• Title/Summary/Keyword: multiple weights

Search Result 298, Processing Time 0.041 seconds

IoT Data Processing Model of Smart Farm Based on Machine Learning (머신러닝 기반 스마트팜의 IoT 데이터 처리 모델)

  • Yoon-Su, Jeong
    • Advanced Industrial SCIence
    • /
    • v.1 no.2
    • /
    • pp.24-29
    • /
    • 2022
  • Recently, smart farm research that applies IoT technology to various farms is being actively conducted to improve agricultural cooling power and minimize cost reduction. In particular, methods for automatically and remotely controlling environmental information data around smart farms through IoT devices are being studied. This paper proposes a processing model that can maintain an optimal growth environment by monitoring environmental information data collected from smart farms in real time based on machine learning. Since the proposed model uses machine learning technology, environmental information is grouped into multiple blockchains to enable continuous data collection through rich big data securing measures. In addition, the proposed model selectively (or binding) the collected environmental information data according to priority using weights and correlation indices. Finally, the proposed model allows us to extend the cost of processing environmental information to n-layer to a minimum so that we can process environmental information in real time.

Deep Learning-based Approach for Visitor Detection and Path Tracking to Enhance Safety in Indoor Cultural Facilities (실내 문화시설 안전을 위한 딥러닝 기반 방문객 검출 및 동선 추적에 관한 연구)

  • Wonseop Shin;Seungmin, Rho
    • Journal of Platform Technology
    • /
    • v.11 no.4
    • /
    • pp.3-12
    • /
    • 2023
  • In the post-COVID era, the importance of quarantine measures is greatly emphasized, and accordingly, research related to the detection of mask wearing conditions and prevention of other infectious diseases using deep learning is being conducted. However, research on the detection and tracking of visitors to cultural facilities to prevent the spread of diseases is equally important, so research on this should be conducted. In this paper, a convolutional neural network-based object detection model is trained through transfer learning using a pre-collected dataset. The weights of the trained detection model are then applied to a multi-object tracking model to monitor visitors. The visitor detection model demonstrates results with a precision of 96.3%, recall of 85.2%, and an F1-score of 90.4%. Quantitative results of the tracking model include a MOTA (Multiple Object Tracking Accuracy) of 65.6%, IDF1 (ID F1 Score) of 68.3%, and HOTA (Higher Order Tracking Accuracy) of 57.2%. Furthermore, a qualitative comparison with other multi-object tracking models showcased superior results for the model proposed in this paper. The research of this paper can be applied to the hygiene systems within cultural facilities in the post-COVID era.

  • PDF

Recommendation System Based on Correlation Analysis of User Behavior Data in Online Shopping Mall Environment (온라인 쇼핑몰 환경에서 사용자 행동 데이터의 상관관계 분석 기반 추천 시스템)

  • Yo Han Park;Jong Hyeok Mun;Jong Sun Choi;Jae Young Choi
    • KIPS Transactions on Computer and Communication Systems
    • /
    • v.13 no.1
    • /
    • pp.10-20
    • /
    • 2024
  • As the online commerce market continues to expand with an increase of diverse products and content, users find it challenging in navigating and in the selection process. Thereafter both platforms and shopping malls are actively working in conducting continuous research on recommendations system to select and present products that align with user preferences. Most existing recommendation studies have relied on user data which is relatively easy to obtain. However, these studies only use a single type of event and their reliance on time dependent data results in issues with reliability and complexity. To address these challenges, this paper proposes a recommendation system that analysis user preferences in consideration of the relationship between various types of event data. The proposed recommendation system analyzes the correlation of multiple events, extracts weights, learns the recommendation model, and provides recommendation services through it. Through extensive experiments the performance of our system was compared with the previously studied algorithms. The results confirmed an improvement in both complexity and performance.

Functional Screening for Cell Death Suppressors and Development of Multiple Stress-Tolerant Plants

  • Moon Hae-Jeong;Baek Dong-Won;Lee Ji-Young;Nam Jae-Sung;Yun Dae-Jin
    • Journal of Plant Biotechnology
    • /
    • v.5 no.3
    • /
    • pp.143-148
    • /
    • 2003
  • Bax, a mammalian pro-apoptotic member of the Bcl-2 family induces cell death when expressed in yeast. To investigate whether Bax expression can induce cell death in plant, we produced transgenic Arabidopsis plants that contained murine Bax cDNA under control of a glucocorticoid-inducible promoter. Transgenic plants treated with dexamethasone, a strong synthetic glucocorticoid, induced Bax accumulation and cell death, suggesting that some elements of cell death mechanism by Bax may be conserved among various organisms. Therefore, we developed novel yeast genetic system, and cloned several Plant Bax Inhibitors (PBIs). Here, we report the function of two PBIs in detail. PBI1 is ascorbate peroxidase (sAPX). Fluorescence method of dihydrorhodamine123 oxidation revealed that expression of Bax in yeast cells generated reactive oxygen species (ROS), and which was greatly reduced by co-expression with sAPX. These results suggest that sAPX inhibits the generation of ROS by Bax, which in turn suppresses Baxinduced cell death in yeast. PBI2 encodes nucleoside diphosphate kinase (NDPK). ROS stress strongly induces the expression of the NDPK2 gene in Arabidopsis thaliana (AtNDPK2). Transgenic plants overexpressing AtNDPK2 have lower levels of ROS than wildtype plants. Mutants lacking AtNDPK2 had higher levels of ROS than wildtype. $H_2O_2$ treatment induced the phosphorylation of two endogenous proteins whose molecular weights suggested they are AtMPK3 and AtMPK6. In the absence of $H_2O_2$ treatment, phosphorylation of these proteins was slightly elevated in plants overexpressing AtNDPK2 but markedly decreased in the AtNDPK2 deletion mutant. Yeast two-hybrid and in vitro protein pull-down assays revealed that AtNDPK2 specifically interacts with AtMPK3 and AtMPK6. Furthermore, AtNDPK2 also enhances the MSP phosphorylation activity of AtMPK3 in vitro. Finally, constitutive overexpression of AtNDPK2 in Arabidopsis plants conferred an enhanced tolerance to multiple environmental stresses that elicit ROS accumulation in situ. Thus, AtNDPK2 appears to playa novel regulatory role in $H_2O_2$-mediated MAPK signaling in plants.

A Study on BMI Regarding Life Style Related with Health of Middle School Students (중학생들의 건강 관련 생활습관에 따른 BMI 연구)

  • Lee, Chang-Hee;Ha, Hun-Yong;Kim, Hee-Taek;Kim, Nam-Song
    • The Journal of Korean Medicine Ophthalmology and Otolaryngology and Dermatology
    • /
    • v.25 no.1
    • /
    • pp.84-103
    • /
    • 2012
  • Objectives : The middle school students'life style were studied with focus on Body Mass Index(BMI). Information was collected during 1st June 2009 to 10th July from 397 students(both male and female) by the subjective survey centered on personal characteristic, understanding about health in general, everyday activities, eating habits, preference in food, understanding about diet and obesity, and thoughts about fitness and diet. Methods : Students were selected from six classes by convenience sampling, then the final analysis was performed on 397 self-administered questionnaires, excepting 5 questionnaires, which have insincere answers. The data collection was carried out by SPSS(V.14.0 English Version), and the data was verified by $x^2$-test, ANOVA, multiple regression analysis. Results and Conclusion : The survey subjects were in the following distribution of body weights - underweight: 63.6%, normal weight: 29.5% and 6.9% were overweight. There was significantly different between BMI and mothers' occupation and satisfaction with school life(p<0.05). As for the analysis(multiple regression analysis) on understanding about health, the factors that affect BMI are self recognition of figure and efforts to reduce weight. In terms of efforts for one's own health, 78.2% of under weight and 82.3% of normal weight were taking active initiatives. But 85.2% of the overweight students were not giving any efforts. As for the free time activities, more than half answered, 'playing with computers'(48.4 - 66.7%, 1.57 hours on average). As for TV, on average, 2.03 hours were spent in overall. And it turned out that the overweight students spent more time watching TV by 46.49 minutes(0.77 hours) on average(p<0.05). 7.4 hours was the average sleeping time. As for the eating habit,'quantity of meal, snack, meal between meals, fat reduction, and supplementary food'were shown to be related to the BMI(p<0.05). The instant food, meat and sweet food were shown to be also related to the BMI. In terms of knowledge about overweight and diet, only 8 students(2% of the total) answered all 10 questions correct. On average, 7-8 questions were correctly answered(53.9 %). When the scores were analyzed against the BMI by classifying the scores to high, middle and low categories, it showed a relationship by different weight group(p<0.02), and the overweight students had higher score by 0.82 compared to the underweight students. When thoughts and attitude on fitness and diet were analyzed in relationship to the BMI, the result was only - "I try to eat fruits more often"(fruits)(p<0.00).

Functional Screening for Cell Death Suppressors and Development of Multiple Stress-Tolerant Plants

  • Moon, Hae-Jeong;Baek, Dong-Won;Lee, Ji-Young;Nam, Jae-Sung;Yun, Dae-Jin
    • Proceedings of the Korean Society of Plant Biotechnology Conference
    • /
    • 2003.04a
    • /
    • pp.65-71
    • /
    • 2003
  • Bax, a mammalian pro-apoptotic member of the Bcl-2 family, induces cell death when expressed in yeast. To investigate whether Bax expression can induce cell death in plant, we produced transgenic Arabidopsis plants that contained murine Bax cDNA under control of a glucocorticoid-inducible promoter. Transgenic plants treated with dexamethasone, a strong synthetic glucocorticoid, induced Bax accumulation and cell death, suggesting that some elements of cell death mechanism by Bax may be conserved among various organisms. Therefore, we developed novel yeast genetic system, and cloned several Plant Bax Inhibitors (PBIs). Here, we report the function of two PBIs in detail. PBI1 is ascorbate peroxidase (sAPX). Fluorescence method of dihydrorho-damine 123 oxidation revealed that expression of Bax in yeast cells generated reactive oxygen species (ROS), and which was greatly reduced by co-expression with sAPX. These results suggest that sAPX inhibits the generation of ROS by Bax, which in turn suppresses Baxinduced cell death in yeast. PBI2 encodes nucleoside diphosphate kinase (NDPK). ROS stress strongly induces the expression of the NDPK2 gene in Arabidopsis thaliana (AtNDPK2). Transgenic plants overexpressing AtNDPK2 have lower levels of ROS than wildtype plants. Mutants lacking AtNDPK2 had higher levels of ROS than wildtype. $H_2O_2$ treatment induced the phosphorylation of two endogenous proteins whose molecular weights suggested they are AtMPK3 and AtMPK6. In the absence of $H_2O_2$ treatment, phosphorylation of these proteins was slightly elevated in plants overexpressing AtNDPK2 but markedly decreased in the AtNDPK2 deletion mutant. Yeast two-hybrid and in vitro protein pull-down assays revealed that AtNDPK2 specifically interacts with AtMPK3 and AtMPK6. Furthermore, AtNDPK2 also enhances the MBP phosphorylation activity of AtMPK3 in vitro. Finally, constitutive overexpression of AtNDPK2 in Arabidopsis plants conferred an enhanced tolerance to multiple environmental stresses that elicit ROS accumulation in situ. Thus, AtNDPK2 appears to play a novel regulatory role in $H_2O_2$-mediated MAPK signaling in plants.

  • PDF

Performance Improvement of Downlink Real-Time Traffic Transmission Using MIMO-OFDMA Systems Based on Beamforming (Beamforming 기반 MIMO-OFDMA 시스템을 이용한 하향링크 실시간 트래픽 전송 성능 개선)

  • Yang Suck-Chel;Park Dae-Jin;Shin Yo-An
    • Journal of the Institute of Electronics Engineers of Korea TC
    • /
    • v.43 no.3 s.345
    • /
    • pp.1-9
    • /
    • 2006
  • In this paper, we propose a MIMO-OFDMA (Multi Input Multi Output-Orthogonal Frequency Division Multiple Access) system based on beamforming for performance improvement of downlink real-time traffic transmission in harsh channel conditions with low CIR (Carrier-to-Interference Ratio). In the proposed system, we first consider the M-GTA-SBA (Modified-Grouped Transmit Antenna-Simple Bit Allocation) using effective CSI (Channel State Information) calculation procedure based on spatial resource grouping, which is adequate for the combination of MRT (Maximum Ratio Transmission) in the transmitter and MRC (Maximum Ratio Combining) in the receiver. In addition, to reduce feedback information for the beamforming, we also apply QEGT (Quantized Equal Gain Transmission) based on quantization of amplitudes and phases of beam weights. Furthermore, considering multi-user environments, we propose the P-SRA (Proposed-Simple Resource Allocation) algorithm for fair and efficient resource allocation. Simulation results reveal that the proposed MIMO-OFDMA system achieves significant improvement of spectral efficiency in low CRI region as compared to a typical open-loop MIMO-OFDMA system using pseudo-orthogonal space time block code and H-ARQ IR (Hybrid-Automatic Repeat Request Incremental Redundancy).

Performance Analysis of MVDR and RLS Beamforming Using Systolic Array Structure (시스토릭 어레이 구조를 갖는 최소분산 비왜곡응답 및 최소자승 회귀 빔형성기법 성능 분석)

  • 이호중;서상우;이원철
    • The Journal of the Acoustical Society of Korea
    • /
    • v.22 no.1
    • /
    • pp.1-6
    • /
    • 2003
  • This paper analyses the performance of either the minimum variance distortionless response (MVDR) or the recursive least square (RLS) beamformer structured on the systolic array. Provided that the snapshot vector including the desired user's signal and the interferences with the noise is received at the array antenna. In order to improve the quality of received signal, MVDR or RLS algorithm can be utilized to update the beamformer weights recursively. Furthermore to increase the channel capacity, by the usage of the above schemes, the effect of the spatial filtering can be obtained which constructively combining multipath components corresponding to the desired user whereas the multiple access interferences (MAI) is nulled out on spatial domain. This paper introduces the MVDR and RLS beamformer structured on systolic array conducting the spatial filtering, and its performance under the multipath fading channel in the presence of multiple access interferences will be analyzed. To show the superior spatial filtering performances of the proposed scheme employing the systolic way structured beamformer, the computer simulations are carried out. And the validity of practical deployment of the proposed scheme will be confirmed throughout showing the BER behaviors and the beampatterns.

A Korean Community-based Question Answering System Using Multiple Machine Learning Methods (다중 기계학습 방법을 이용한 한국어 커뮤니티 기반 질의-응답 시스템)

  • Kwon, Sunjae;Kim, Juae;Kang, Sangwoo;Seo, Jungyun
    • Journal of KIISE
    • /
    • v.43 no.10
    • /
    • pp.1085-1093
    • /
    • 2016
  • Community-based Question Answering system is a system which provides answers for each question from the documents uploaded on web communities. In order to enhance the capacity of question analysis, former methods have developed specific rules suitable for a target region or have applied machine learning to partial processes. However, these methods incur an excessive cost for expanding fields or lead to cases in which system is overfitted for a specific field. This paper proposes a multiple machine learning method which automates the overall process by adapting appropriate machine learning in each procedure for efficient processing of community-based Question Answering system. This system can be divided into question analysis part and answer selection part. The question analysis part consists of the question focus extractor, which analyzes the focused phrases in questions and uses conditional random fields, and the question type classifier, which classifies topics of questions and uses support vector machine. In the answer selection part, the we trains weights that are used by the similarity estimation models through an artificial neural network. Also these are a number of cases in which the results of morphological analysis are not reliable for the data uploaded on web communities. Therefore, we suggest a method that minimizes the impact of morphological analysis by using character features in the stage of question analysis. The proposed system outperforms the former system by showing a Mean Average Precision criteria of 0.765 and R-Precision criteria of 0.872.

Estimation of Genetic Correlations for the Growth and Carcass Traits in Hanwoo (한우의 성장형질과 도체형질에 대한 유전상관 추정)

  • Park, C.J.;Park, Y.I.
    • Journal of Animal Science and Technology
    • /
    • v.44 no.6
    • /
    • pp.685-692
    • /
    • 2002
  • This study was carried out to estimate the genetic correlations for the carcass and growth traits of Hanwoo bulls measured at 12 and 18 months of age on the basis of the data form 1,823 heads of Hanwoo bulls raised at the Livestock Improvement Main Center from 1991 to 1998. Genetic correlations were estimated with multiple trait animal model using MTDFREML. The genetic correlations of the body weight at 12 months with average daily gain during 6${\sim}$12 months and with the body length were 0.76 and 0.79, respectively. The genetic correlations of the body weight at 18 months with average daily gain during 6${\sim}$18 months and with the body length were 0.86 and 0.82, respectively. The genetic correlations of the carcass weight with dressing percent, eye muscle area, backfat thickness and carcass length were 0.39, 0.37, 0.44 and 0.63, respectively. And estimate of 0.36 was obtained for the genetic correlation between backfat thickness and marbling score. The high and positive genetic correlations of 0.71 and 0.96 were estimated for the carcass weight with the body weights at 12 and 18 months. The genetic correlations of the carcass weight with body lengths at 12 and 18 months were 0.63 and 0.75, respectively. Positive genetic correlations were estimated for the dressing percentage with the body weight, average daily gain, body length, thurls width and chest girth. Low genetic correlations were estimated between eye muscle area and the growth traits ranging from -0.07 to 0.32. Dressing percentage was low correlated genetically with the growth traits except for the chest girth at 18 months. The genetic correlation between marbling score and chest girth at 18 months estimated was 0.25.