A new unsupervised convolutional neural network model for Chinese scene text detection

As one of the most popular deep learning models, convolution neural network (CNN) has achieved huge success in image information extraction. Traditionally CNN is trained by supervised learning method with labeled data and used as a classifier by adding a classification layer in the end. Its capability of extracting image features is largely limited due to the difficulty of setting up a large training dataset. In this paper, we propose a new unsupervised learning CNN model, which uses a so-called convolutional sparse auto-encoder (CSAE) algorithm pre-Train the CNN. Instead of using labeled natural images for CNN training, the CSAE algorithm can be used to train the CNN with unlabeled artificial images, which enables easy expansion of training data and unsupervised learning. The CSAE algorithm is especially designed for extracting complex features from specific objects such as Chinese characters. After the features of articficial images are extracted by the CSAE algorithm, the learned parameters are used to initialize the first CNN convolutional layer, and then the CNN model is fine-Trained by scene image patches with a linear classifier. The new CNN model is applied to Chinese scene text detection and is evaluated with a multilingual image dataset, which labels Chinese, English and numerals texts separately. More than 10% detection precision gain is observed over two CNN models.

Biologically inspired features for scene classification in video surveillance

Inspired by human visual cognition mechanism, this paper first presents a scene classification method based on an improved standard model feature. Compared with state-of-the-art efforts in scene classification, the newly proposed method is more robust, more selective, and of lower complexity. These advantages are demonstrated by two sets of experiments on both our own database and standard public ones. Furthermore, occlusion and disorder problems in scene classification in video surveillance are also first studied in this paper. © 2010 IEEE.

Learning user and product distributed representations using a sequence model for sentiment analysis

In product reviews, it is observed that the distribution of polarity ratings over reviews written by different users or evaluated based on different products are often skewed in the real world. As such, incorporating user and product information would be helpful for the task of sentiment classification of reviews. However, existing approaches ignored the temporal nature of reviews posted by the same user or evaluated on the same product. We argue that the temporal relations of reviews might be potentially useful for learning user and product embedding and thus propose employing a sequence model to embed these temporal relations into user and product representations so as to improve the performance of document-level sentiment analysis. Specifically, we first learn a distributed representation of each review by a one-dimensional convolutional neural network. Then, taking these representations as pretrained vectors, we use a recurrent neural network with gated recurrent units to learn distributed representations of users and products. Finally, we feed the user, product and review representations into a machine learning classifier for sentiment classification. Our approach has been evaluated on three large-scale review datasets from the IMDB and Yelp. Experimental results show that: (1) sequence modeling for the purposes of distributed user and product representation learning can improve the performance of document-level sentiment classification; (2) the proposed approach achieves state-of-The-Art results on these benchmark datasets.

Neural Networks in Bankruptcy Prediction - A Comparative Study on the Basis of the First Hungarian Bankruptcy Model

The article attempts to answer the question whether or not the latest bankruptcy prediction techniques are more reliable than traditional mathematical–statistical ones in Hungary. Simulation experiments carried out on the database of the first Hungarian bankruptcy prediction model clearly prove that bankruptcy models built using artificial neural networks have higher classification accuracy than models created in the 1990s based on discriminant analysis and logistic regression analysis. The article presents the main results, analyses the reasons for the differences and presents constructive proposals concerning the further development of Hungarian bankruptcy prediction.

Application of support vector machines on the basis of the first Hungarian bankruptcy model

In our study we rely on a data mining procedure known as support vector machine (SVM) on the database of the first Hungarian bankruptcy model. The models constructed are then contrasted with the results of earlier bankruptcy models with the use of classification accuracy and the area under the ROC curve. In using the SVM technique, in addition to conventional kernel functions, we also examine the possibilities of applying the ANOVA kernel function and take a detailed look at data preparation tasks recommended in using the SVM method (handling of outliers). The results of the models assembled suggest that a significant improvement of classification accuracy can be achieved on the database of the first Hungarian bankruptcy model when using the SVM method as opposed to neural networks.

A közszolgálati szervezetek értékelési módszereinek osztályozása (Classification of evaluation methods of public sector organizations)

Az utóbbi évtizedekben egyre gyakrabban merült fel a közszolgálati szervezetek értékelésének igénye, és egyre újabb módszerek jelentek meg, amelyek felvetették ezek rendszerezésének szükségességét mind a gyakorlatban, mind a kutatásokban. A szerző a szakirodalomban fellelhető osztályozási kísérleteknek és az értékelés szakterülete szempontjainak figyelembevételével javaslatot tesz a közszolgálati szervezetek értékelési módszereinek osztályozási keretrendszerére. Az osztályozási szempontok között szerepel az értékelő helyzete, az értékelés szerepe és a megismerés módszere. Az osztályozási keretrendszer tartalmát a szerző példákkal is illusztrálja, amely jelzi a modell gyakorlati alkalmazhatóságát. Ugyanakkor a keretrendszer a kutatások fókuszának és érvényességi körének meghatározásában is segítséget nyújthat. _____ In the last decades the need of the evaluation of public sector organizations has emerged more and more often, and many new methods have shown up that has raised the need of their classification in practice and in research, as well. Based on literature review and the literature of evaluation the author makes a proposal on the classification framework of the evaluation methods of public sector organizations. The dimensions of the classification include the situation of evaluator, the role of evaluation and the approach of knowledge. The author illustrates the content of the framework with examples referring to the applicability of the model in practice. At the same time, the framework is also useful in determining the focus or the scope of research projects.

Gender differences in behavioral and psychosocial correlates of substance abuse among adolescents in residential treatment

This dissertation reports the results of a study that examined differences between genders in a sample of adolescents from a residential substance abuse treatment facility. The sample included 72 males and 65 females, ages 12 through 17. The data were archival, having been originally collected for a study of elopement from treatment. The current study included 23 variables. The variables were from multiple dimensions, including socioeconomic, legal, school, family, substance abuse, psychological, social support, and treatment histories. Collectively, they provided information about problem behaviors and psychosocial problems that are correlates of adolescent substance abuse. The study hypothesized that these problem behaviors and psychosocial problems exist in different patterns and combinations between genders.^ Further, it expected that these patterns and combinations would constitute profiles important for treatment. K-means cluster analysis identified differential profiles between genders in all three areas: problem behaviors, psychosocial problems, and treatment profiles. In the dimension of problem behaviors, the predominantly female group was characterized as suicidal and destructive, while the predominantly male group was identified as aggressive and low achieving. In the dimension of psychosocial problems, the predominantly female group was characterized as abused depressives, while the male group was identified as asocial, low problem severity. A third group, neither predominantly female or male, was characterized as social, high problem severity. When these dimensions were combined to form treatment profiles, the predominantly female group was characterized as abused, self-harmful, and social, and the male group was identified as aggressive, destructive, low achieving, and asocial. Finally, logistic regression and discriminant analysis were used to determine whether a history of sexual and physical abuse impacted problem behavior differentially between genders. Sexual abuse had a substantially greater influence in producing self-mutilating and suicidal behavior among females than among males. Additionally, a model including sexual abuse, physical abuse, low family support, and low support from friends showed a moderate capacity to predict unusual harmful behavior (fire-starting and cruelty to animals) among males. Implications for social work practice, social work research, and systems science are discussed. ^

Private higher education policy in Ohio, 1980--2006: A case study demonstrating the usefulness of Zumeta's public policy posture model

This study describes the case of private higher education in Ohio between 1980 and 2006 using Zumeta's (1996) model of state policy and private higher education. More specifically, this study used case study methodology and multiple sources to demonstrate the usefulness of Zumeta's model and illustrate its limitations. Ohio served as the subject state and data for 67 private, 4-year, degree-granting, Higher Learning Commission-accredited institutions were collected. Data sources for this study included the National Center for Education Statistics Integrated Postsecondary Data System as well as database information and documents from various state agencies in Ohio, including the Ohio Board of Regents. ^ The findings of this study indicated that the general state context for higher education in Ohio during the study time period was shaped by deteriorating economic factors, stagnating population growth coupled with a rapidly aging society, fluctuating state income and increasing expenditures in areas such as corrections, transportation and social services. However, private higher education experienced consistent enrollment growth, an increase in the number of institutions, widening involvement in state-wide planning for higher education, and greater fiscal support from the state in a variety of forms such as the Ohio Choice Grant. This study also demonstrated that private higher education in Ohio benefited because of its inclusion in state-wide planning and the state's decision to grant state aid directly to students. ^ Taken together, this study supported Zumeta's (1996) classification of Ohio as having a hybrid market-competitive/central-planning policy posture toward private higher education. Furthermore, this study demonstrated that Zumeta's model is a useful tool for both policy makers and researchers for understanding a state's relationship to its private higher education sector. However, this study also demonstrated that Zumeta's model is less useful when applied over an extended time period. Additionally, this study identifies a further limitation of Zumeta's model resulting from his failure to define "state mandate" and the "level of state mandates" that allows for inconsistent analysis of this component. ^

A gender study investigating physics self-efficacy

The underrepresentation of women in physics has been well documented and a source of concern for both policy makers and educators. My dissertation focuses on understanding the role self-efficacy plays in retaining students, particularly women, in introductory physics. I use an explanatory mixed methods approach to first investigate quantitatively the influence of self-efficacy in predicting success and then to qualitatively explore the development of self-efficacy. In the initial quantitative studies, I explore the utility of self-efficacy in predicting the success of introductory physics students, both women and men. Results indicate that self-efficacy is a significant predictor of success for all students. I then disaggregate the data to examine how self-efficacy develops differently for women and men in the introductory physics course. Results show women rely on different sources of self-efficacy than do men, and that a particular instructional environment, Modeling Instruction, has a positive impact on these sources of self-efficacy. In the qualitative phase of the project, this dissertation focuses on the development of self-efficacy. Using the qualitative tool of microanalysis, I introduce a methodology for understanding how self-efficacy develops moment-by-moment using the lens of self-efficacy opportunities. I then use the characterizations of self-efficacy opportunities to focus on a particular course environment and to identify and describe a mechanism by which Modeling Instruction impacts student self-efficacy. Results indicate that the emphasizing the development and deployment of models affords opportunities to impact self-efficacy. The findings of this dissertation indicate that introducing key elements into the classroom, such as cooperative group work, model development and deployment, and interaction with the instructor, create a mechanism by which instructors can impact the self-efficacy of their students. Results from this study indicate that creating a model to impact the retention rates of women in physics should include attending to self-efficacy and designing activities in the classroom that create self-efficacy opportunities.

Quality of life and application of the transtheoretical model to diabetes self -management behaviors in older adults with type 2 diabetes

One in five adults 65 years and older has diabetes. Coping with diabetes is a lifelong task, and much of the responsibility for managing the disease falls upon the individual. Reports of non-adherence to recommended treatments are high. Understanding the additive impact of diabetes on quality of life issues is important. The purpose of this study was to investigate the quality of life and diabetes self-management behaviors in ethnically diverse older adults with type 2 diabetes. The SF-12v2 was used to measure physical and mental health quality of life. Scores were compared to general, age sub-groups, and diabetes-specific norms. The Transtheoretical Model (TTM) was applied to assess perceived versus actual behavior for three diabetes self-management tasks: dietary management, medication management, and blood glucose self-monitoring. Dietary intake and hemoglobin A1c values were measured as outcome variables. Utilizing a cross-sectional research design, participants were recruited from Elderly Nutrition Program congregate meal sites (n = 148, mean age 75). ^ Results showed that mean scores of the SF-12v2 were significantly lower in the study sample than the general norms for physical health (p < .001), mental health (p < .01), age sub-group norms (p < .05), and diabetes-specific norms for physical health (p < .001). A multiple regression analysis found that adherence to an exercise plan was significantly associated with better physical health (p < .001). Transtheoretical Model multiple regression analyses explained 68% of the variance for % Kcal from fat, 41% for fiber, 70% for % Kcal from carbohydrate, and 7% for hemoglobin A 1c values. Significant associations were found between TTM stage of change and dietary fiber intake (p < .01). Other significant associations related to diet included gender (p < .01), ethnicity (p < .05), employment (p < .05), type of insurance (p < .05), adherence to an exercise plan (p < .05), number of doctor visits/year ( p < .01), and physical health (p < .05). Significant associations were found between hemoglobin A1c values and age ( p < .05), being non-Hispanic Black (p < .01), income (p < .01), and eye problems (p < .05). ^ The study highlights the importance of the beneficial effects of exercise on quality of life issues. Furthermore, application of the Transtheoretical Model in conjunction with an assessment of dietary intake may be valuable in helping individuals make lifestyle changes. ^

A model of self -transformative identity development in troubled adolescent youth

Within the Stage II program evaluation of the Miami Youth Development Project's (YDP) Changing Lives Program (CLP), this study evaluated CLP intervention effectiveness in promoting positive change in emotion-focused identity exploration (i.e. feelings of personal expressiveness; PE) and a "negative" symptom of identity development (i.e. identity distress; ID) as a first step toward the investigation of a self-transformative model of identity development in adolescent youth. Using structural equation modeling techniques, this study found that participation in the CLP is associated with positive changes in PE (path = .841, p < .002), but not changes in ID. Increase in ID scores was found to be associated with increases in PE (path = .229, p < .002), as well. Intervention effects were not moderated by age/stage, gender, or ethnicity, though differences were found in the degree to which participating subgroups (African-American/Hispanic, male/female, 14-16 years old/17-19 years old) experience change in PE and ID. Findings also suggest that moderate levels of ID may not be deleterious to identity exploration and may be associated with active exploration. ^

The influence of gender on perceived treatment need among a community sample of substance users

Purpose: Most individuals do not perceive a need for substance use treatment despite meeting diagnostic criteria for substance use disorders and they are least likely to pursue treatment voluntarily. There are also those who perceive a need for treatment and yet do not pursue it. This study aimed to understand which factors increase the likelihood of perceiving a need for treatment for individuals who meet diagnostic criteria for substance use disorders in the hopes to better assist with more targeted efforts for gender-specific treatment recruitment and retention. Using Andersen and Newman's (1973/2005) model of individual determinants of healthcare utilization, the central hypothesis of the study was that gender moderates the relationship between substance use problem severity and perceived treatment need, so that women with increasing problems due to their use of substances are more likely than men to perceive a need for treatment. Additional predisposing and enabling factors from Andersen and Newman's (1973/2005) model were included in the study to understand their impact on perceived need. Method: The study was a secondary data analysis of the 2010 National Survey on Drug Use and Health (NSDUH) using logistic regression. The weighted sample consisted of a total 20,077,235 American household residents (The unweighted sample was 5,484 participants). Results of the logistic regression were verified using Relogit software for rare events logistic regression due to the rare event of perceived treatment need (King & Zeng, 2001a; 2001b). Results: The moderating effect of female gender was not found. Conversely, men were significantly more likely than women to perceive a need for treatment as substance use problem severity increased. The study also found that a number of factors such as race, ethnicity, socioeconomic status, age, marital status, education, co-occurring mental health disorders, and prior treatment history differently impacted the likelihood of perceiving a need for treatment among men and women. Conclusion: Perceived treatment need among individuals who meet criteria for substance use disorders is rare, but identifying factors associated with an increased likelihood of perceiving need for treatment can help the development of gender-appropriate outreach and recruitment for social work treatment, and public health messages.

Influence of gender and life stressors on longitudinal depression treatment outcomes among older primary care patients

Purpose: Depression in older females is a significant and growing problem. Females who experience life stressors across the life span are at higher risk for developing problems with depression than their male counterparts. The primary aim of this study was (a) to examine gender-specific differences in the correlates of depression in older primary care patients based on baseline and longitudinal analyses; and (b) to examine the longitudinal effect of biopsychosocial risk factors on depression treatment outcomes in different models of behavioral healthcare (i.e., integrated care and enhanced referral). Method: This study used a quantitative secondary data analysis with longitudinal data from the Primary Care Research in Substance Abuse and Mental Health for Elderly (PRISM-E) study. A linear mixed model approach to hierarchical linear modeling was used for analysis using baseline assessment, and follow-up from three-month and six-month. Results: For participants diagnosed with major depressive disorder female gender was associated with increased depression severity at six-month compared to males at six-month. Further, the interaction between gender and life stressors found that females who reported loss of family and friends, family issues, money issues, medical illness was related to higher depression severity compared to males whereas lack of activities was related to lower depression severity among females compared to males. Conclusion: These findings suggest that gender moderated the relationship between specific life stressors and depression severity similar to how a protective factor can impact a person's response to a problem and reduce the negative impact of a risk factor on a problem outcome. Therefore, life stressors may be a reliable predictor of depression for both females and males in either behavioral health treatment model. This study concluded that life stressors influence males basic comfort, stability, and survival whereas life stressors influence females' development, personal growth, and happiness; therefore, life stressors may be a useful component to include in gender-based screening and assessment tools for depression. ^

Consulting Services to Determine the Effectiveness of Vegetation Classification Using WorldView 2 Satellite Data for the Greater Everglades

The purpose of this project was to evaluate the use of remote sensing 1) to detect and map Everglades wetland plant communities at different scales; and 2) to compare map products delineated and resampled at various scales with the intent to quantify and describe the quantitative and qualitative differences between such products. We evaluated data provided by Digital Globe’s WorldView 2 (WV2) sensor with a spatial resolution of 2m and data from Landsat’s Thematic and Enhanced Thematic Mapper (TM and ETM+) sensors with a spatial resolution of 30m. We were also interested in the comparability and scalability of products derived from these data sources. The adequacy of each data set to map wetland plant communities was evaluated utilizing two metrics: 1) model-based accuracy estimates of the classification procedures; and 2) design-based post-classification accuracy estimates of derived maps.

A model of self-transformative identity development in troubled adolescent youth

Within the Stage II program evaluation of the Miami Youth Development Project's (YDP) Changing Lives Program (CLP), this study evaluated CLP intervention effectiveness in promoting positive change in emotion-focused identity exploration (i.e. feelings of personal expressiveness; PE) and a "negative" symptom of identity development (i.e. identity distress; ID) as a first step toward the investigation of a self-transformative model of identity development in adolescent youth. Using structural equation modeling techniques, this study found that participation in the CLP is associated with positive changes in PE (path = .841, p < .002), but not changes in ID. Increase in ID scores was found to be associated with increases in PE (path = .229, p < .002), as well. Intervention effects were not moderated by age/stage, gender, or ethnicity, though differences were found in the degree to which participating subgroups (African- American/Hispanic, male/female, 14-16 years old/17-19 years old) experience change in PE and ID. Findings also suggest that moderate levels of ID may not be deleterious to identity exploration and may be associated with active exploration.