• Title/Summary/Keyword: Contribution rate

Search Result 868, Processing Time 0.022 seconds

Vehicle Image Recognition Using Deep Convolution Neural Network and Compressed Dictionary Learning

  • Zhou, Yanyan
    • Journal of Information Processing Systems
    • /
    • v.17 no.2
    • /
    • pp.411-425
    • /
    • 2021
  • In this paper, a vehicle recognition algorithm based on deep convolutional neural network and compression dictionary is proposed. Firstly, the network structure of fine vehicle recognition based on convolutional neural network is introduced. Then, a vehicle recognition system based on multi-scale pyramid convolutional neural network is constructed. The contribution of different networks to the recognition results is adjusted by the adaptive fusion method that adjusts the network according to the recognition accuracy of a single network. The proportion of output in the network output of the entire multiscale network. Then, the compressed dictionary learning and the data dimension reduction are carried out using the effective block structure method combined with very sparse random projection matrix, which solves the computational complexity caused by high-dimensional features and shortens the dictionary learning time. Finally, the sparse representation classification method is used to realize vehicle type recognition. The experimental results show that the detection effect of the proposed algorithm is stable in sunny, cloudy and rainy weather, and it has strong adaptability to typical application scenarios such as occlusion and blurring, with an average recognition rate of more than 95%.

Industrial Process Monitoring and Fault Diagnosis Based on Temporal Attention Augmented Deep Network

  • Mu, Ke;Luo, Lin;Wang, Qiao;Mao, Fushun
    • Journal of Information Processing Systems
    • /
    • v.17 no.2
    • /
    • pp.242-252
    • /
    • 2021
  • Following the intuition that the local information in time instances is hardly incorporated into the posterior sequence in long short-term memory (LSTM), this paper proposes an attention augmented mechanism for fault diagnosis of the complex chemical process data. Unlike conventional fault diagnosis and classification methods, an attention mechanism layer architecture is introduced to detect and focus on local temporal information. The augmented deep network results preserve each local instance's importance and contribution and allow the interpretable feature representation and classification simultaneously. The comprehensive comparative analyses demonstrate that the developed model has a high-quality fault classification rate of 95.49%, on average. The results are comparable to those obtained using various other techniques for the Tennessee Eastman benchmark process.

Statistical characterisation of end milling of AISI 52100 annealed bearing steel

  • Benghersallah, Mohieddine;Benchiheub, Slimane;Amirat, Abdelaziz
    • Advances in materials Research
    • /
    • v.7 no.2
    • /
    • pp.137-148
    • /
    • 2018
  • The present paper is a contribution in characterising end milling process of AISI 52100 ball bearing steel through statistical analyses of variance (ANOVA). The latter has been performed to identify the effect of the cutting parameters on the machined surface roughness and the cutting tool life. Wear measurements have been carried on multilayer coated carbide inserts and the respective surface roughness has been recorded. Taguchi's technique has been adapted to conduct the design experiments in terms of orthogonal arrays according to the cutting parameters (cutting speed, feed rate and depth of cut), the type of coating (TiN, TiCN, TiAlN) and lubricating condition. Regression analyses have conducted to the development of simplified empirical models that can be effectively used to predict surface roughness and tool wear in the present milling process.

Spectroscopic Studies on the Interaction of N-alkyl Phenothiazines with Bovine Serum Albumin

  • Seetharamappa, J.;Shaikh, S.M.T;Kamat, B.P.
    • Journal of Photoscience
    • /
    • v.12 no.1
    • /
    • pp.25-32
    • /
    • 2005
  • Binding of N-Alkyl phenothiazines (NAP) to bovine serum albumin (BSA) was studied by spectroscopic methods.It was found that the phenothiazine ring common to all drugs makes major contribution to interaction. However, the nature of alkylamino group at position 10 influences the protein binding significantly. Stern-Volmer plots indicated the presence of static component in the quenching mechanism. The high magnitude of rate constant of quenching indicated that the process of energy transfer occurs by intermolecular interaction and thus the drug-binding site is in close proximity to tryptophan residues of BSA. Binding studies in presence of hydrophobic probe, 8-anilino-1-naphthalein-sulphonic acid showed that there is hydrophobic interaction between drug and the probe and they do not share common sites in BSA. Thermodynamic parameters obtained from data at different temperatures showed that the binding of NAP to BSA predominantly involve hydrophobic forces. The effects of some cations and anions common ions were investigated on NAP-BSA interactions. The CD spectrum of BSA in presence of drug showedthat binding of drug leads to change in the helicity of the protein.

  • PDF

Development of Prediction Model of Subcontract's Bidding-Ratio for Private Apartment Projects (민간 공동주택 하도급 낙찰률 예측모델 개발)

  • Jang, Ki-Suk;Koo, Kyo-Jin
    • Proceedings of the Korean Institute of Building Construction Conference
    • /
    • 2021.11a
    • /
    • pp.250-251
    • /
    • 2021
  • A subcontract work order is the basis of the construction process and consists of the root and trunk of the construction industry. The construction process through a subcontract work order is an important element of project success, and it is the basic unit of creating profit in the construction industry. Therefore, correct analysis and forecasting of subcontract work orders allow correct estimation of construction cost and profit which is the foundation of corporate decision making. This study has started to provide predictions of subcontractor's bidding-ratio for decision-making. Since the actual project data has been used in this study, the contribution level of the model is highly expected in actual field. The statistical confidential level of adjusted decision coefficient is concluded low because of limited sample numbers. However, its accuracy and confidence level can be increased through increasing sample numbers, considering more variables, and studying of reducing error.

  • PDF

Legal Implications of U.S. CVD on Tires and Undervalued Currency in the WTO's SCM

  • Thi Thanh Tuyen Nguyen;Xuan Zhou;Chang Hwan Choi
    • Journal of Korea Trade
    • /
    • v.27 no.5
    • /
    • pp.41-62
    • /
    • 2023
  • Purpose - This paper examines whether the imposition of countervailing duties by the United States on undervalued foreign currency is legally consistent with the WTO's SCM Agreement. Design/methodology - The study uses a methodology that involves analyzing relevant WTO agreements, prior panel reports, Appellate Body decisions, and other legal documents. Findings - The findings suggest that to impose countervailing duties, certain legal requirements must be met, including financial contribution, benefit, and specificity. The paper also notes that when calculating the benefits of undervalued foreign currency, losses from import activities due to currency undervaluation must be considered. Additionally, classifying all exports to the US under specific industries or business groups is likely to be inconsistent with the SCM Agreement. Originality/value - Even the US countervailing measures on exchange rate subsidies may not comply with WTO regulations due to incorrect calculation of benefits and a lack of specificity, however, it suggests that when intervening in the foreign exchange market, the measures should aim to achieve only minimum policy goals.

Smart Health Monitoring System (SHMS) An Enabling Technology for patient Care

  • Irfan Ali Kandhro;Asif Ali Wagan;Muhammad Abdul Aleem;Rasheeda Ali Hassan;Ali Abbas
    • International Journal of Computer Science & Network Security
    • /
    • v.24 no.3
    • /
    • pp.43-52
    • /
    • 2024
  • Health Monitoring System is a sophisticating technology and another way to the normal/regular management of the health of the patient. This Health Monitoring Mobile Application is a contribution from our side to the public and to the overall health industry in Pakistan. With the help of Health mobile application, the users will be able to store their medical records, prescriptions and retrieve them later. The users can store and keep track of their vital readings (heart rate, blood pressure, fasting glucose, random glucose). The mobile application also shows hospitals that are nearby in case the user wants to avail of any medical help. An important feature of the application is the symptoms-based disease prediction, the user selects the symptoms which he has and then the application will name certain diseases that match those symptoms based on relevant algorithms. The major advances and issues have been discussed, and as well as potential tasks to health monitoring will be identified and evaluated.

The Impact of Housing Prices and Private Education Costs on Fertility Rates

  • Clara Jungwon Choi;Jaehee Lee;Jinbaek Park
    • International Journal of Advanced Culture Technology
    • /
    • v.12 no.2
    • /
    • pp.62-71
    • /
    • 2024
  • The Study analyzed the effect of private education costs and housing prices on the total fertility rates in 16 metropolitan cities in Korea from 2009 to 2021, and estimated the contribution rates of each variable on the decrease in the total fertility rate. Using a dynamic panel data model considering the time series correlation of the total fertility rates, the total fertility rates for the year was positively (+) affected by the total fertility rates of the previous year, and the increase in apartment sales and Jeonse prices in the previous year reduced the total fertility rates. In addition, the increase in private education costs per capita in the previous year was analyzed to consistently reduce the total fertility rates.

Chemical Composition Characteristics of Dustfall in Nakdong River Area (낙동강 하류역 강하먼지의 화학적 조성 특성)

  • Jeon, Byung-Il;Hwang, Yong-Sik
    • Journal of the Korean earth science society
    • /
    • v.25 no.6
    • /
    • pp.428-442
    • /
    • 2004
  • Dustfall samples were collected by the modified American dust jar (bulk type) at 5 sampling sites in the Nakdong river area from lune 2002 to May 2003. Nineteen chemical species (Al, Ca, Cd, Cr, Cu, Fe, K, Mg, Mn, Na, Ni, Pb, Si, V, Zn, $Cl^-$, $NO_3^-$, $SO_4^{2-}$, and $NH_4^+$) were analyzed via the combination of ICP/AES, AAS, IC and UV. The purposes of this study were to qualitatively evaluate the chemical composition of dustfalls by examining their regional and seasonal distribution patterns. Computation of the enrichment factor showed that well-defined anthropogenic sources, particularly in Pb were found in the order Gamjeondong (industrial area), Wondong, Silla University, Samrangiin and Mulgum. The seasonal mean of soil contribution showed its highest value (16.3%) during the winter with an annual mean of 11.2%. The concentration ratio of [$SO_4^{2-}/NO_3^-$] was found to be highest (5.12) during the winter, while the lowest ratio value (3.30) was seen during the all. fall, Also regional equivalent ratios of [$SO_4^{2-}/NO_3^-$] were found in the order: Silla University (6.78), Gamjeondong (4.98), Mulgum (3.95), Wondong (3.85), and Samrangjin (2.87). Seasonal distribution of water soluble components for total dustfall were found in the order: spring (71.6%), summer (61.2%), fall (49.2%) and winter (48.6%) with a mean ratio of 57.6%. Regional contribution of sea salts of water soluble ions were found in the order: Silla university (34.5%), Gamjeondong (28.3%), Wondong (17.3%), Samrangiin (17.2%) and Mulgum (13.8%), the total mean contribution rate was 22.1%. As for the chemical composition of dustftll on the lower Nakdong river, there is a decreased influence of sea salt and artificial anthropogenic sources and increased influence of soil particle inland. Also, the total amount of deposition on the lower Nakdong river has decreased, with the river's surface serving as a confounding factor in resuspending dusts.

Factors Affecting the Participation Rate in the Health Screening Program of Medical Insurance (의료보험 성인병 건강검진율의 결정요인)

  • Youn, Sung-Tae;Jee, Sun-Ha;Suh, Il;Ohrr, Hee-Choul;Kim, Han-Joong
    • Journal of Preventive Medicine and Public Health
    • /
    • v.33 no.2
    • /
    • pp.150-156
    • /
    • 2000
  • Objective : To analyze the factors affecting the participation rate in the health screening program of medical insurance. Method : We investigated the factors associated with the participation rate in the health screening program in Korea. Data were collected at the aggregate level from 145 employee health insurance societies and 227 self-employed health insurance societies from 1995 to 1997 Data were also collected at the individual level from four health insurance societies. This study hypothesized that the participation rate of the health screening program was related to 1) the characteristics of its members and the size of the health insurance society; 2) the specifications of the health screening program; 3) the venue of the health screening institution and the interests of individuals in the health screening program; and 4) the activities of the health insurance society. We used bivariate and multiple regression models to examine the factors on the participation rate of the health screening program. Results : First, in the case of dependents of on employee health insurance society, the ratio of dependents 40 years old and over, the average monthly contribution per household, the interest and satisfaction level of individuals in health screening, and the level of refunds for over-payment were all associated with the participation rate in the health screening program, accounting for 54.4% of the participation rate. Second, in case of those insured by the self-employed health insurance society, the interest and satisfaction level of individuals in health screening, the level of refunds for over-payment, and the performance level of on-the-spot health screening were statistically significant, accounting for 40.1% of the participation rate. Conclusion : The factors concerning the participation rate in the health screening program of medical insurance, in both a health insurance society and for individuals, were closely related to the age and gender of individuals and household contributions.

  • PDF