Sparse deep feature learning for facial expression recognition
یادگیری ویژگی های عمیق پراکنده برای تشخیص چهره صورت-2019
While weight sparseness-based regularization has been used to learn better deep features for image recognition problems, it introduced a large number of variables for optimization and can easily con- verge to a local optimum. The L2-norm regularization proposed for face recognition reduces the impact of the noisy information, while expression information is also suppressed during the regularization. A feature sparseness-based regularization that learns deep features with better generalization capability is proposed in this paper. The regularization is integrated into the loss function and optimized with a deep metric learning framework. Through a toy example, it is showed that a simple network with the proposed sparseness outperforms the one with the L2-norm regularization. Furthermore, the proposed approach achieved competitive performances on four publicly available datasets, i.e., FER2013, CK + , Oulu-CASIA and MMI. The state-of-the-art cross-database performances also justify the generalization capability of the proposed approach.
Keywords: Expression recognition | Feature sparseness | Deep metric learning | Fine tuning | Generalization capability
A generalizable deep learning framework for localizing and characterizing acoustic emission sources in riveted metallic panels
یک چارچوب یادگیری عمیق قابل تعمیم برای محلی سازی و توصیف منابع انتشار صوتی در پانل های فلزی پرچین-2019
This paper introduces a deep learning-based framework to localize and characterize acoustic emission (AE) sources in plate-like structures that have complex geometric features, such as doublers and rivet connections. Specifically, stacked autoencoders are pre-trained and utilized in a two-step approach that first localizes AE sources and then characterizes them. To achieve these tasks with only one AE sensor, the paper leverages the reverberation patterns, multimodal characteristics, and dispersive behavior of AE waveforms. The considered waveforms include AE sources near rivet connections, on the surface of the plate-like structure, and on its edges. After identifying AE sources that occur near rivet connections, the proposed framework classifies them into four source-to-rivet distance categories. In addition, the paper investigates the sensitivity of localization results to the number of sensors and compares their localization accuracy with the triangulation method as well as machine learning algorithms, including support vector machine (SVM) and shallow neural network. Moreover, the generalization of the deep learning approach is evaluated for typical scenarios in which the training and testing conditions are not identical. To train and test the performance of the proposed approach, Hsu-Nielsen pencil lead break tests were carried out on two identical aluminum panels with a riveted stiffener. The results demonstrate the effectiveness of the deep learning-based framework for singlesensor, AE-based structural health monitoring of plate-like structures.
Keywords: Acoustic emission | Deep learning | Edge reflection | Reverberation patterns | Plate-like structures | Pattern recognition | Stacked autoencoders | Guided ultrasonic waves | Machine learning | Structural health monitoring
A comprehensive survey of edge prediction in social networks: Techniques, parameters and challenges
مرور جامع پیش بینی لبه ها در شبکه های اجتماعی: تکنیک ها ، پارامترها و چالش ها-2019
Recent development in the area of social networks has sought attention of the researchers to crunch and analyse the data and information of the users to retrieve relevant knowledge for further predictions and recommendations. Edge prediction is one such instance of social network analysis problem exploiting the prevailing data and information pertaining to the network such as: the attributes of the nodes and edges connecting the nodes in order to predict relationships potentially likely to exist in near future. Edge prediction has various applications in significant areas such as: knowledge mining, business recommen- dation systems, expert systems and bio informatics. In this work, we have classified the edge prediction problem in social network from five aspects: type of SN, feature used for edge prediction, edge prediction method, solution to edge prediction problem and performance measure. The strength of this article is the categorical review of the edge prediction methods in way to draw specific research problems to address further such as: complexity, accuracy, computational overhead and cost, scalability, generalization and performance issues. In addition to this, we have also provided an insightful of edge prediction method applied across various social network categories to understand the advantages and disadvantages to de- rive future work. The experimental exercise on real world social network particularly Face-book exhibits that the computation time taken in processing large network could be improved significantly may be through distributed techniques or so as the performance of edge prediction methods degrades with the scalability of the social networks. We did not focused upon any appropriate edge prediction methodology as it is out of the scope of the paper because we have exclusively reviewed the existing work done and we are exploring an appropriate ensemble method to precisely predict the future edges between nodes.
Keywords: Social network | Edge prediction methods | Complexity | Accuracy | Computational overhead and cost | Scalability | Generalization
Understanding gastronomic image from tourists’ perspective: A repertory grid approach
درک وجهه غذایی از دیدگاه گردشگران: یک دیدگاه شبکه مخزن-2018
Gastronomic image (GI) has increasingly been recognized as a valuable and inimitable source of competitive advantage by many destinations. However, little is known as to what attributes constitute GI, especially from tourists’ perspective. This study attempts to explore the salient attributes and dimensions of GI through the repertory grid method and generalized Procrustes analysis. Based on 50 repertory grid interviews with international tourists visiting Taiwan, a total of 46 GI attributes were identified. These attributes were classified into seven categories, namely, attractiveness, flavor profile, familiarity, cooking method and ingredients, distinctiveness, convenience and price, and health and safety. The findings provide useful insights for practice and serve as the basis for future research in the field of GI.
keywords: Gastronomic image |Repertory grid method |Generalized procrustes analysis |Triadic elicitation technique
یک تعمیم از تاثیر جام جهانی فوتبال
سال انتشار: 2018 - تعداد صفحات فایل pdf انگلیسی: 3 - تعداد صفحات فایل doc فارسی: 6
هدف این مقاله بررسی تاثیر پیروزی تیم ملی فوتبال در جام جهانی روی موفقیت گردشگری آن کشور می باشد. برای بررسی تعمیم نتایج تجربی یافت شده تاکنون، چهار دوره با داده های موجود از دهه 90 تحلیل می شوند. نتیجه گیری نشان می دهد که به استثنای دوره 2010 هیچ تاثیر قابل توجه تعمیم یافته ای شناسایی نشده است.
کلمات کلیدی: جام جهانی فیفا | بازار سهام | دانش برند | تصویر
|مقاله ترجمه شده|
Modeling generalized interline power-flow controller (GIPFC) using 48-pulse voltage source converters
مدلسازی کنترل کننده جریان توانی درون خطی تعمیم یافته با استفاده از مبدل های منبع ولتاژ 48 پالسی-2018
Generalized interline power-flow controller (GIPFC) is one of the voltage-source controller (VSC)-based flexible AC transmission system (FACTS) controllers that can independently regulate the power-flow over each transmission line of a multiline system. This paper presents the modeling and performance analysis of GIPFC based on 48-pulsed voltage-source converters. This paper deals with a cascaded multilevel converter model, which is a 48-pulse (three levels) voltage source converter. The voltage source converter described in this paper is a harmonic neutralized, 48-pulse GTO converter. The GIPFC controller is based on d-q orthogonal coordinates. The algorithm is verified using simulations in MATLAB/Simulink environment. Comparisons between unified power flow controller (UPFC) and GIPFC are also included.
keywords: Generalized interline power-flow controller (GIPFC) |Voltage source converter (VCS) |48-pulse GTO converter
A generalization of the FIFA World Cup effect
یک تعمیم برای تاثیر جام جهانی فوتبال-2018
The objective of this article is to explore the effect of the national soccer teams victory in the FIFA World Cup on the winning countrys tourism. To test the generalization of the empirical results found so far, the four editions with available data since the 90s are analyzed. The conclusion shows that no generalized significant effect is identified, with the exception of the 2010 edition.
keywords: FIFA World Cup |Stock market |Brand knowledge |Image
Bankruptcy prediction models generalizability: Evidence from emerging market economies
تعمیم پذیری مدلهای پیش بینی ورشکستگی: شواهدی از اقتصاد بازارهای نوظهور-2018
Dealing with endogeneity bias: The generalized method of moments (GMM) for panel data
سروکار داشتن با انحراف درون زا: روش تعمیم یافته لحظه ها برای داده های پنلی-2018
Endogeneity bias can lead to inconsistent estimates and incorrect inferences, which may provide misleading conclusions and inappropriate theoretical interpretations. Sometimes, such bias can even lead to coefficients having the wrong sign. Although this is a long-standing issue, it is now emerging in marketing and management science, with high-ranked journals increasingly exploring the issue. In this paper, we methodologically demonstrate how to detect and deal with endogeneity issues in panel data. For illustration purposes, we used a dataset consisting of observations over a 15-year period (i.e., 2002 to 2016) from 101 UK listed companies and examined the direct effect of R&D expenditures, corporate governance, and firms characteristics on performance. Due to endogeneity bias, the result of our analyses indicates significant differences in findings reported under the ordinary least square (OLS) approach, fixed effects and the generalized method of moments (GMM) estimations. We also provide generic STATA commands that can be utilized by marketing researchers in implementing a GMM model that better controls for the three sources of endogeneity, namely, unobserved heterogeneity, simultaneity and dynamic endogeneity.
keywords: Endogeneity bias |Generalized method of moments |Methodological issues |Panel data
Downside risks and the cross-section of asset returns
خطرات پایین دست و سطح مقطع بازگشت های دارایی-2018
In an intertemporal equilibrium asset pricing model featuring disappointment aversion and changing macroeconomic uncertainty, we show that besides the market return and market volatility, three disappointment-related factors are also priced: a downstate factor, a market downside factor, and a volatility downside factor. We find that expected returns on various asset classes reflect premiums for bearing undesirable exposures to these factors. The signs of estimated risk premiums are consistent with the theoretical predictions. Our most general, five-factor model is very successful in jointly pricing stock, option, and currency portfolios, and provides considerable improvement over nested specifications previously discussed in the literature.
keywords: Generalized disappointment aversion |Downside risks |Cross-section