$ (0.9950), $ES^{I}$ (0.5000) and $TF^{F2}$ (0.4950) in Jeju horses, and sfecific alleles, $D^{cgm(f)}$ (0.0196), $HB^{A}$ (0.0147), $HB^{A2}$ (0.0196), $ES^{G}$ (0.0441), $ES^{H}$ (0.0098), $TF^{E}$TF'(0.0246), $TF^{H2}$ (0.0049) and $PGD^{D}$ (0.0098) were detected in Jeju horses. These preliminary results present basic information for detecting the genetic markers in Jeju horse. and developing a system for parentage verification and individuals identification in jeju horses.

Analysis of Optimal Pathways for Terrestrial LiDAR Scanning for the Establishment of Digital Inventory of Forest Resources (디지털 산림자원정보 구축을 위한 최적의 지상LiDAR 스캔 경로 분석)

  • Ko, Chi-Ung;Yim, Jong-Su;Kim, Dong-Geun;Kang, Jin-Taek
    • Korean Journal of Remote Sensing
    • /
    • v.37 no.2
    • /
    • pp.245-256
    • /
    • 2021
  • This study was conducted to identify the applicability of a LiDAR sensor to forest resources inventories by comparing data on a tree's position, height, and DBH obtained by the sensor with those by existing forest inventory methods, for the tree species of Criptomeria japonica in Jeolmul forest in Jeju, South Korea. To this end, a backpack personal LiDAR (Greenvalley International, Model D50) was employed. To facilitate the process of the data collection, patterns of collecting the data by the sensor were divided into seven ones, considering the density of sample plots and the work efficiency. Then, the accuracy of estimating the variables of each tree was assessed. The amount of time spent on acquiring and processing the data by each method was compared to evaluate the efficiency. The findings showed that the rate of detecting standing trees by the LiDAR was 100%. Also, the high statistical accuracy was observed in both Pattern 5 (DBH: RMSE 1.07 cm, Bias -0.79 cm, Height: RMSE 0.95 m, Bias -3.2 m), and Pattern 7 (DBH: RMSE 1.18 cm, Bias -0.82 cm, Height: RMSE 1.13 m, Bias -2.62 m), compared to the results drawn in the typical inventory manner. Concerning the time issue, 115 to 135 minutes per 1ha were taken to process the data by utilizing the LiDAR, while 375 to 1,115 spent in the existing way, proving the higher efficiency of the device. It can thus be concluded that using a backpack personal LiDAR helps increase efficiency in conducting a forest resources inventory in an planted coniferous forest with understory vegetation, implying a need for further research in a variety of forests.

Diagnostic Evaluation of the BioFire® Meningitis/Encephalitis Panel: A Pilot Study Including Febrile Infants Younger than 90 Days (BioFire® Meningitis/Encephalitis Panel의 진단적 유용성 평가: 90일 미만 발열영아에서의 예비 연구)

  • Kim, Kyung Min;Park, Ji Young;Park, Kyoung Un;Sohn, Young Joo;Choi, Youn Young;Han, Mi Seon;Choi, Eun Hwa
    • Pediatric Infection and Vaccine
    • /
    • v.28 no.2
    • /
    • pp.92-100
    • /
    • 2021
  • Purpose: Rapid detection of etiologic organisms is crucial for initiating appropriate therapy in patients with central nervous system (CNS) infection. This study aimed to evaluate the diagnostic value of the BioFire® Meningitis/Encephalitis (ME) panel in detecting etiologic organisms in cerebrospinal fluid (CSF) samples from febrile infants. Methods: CSF samples from infants aged <90 days who were evaluated for fever were collected between January 2016 and July 2019 at the Seoul National University Children's Hospital. We performed BioFire® ME panel testing of CSF samples that had been used for CSF analysis and conventional tests (bacterial culture, Xpert® enterovirus assay, and herpes simplex virus-1 and -2 polymerase chain reaction) and stored at -70℃ until further use. Results: In total, 72 (24 pathogen-identified and 48 pathogen-unidentified) CSF samples were included. Using BioFire® ME panel testing, 41 (85.4%) of the 48 pathogen-unidentified CSF samples yielded negative results and 22 (91.7%) of the 24 pathogen-identified CSF samples yielded the same results (enterovirus in 19, Streptococcus agalactiae in 2, and Streptococcus pneumoniae in 1) as those obtained using the conventional tests, thereby resulting in an overall agreement of 87.5% (63/72). Six of the 7 pathogen-unidentified samples were positive for human parechovirus (HPeV) via BioFire® ME panel testing. Conclusions: Compared with the currently available etiologic tests for CNS infection, BioFire® ME panel testing demonstrated a high agreement score for pathogen-identified samples and enabled HPeV detection in young infants. The clinical utility and cost-effectiveness of BioFire® ME panel testing in children must be evaluated for its wider application.

Development of Method using LC-ESI-MS/MS and KASP for Identification of Gymnema sylvestre in Food (식품에서 당살초 판별을 위한 LC-ESI-MS/MS 분석법과 KASP 마커 개발)

  • Park, Boreum;Lee, Sun Hee;Eom, Kwonyong;Noh, Eunyoung;Moon Han, Kyoung;Hwang, Jinwoo;Kim, Hyungil;Baek, Sun Young
    • Journal of Food Hygiene and Safety
    • /
    • v.37 no.2
    • /
    • pp.46-54
    • /
    • 2022
  • Known for its effectiveness in weight loss and diabetes prevention, Gymnema sylvestre products can be found in the US, Japanese, and Indian markets. However, the recommended dosage or safety of these products has not yet been proven. Therefore, development of an analytical method for detecting the content of Gymnema sylvestre in food products is required. Accordingly, this study proposes an analysis method that can examine Gymnema sylvestre in food using LC-ESI-MS/MS and KASP (Kompetitive Allele-Specific PCR) markers. In LC-ESI-MS/MS, a simultaneous analysis method for gymnemic acid and deacylgymnemic acid was optimized using negative ionization mode, and its validation test was completed for solid and liquid samples. In addition, KASP markers were prepared by finding the specific SNP of G. sylvestre in ITS2 and matK through DNA barcodes. The two KASP markers returned positive FAM fluorescence result when combined with G. sylvestre, and this aspect was confirmed in raw G. sylvestre as well. The applicability of the method was tested on 21 different food and healthy functional products containing G. sylvestre purchased on the internet. As a result, although there was a difference in the ratios of gymnemic acid and deacylgymnemic acid in LC-ESI-MS/MS, the index component was detected in all 21 products samples. In the KASP analysis, 9 products returned positive FAM result, and the rest of the products were found to be containing G. sylvestre extract. This study is the first study to use the dual system of LC-ESI-MS/MS and KASP for the analysis of G. sylvestre. The study has confirmed that these two methods are applicable to the examine G. sylvestre content in food products.

Efficient Topic Modeling by Mapping Global and Local Topics (전역 토픽의 지역 매핑을 통한 효율적 토픽 모델링 방안)

  • Choi, Hochang;Kim, Namgyu
    • Journal of Intelligence and Information Systems
    • /
    • v.23 no.3
    • /
    • pp.69-94
    • /
    • 2017
  • Recently, increase of demand for big data analysis has been driving the vigorous development of related technologies and tools. In addition, development of IT and increased penetration rate of smart devices are producing a large amount of data. According to this phenomenon, data analysis technology is rapidly becoming popular. Also, attempts to acquire insights through data analysis have been continuously increasing. It means that the big data analysis will be more important in various industries for the foreseeable future. Big data analysis is generally performed by a small number of experts and delivered to each demander of analysis. However, increase of interest about big data analysis arouses activation of computer programming education and development of many programs for data analysis. Accordingly, the entry barriers of big data analysis are gradually lowering and data analysis technology being spread out. As the result, big data analysis is expected to be performed by demanders of analysis themselves. Along with this, interest about various unstructured data is continually increasing. Especially, a lot of attention is focused on using text data. Emergence of new platforms and techniques using the web bring about mass production of text data and active attempt to analyze text data. Furthermore, result of text analysis has been utilized in various fields. Text mining is a concept that embraces various theories and techniques for text analysis. Many text mining techniques are utilized in this field for various research purposes, topic modeling is one of the most widely used and studied. Topic modeling is a technique that extracts the major issues from a lot of documents, identifies the documents that correspond to each issue and provides identified documents as a cluster. It is evaluated as a very useful technique in that reflect the semantic elements of the document. Traditional topic modeling is based on the distribution of key terms across the entire document. Thus, it is essential to analyze the entire document at once to identify topic of each document. This condition causes a long time in analysis process when topic modeling is applied to a lot of documents. In addition, it has a scalability problem that is an exponential increase in the processing time with the increase of analysis objects. This problem is particularly noticeable when the documents are distributed across multiple systems or regions. To overcome these problems, divide and conquer approach can be applied to topic modeling. It means dividing a large number of documents into sub-units and deriving topics through repetition of topic modeling to each unit. This method can be used for topic modeling on a large number of documents with limited system resources, and can improve processing speed of topic modeling. It also can significantly reduce analysis time and cost through ability to analyze documents in each location or place without combining analysis object documents. However, despite many advantages, this method has two major problems. First, the relationship between local topics derived from each unit and global topics derived from entire document is unclear. It means that in each document, local topics can be identified, but global topics cannot be identified. Second, a method for measuring the accuracy of the proposed methodology should be established. That is to say, assuming that global topic is ideal answer, the difference in a local topic on a global topic needs to be measured. By those difficulties, the study in this method is not performed sufficiently, compare with other studies dealing with topic modeling. In this paper, we propose a topic modeling approach to solve the above two problems. First of all, we divide the entire document cluster(Global set) into sub-clusters(Local set), and generate the reduced entire document cluster(RGS, Reduced global set) that consist of delegated documents extracted from each local set. We try to solve the first problem by mapping RGS topics and local topics. Along with this, we verify the accuracy of the proposed methodology by detecting documents, whether to be discerned as the same topic at result of global and local set. Using 24,000 news articles, we conduct experiments to evaluate practical applicability of the proposed methodology. In addition, through additional experiment, we confirmed that the proposed methodology can provide similar results to the entire topic modeling. We also proposed a reasonable method for comparing the result of both methods.

Brief Introduction of Research Progresses in Control and Biocontrol of Clubroot Disease in China

  • He, Yueqiu;Wu, Yixin;He, Pengfei;Li, Xinyu
    • 한국균학회소식:학술대회논문집
    • /
    • 2015.05a
    • /
    • pp.45-46
    • /
    • 2015
  • Clubroot disease of crucifers has occurred since 1957. It has spread to the whole China, especially in the southwest and nourtheast where it causes 30-80% loss in some fields. The disease has being expanded in the recent years as seeds are imported and the floating seedling system practices. For its effective control, the Ministry of Agriculture of China set up a program in 2010 and a research team led by Dr. Yueqiu HE, Yunnan Agricultural University. The team includes 20 main reseachers of 11 universities and 5 institutions. After 5 years, the team has made a lot of progresses in disease occurrence regulation, resources collection, resistance identification and breeding, biological agent exploration, formulation, chemicals evaluation, and control strategy. About 1200 collections of local and commercial crucifers were identified in the field and by artificiall inoculation in the laboratories, 10 resistant cultivars were breeded including 7 Chinese cabbages and 3 cabbages. More than 800 antagostic strains were isolated including bacteria, stretomyces and fungi. Around 100 chemicals were evaluated in the field and greenhouse based on its control effect, among them, 6 showed high control effect, especially fluazinam and cyazofamid could control about 80% the disease. However, fluzinam has negative effect on soil microbes. Clubroot disease could not be controlled by bioagents and chemicals once when the pathogen Plasmodiophora brassicae infected its hosts and set up the parasitic relationship. We found the earlier the pathogent infected its host, the severer the disease was. Therefore, early control was the most effective. For Chinese cabbage, all controlling measures should be taken in the early 30 days because the new infection could not cause severe symptom after 30 days of seeding. For example, a biocontrol agent, Bacillus subtilis Strain XF-1 could control the disease 70%-85% averagely when it mixed with seedling substrate and was drenching 3 times after transplanting, i.e. immediately, 7 days, 14 days. XF-1 has been deeply researched in control mechanisms, its genome, and development and application of biocontrol formulate. It could produce antagonistic protein, enzyme, antibiotics and IAA, which promoted rhizogenesis and growth. Its The genome was sequenced by Illumina/Solexa Genome Analyzer to assembled into 20 scaffolds then the gaps between scaffolds were filled by long fragment PCR amplification to obtain complet genmone with 4,061,186 bp in size. The whole genome was found to have 43.8% GC, 108 tandem repeats with an average of 2.65 copies and 84 transposons. The CDSs were predicted as 3,853 in which 112 CDSs were predicted to secondary metabolite biosynthesis, transport and catabolism. Among those, five NRPS/PKS giant gene clusters being responsible for the biosynthesis of polyketide (pksABCDEFHJLMNRS in size 72.9 kb), surfactin(srfABCD, 26.148 kb, bacilysin(bacABCDE 5.903 kb), bacillibactin(dhbABCEF, 11.774 kb) and fengycin(ppsABCDE, 37.799 kb) have high homolgous to fuction confirmed biosynthesis gene in other strain. Moreover, there are many of key regulatory genes for secondary metabolites from XF-1, such as comABPQKX Z, degQ, sfp, yczE, degU, ycxABCD and ywfG. were also predicted. Therefore, XF-1 has potential of biosynthesis for secondary metabolites surfactin, fengycin, bacillibactin, bacilysin and Bacillaene. Thirty two compounds were detected from cell extracts of XF-1 by MALDI-TOF-MS, including one Macrolactin (m/z 441.06), two fusaricidin (m/z 850.493 and 968.515), one circulocin (m/z 852.509), nine surfactin (m/z 1044.656~1102.652), five iturin (m/z 1096.631~1150.57) and forty fengycin (m/z 1449.79~1543.805). The top three compositions types (contening 56.67% of total extract) are surfactin, iturin and fengycin, in which the most abundant is the surfactin type composition 30.37% of total extract and in second place is the fengycin with 23.28% content with rich diversity of chemical structure, and the smallest one is the iturin with 3.02% content. Moreover, the same main compositions were detected in Bacillus sp.355 which is also a good effects biocontol bacterial for controlling the clubroot of crucifer. Wherefore those compounds surfactin, iturin and fengycin maybe the main active compositions of XF-1 against P. brassicae. Twenty one fengycin type compounds were evaluate by LC-ESI-MS/MS with antifungal activities, including fengycin A $C_{16{\sim}C19}$, fengycin B $C_{14{\sim}C17}$, fengycin C $C_{15{\sim}C18}$, fengycin D $C_{15{\sim}C18}$ and fengycin S $C_{15{\sim}C18}$. Furthermore, one novel compound was identified as Dehydroxyfengycin $C_{17}$ according its MS, 1D and 2D NMR spectral data, which molecular weight is 1488.8480 Da and formula $C_{75}H_{116}N_{12}O_{19}$. The fengycin type compounds (FTCPs $250{\mu}g/mL$) were used to treat the resting spores of P. brassicae ($10^7/mL$) by detecting leakage of the cytoplasm components and cell destruction. After 12 h treatment, the absorbencies at 260 nm (A260) and at 280 nm (A280) increased gradually to approaching the maximum of absorbance, accompanying the collapse of P. brassicae resting spores, and nearly no complete cells were observed at 24 h treatment. The results suggested that the cells could be lyzed by the FTCPs of XF-1, and the diversity of FTCPs was mainly attributed to a mechanism of clubroot disease biocontrol. In the five selected medium MOLP, PSA, LB, Landy and LD, the most suitable for growth of strain medium is MOLP, and the least for strains longevity is the Landy sucrose medium. However, the lipopeptide highest yield is in Landy sucrose medium. The lipopeptides in five medium were analyzed with HPLC, and the results showed that lipopeptides component were same, while their contents from B. subtilis XF-1 fermented in five medium were different. We found that it is the lipopeptides content but ingredients of XF-1 could be impacted by medium and lacking of nutrition seems promoting lipopeptides secretion from XF-1. The volatile components with inhibition fungal Cylindrocarpon spp. activity which were collect in sealed vesel were detected with metheds of HS-SPME-GC-MS in eight biocontrol Bacillus species and four positive mutant strains of XF-1 mutagenized with chemical mutagens, respectively. They have same main volatile components including pyrazine, aldehydes, oxazolidinone and sulfide which are composed of 91.62% in XF-1, in which, the most abundant is the pyrazine type composition with 47.03%, and in second place is the aldehydes with 23.84%, and the third place is oxazolidinone with 15.68%, and the smallest ones is the sulfide with 5.07%.

  • 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.