Dissertations / Theses on the topic 'Symptom recognition'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 35 dissertations / theses for your research on the topic 'Symptom recognition.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Kennedy, Michael G. "Relapse in Schizophrenia : the relationships among insight, symptom recognition, symptom self-management, and perceived effectiveness of symptom self-management at the time of hospitalization /." Thesis, Connect to this title online; UW restricted, 1994. http://hdl.handle.net/1773/7372.
Full textHull, Carolyn M., and Carolyn M. Hull. "Assessing the Impact of a Transitional Care Program on Symptom Recognition and Self-care in Heart Failure Patients." Diss., The University of Arizona, 2017. http://hdl.handle.net/10150/622989.
Full textLim, Anita Wey Wey. "Investigating the potential for expediting diagnosis of ovarian cancer via prompt symptom recognition & "targeted screening"." Thesis, Queen Mary, University of London, 2009. http://qmro.qmul.ac.uk/xmlui/handle/123456789/500.
Full textWalsh, Susan A. "The Effects of Pattern Recognition Based Simulation Scenarios on Symptom Recognition of Myocardial Infarction, Critical Thinking, Clinical Decision-Making, and Clinical Judgment in Nursing Students." Digital Archive @ GSU, 2010. http://digitalarchive.gsu.edu/nursing_diss/18.
Full textFarmer, Caroline. "Understanding poor help-seeking rates for major depressive disorder." Thesis, University of Exeter, 2013. http://hdl.handle.net/10871/14620.
Full textTsanas, Athanasios. "Accurate telemonitoring of Parkinson's disease symptom severity using nonlinear speech signal processing and statistical machine learning." Thesis, University of Oxford, 2012. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.572585.
Full textFriedman, Karen Blanc Spiers Mary. "Are symptoms of postpartum depression associated with deficits in facial and auditory emotional recognition? /." Philadelphia, Pa. : Drexel University, 2008. http://hdl.handle.net/1860/2828.
Full textHorsley, John Robert. "Respiratory symptoms in the elderly and their clinical significance in the recognition of asthma." Thesis, University of Southampton, 1990. https://eprints.soton.ac.uk/421960/.
Full textLee, Brian N. "Facial Expression Discrimination in Adults Experiencing Posttraumatic Stress Symptoms." TopSCHOLAR®, 2011. http://digitalcommons.wku.edu/theses/1123.
Full textSink, Holli E. "Distinguishing Subtypes of Psychopathy in Youth based on Anxiety, Posttraumatic Stress Symptoms, and Emotion Recognition." Miami University / OhioLINK, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=miami1279481371.
Full textWarren, Vicki J. "Recognition of Facial Expression of Emotion by Persons with Metal Retardation and Symptoms of Depression." The Ohio State University, 1991. http://rave.ohiolink.edu/etdc/view?acc_num=osu1381495185.
Full textWarren, Vicki J. "Recognition of facial expression of emotion by persons with mental retardation and symptoms of depression /." The Ohio State University, 1991. http://rave.ohiolink.edu/etdc/view?acc_num=osu148775943632696.
Full textMotan, Irem. "Recognition Of Self Conscious Emotions In Relation To Psychopathology." Phd thesis, METU, 2007. http://etd.lib.metu.edu.tr/upload/12609222/index.pdf.
Full textrecognition and their relation to psychopathology are meant to be discussed. To achieve aforementioned goals, the study is partitioned into three separate but interdependent phases. The aim of the study is scale adaptation for which the State Shame and Guilt Scale, Test of Self-Conscious Affect-3, Guilt- Shame Scale, State-Trait Anxiety Inventory, and Beck Depression Inventory are applied to a group of 250 university students. The second study&rsquo
s objective is to determine the nonverbal expressions used in recognition of self-conscious emotions. To meet this goal, 5 TAT cards, whose compatibility with the research questions is verified, are applied to 45 university students in separate sessions by using close ended questions. In the third part of the study, 9 TAT cards, which include clues about recognition and nonverbal expressions of self-conscious emotions, adapted corresponding scales, and a psychopathological symptoms measuring scale (SCL-90) in self-report format are applied on a group of 250 university students. Factor and correlation analyses done in the first part reveal that adapted scales are reliable and valid, while group comparisons and measurements of the second part indicate differences in emotions. Findings reveal that shame can be recognized by nonverbal expressions whereas for guilt contextual clues are facilitated. In the third part, group comparisons and regression analyses, which are done in order to reveal self-conscious emotions&rsquo
recognition and their significant relationships with psychopathology, display that state self-conscious emotions and shame-proneness have very important roles on psychopathology. All these findings are discussed in the light of cultural effects.
Fuks, Geddes Czesia. "How do adolescents define depression? Links with depressive symptoms, self-recognition of depression, and social and emotional competence." Thesis, University of British Columbia, 2008. http://hdl.handle.net/2429/1053.
Full textDaly, England Mary Ann, and England Mary Ann Daly. "Development of a Cardiac Prodromal Symptoms Recognition List for the Assessment of Women in Primary Care." Diss., The University of Arizona, 2016. http://hdl.handle.net/10150/621826.
Full textÖzgürdal, Seza, Haren Elisabeth van, Marta Hauser, Andreas Ströhle, Michael Bauer, Hans-Jörg Assion, and Georg Juckel. "Early Mood Swings as Symptoms of the Bipolar Prodrome: Preliminary Results of a Retrospective Analysis." Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2014. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-134197.
Full textGombojav, Narangerel. "Sympton-recognition, health service-seeking behaviour and the management of acute respiratory infection in infants in urban Mongolia." Thesis, University of the West of England, Bristol, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.445111.
Full textMadison, Annelise Alissa. "Social Anxiety Symptoms, Heart Rate Variability, and Vocal Emotion Recognition: Evidence of a Normative Vagally-Mediated Positivity Bias in Women." The Ohio State University, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=osu15582676377176.
Full textÖzgürdal, Seza, Haren Elisabeth van, Marta Hauser, Andreas Ströhle, Michael Bauer, Hans-Jörg Assion, and Georg Juckel. "Early Mood Swings as Symptoms of the Bipolar Prodrome: Preliminary Results of a Retrospective Analysis." Karger, 2009. https://tud.qucosa.de/id/qucosa%3A27567.
Full textStephens, Victoria Clare. "Effects on depressive symptoms of a Web-based Cognitive Bias Modification-Interpretation (CBM-I) program for emotion recognition : a randomised controlled trial." Thesis, University of Exeter, 2014. http://hdl.handle.net/10871/16430.
Full textAka, Turkuler B. "Perceived Parenting Styles, Emotion Recognition, And Emotion Regulation In Relation To Psychological Well-being: Symptoms Of Depression, Obsessive-compulsive Disorder, And Social Anxiety." Phd thesis, METU, 2011. http://etd.lib.metu.edu.tr/upload/12613378/index.pdf.
Full textReading the Mind in the Eyes&rdquo
Test (Revised), Emotion Regulation Questionnaire, Emotion Regulation Processes, Beck Depression Inventory, Liebowitz Social Anxiety Scale, Maudsley Obsessive Compulsive Inventory, White Bear Suppression Inventory, Thought-Action Fusion Scale, and Emotional Approach Coping Scale. The psychometric properties of Emotion Regulation Questionnaire and Emotion Regulation Processes were investigated and found to have good validity and reliability characteristics. The three sets of hierarchical multiple regression analyses were conducted to reveal the significant associates of psychological well-being. As expected, the results of the current study revealed that perceived parenting styles, different emotion regulation strategies and processes had associated with psychological well-being in terms of depression, obsessivecompulsive disorder and social anxiety symptoms. The findings, and their implications with suggestions for future research and practice, were discussed in the light of relevant literature.
Niksic, Maja. "Public cancer awareness and cancer survival in England : recognition of cancer symptoms and perception of barriers to seeking medical help in relation to breast, lung and bowel cancer survival in England." Thesis, King's College London (University of London), 2016. https://kclpure.kcl.ac.uk/portal/en/theses/public-cancer-awareness-and-cancer-survival-in-england(d8715922-6635-4840-8c4f-66c26adbf0c2).html.
Full textHuston, Chloe Ann. "Validation of the Tri-Choice Naming and Response Bias Measure." Cleveland State University / OhioLINK, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=csu16194338067807.
Full textWyatt, Peggy A. "Evaluating acute myocardial infarction symptom recognition in women." Thesis, 2001. http://hdl.handle.net/2429/11920.
Full textYang, Chih-Wei, and 楊智幃. "An Intelligent Symptom Named Entity Recognition Method using Conditional Random Fields." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/78475948247009778093.
Full text國立臺灣大學
資訊管理學研究所
105
With the advance of technology and the prevalence of Internet access, more and more users attempt to search medical advice on the Internet, and various healthcare websites thus thrive. Users usually seek assistance from those who own similar experiences on healthcare websites. However, there is a great deal of unreliable information without professional endorsement, as the result, users tend to be misled and their conditions may further deteriorate. Even if there are authoritative practitioners involved, they have problem dealing with heavy demand in daily medical advice. Recently, a number of researches explore the intelligent disease inference system, and simply divide it into two parts: medical named entity recognition and disease normalization. This research mainly focuses on symptom named entity recognition. We conduct the experiments using pre-annotated clinical reports released by International Workshop on Semantic Evaluation 2014 Task 7. For each word in the report, we extract features and categorize them into four groups including lexical/morphological, syntactic, semantic, and combinational features, and then utilize machine learning based approach – condition random fields (CRFs) to construct a model that identifies the span of symptom entities in clinical reports. The system performance is evaluated by precision, recall, and f-measure. Our method outperformed some participants in Workshop on Semantic Evaluation 2014 Task 7. Eventually, we analyze the feature influence and key to improve our system in the future.
Maldonado, Eliud Roberto. "Early symptom recognition among Latino parents of children with Autism spectrum disorders : an ethnographic study /." 2008. http://www.library.wisc.edu/databases/connect/dissertations.html.
Full textMlaba, Nonkululeko Zamaximba. "Risk factors associated with HSV-2 sero-prevalence and, the level of symptom recognition among women in inner city Johannesburg - implications for public health interventions." Thesis, 2009. http://hdl.handle.net/10539/7445.
Full textBackground: Herpes Simplex Virus type 2 (HSV-2) is a common cause of genital ulcers worldwide and has emerged as a co-factor in human immunodeficiency virus (HIV) acquisition and transmission. A study was conducted to determine the prevalence of HSV-2, its correlates, the accuracy of reported history of genital ulcer disease (GUD) to predict HSV-2 infection and the extent of symptom recognition in a clinic population in Johannesburg. Methods: 210 women aged 18 years or older were interviewed and socio-demographic, sexual behaviour and clinical information collected. Serological testing for HSV-2 and HIV infections was performed, but only where sera were available for the latter. Factors associations with HSV-2 infection were assessed using logistic regression to estimate odds ratios (OR) and 95% confidence intervals (CI). The sensitivity, specificity, predictive values and likelihood ratios of a history of GUD were calculated. Results: The estimated sero prevalence of HSV-2 was 73% (95% CI 67% - 79%). Few participants, 13/206 (6%) participants had knowledge of genital herpes. Only 9/203 (4%) participants recognised lesions of genital herpes following education and counselling about HSV-2 infection. HSV-2 infection was associated with older age(>25 years of age) OR 2.6 (95% CI 1.4-5.0), spending more than 2 nights away from home, OR 6.0 (95% CI 1.0-62.7), having more than 2 sexual lifetime partners, OR 2.2 (95% CI 1.1-3.9), a history of an STI in the past 3 months ,OR 3.6 (95% CI 1.2-9.5) and HIV infection, OR3.3( 95%CI 1.4-7.9). A history of genital ulceration performed poorly as a predictor of HSV-2 seropositivity; the sensitivity was 7% and specificity was 96%. Conclusion: HSV-2 prevalence was high and few participants were aware of their infection. HVS-2 infection was associated with risky sexual behaviour .A history of genital ulcer disease was not sufficient as a diagnostic tool for HSV-2 infection. Public health interventions should focus on behavioural modification and increasing awareness of genital herpes. HSV-2 management should be incorporated into HIV care and STI protocols.
Sousa, Joana Sofia Dias Pereira de. "O autocuidado em pessoas com insuficiência cardíaca." Doctoral thesis, 2019. http://hdl.handle.net/10400.14/32147.
Full textHeart failure is a chronic condition, in which a person can better manage his or her health through the adoption of self-care behaviors. These behaviors can be learned and accomplished by a disease management program. Based on Dorothea Orem’s Theory of Nursing Systems, the present study used the nurse as part of the Educational Support System, in order to facilitate the adoption of self-care behaviors in persons with heart failure. The aim of this work was: 1) to develop a complex intervention which responded to the difficulties of the hospitalized persons with heart failure in NYHA class II and III, at the therapeutic self-care level – in perception and recognition of signs and symptoms, with evaluation of their impact on Quality of Life; and 2) to do a cost-effective study between the average hospital stay and the cost of a heart failure structured consultation. Based on the method of complex interventions, from the Medical Research Council, a complex intervention was developed, which emerged from a systematic literature review and from semi-structured interviews to hospitalized persons with heart failure, to cardiologists and to nurses who were experts in the management of chronic diseases. The topic addressed was fluid management and monitoring of signs and symptoms of heart failure. A pilot study was designed to implement the intervention, with four moments of evaluation (hospital discharge, one week after hospital discharge, one month after discharge and three months after discharge), where 63 persons with heart failure were enrolled and randomized into control group, defined as usual care (n=33) and into intervention group (n=30), in a cardiology ward of an university hospital. Of the 63 participants in the study, 74,6% were male, with a mean age of 54,83 years (±10,28). At the end of the implementation of the complex intervention there was an improvement in self-care behaviors and in quality of life at the intervention group comparing with the control group. According to the estimated costs, the implementation of a disease management program will allow a saving of 19 times the estimated value for people who do not participate at this program. The present study suggests that the person with heart failure, included in a disease management program, has better self-care behaviors, better quality of life, less emergency admissions and fewer hospitalizations.
PENG, YU-CHE, and 彭昱哲. "Emotion Recognition in College Students with High-Risk ADHD Symptoms." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/qnvk8s.
Full text東吳大學
心理學系
107
Attention Deficient/Hyperactivity Disorder (ADHD) is a common disorder in childhood. But there 79% of adolescents and adults still meet the diagnosis of ADHD. Besides the symptoms of hyperactivity/impulsiveness, many studies also found that they have difficulty in emotional recognition. But the subjects of ADHD emotional recognition were mainly children, and the emotional stimuli studied were mostly facial expressions, which is different from the dynamic situation experienced in daily life. In addition, the research on emotional recognition design has negative emotion stimulation more than positive emotion stimulation. Such design may make negative emotion recognition relatively difficult. Therefore, this study will adjust these research deficiencies through dynamic emotions. The film, with a balanced design of positive and negative emotions, explores whether the emotional recognition ability of high-risk ADHD college students is different from that of normal college students. The study sample consists of 52 college students, including 26 high-risk ADHD students (8 males) and 26 control individuals (5 males). Each college student finish the Adult ADHD Self-Report Scale (ASRS) and the online questionnaire to confirm the willingness to participate, and then take assessment by using the Conners Continuous Performance Test 3rd Edition (CPT-3) and the Emotion recognition test (TASIT and GERT-S), and finish the Achenbach System of Empirically Based Assessment – Adult self-report (ASEBA-ASR) in the end of experiment. The one-way multivariate analysis was used to analysis whether there was a significant difference in the recognition accuracy and the recognition response time, the correct rate of emotion recognition which was calculated by Unbiased Hit Rate (Hu), So that the score can be include the concept of sensitivity and specificity, and excluded the interference of the subject's selection bias is. The results showed that the correct rate of happiness, disgust and neutral emotions of the high-risk ADHD college students was worse than that of the normal college students. The response time of pride was only emotion that high-risk ADHD college students was longer than normal college students. According to the research results, it is suggested that in the future, the emotion recognition stimulants can use dynamic films to make the experiment more ecologically effective, and Hu is used as the correct rate calculation method to more accurately understand the emotional ability. In clinical application, high-risk ADHD students have potential obstacles in identifying emotions such as happiness, neutrality, disgust and pride. It is suggested that in addition to dealing with the core symptoms of ADHD, it can also enhance the ability of high-risk ADHD students to recognize four emotions, especially Identify the correct rate of negative emotions, thereby improving their potential interpersonal problems and possible somatic symptoms.
Jhuo, Yuan-sheng, and 周元生. "An Online Recognition for Power Transformer Inrush Currents and Abnormal Symptoms." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/71571378611608071573.
Full text國立聯合大學
電機工程學系碩士班
96
The power transformer is one of several expensive equipments in power systems . Once the power transformer is malfunctioning, it will cause an unbalanced power supply , which may further lead to the loss of power and utilities need to pay a huge repair expense . Unfortunately , the electric utilities have not yet found effective prevention methods for this kind of problems so far . With the fast development of electric power technology and the continuous efforts made by the power engineers, the possibility of solving the above problems has appeared . The main objective of this study is to investigate an online recognition system for power transformers . The study uses MATLAB software and its related programs as the simulation tool to analyze the power transformer inrush currents in the blink of energizing , which tend to cause the oscillation phenomena within the inside insulating materials, cores and coils , i.e. the inherent capacitance, resistance and inductance. In terms of this phenomenon , various key feature indices can be derived, moreover , by using neural networks the normal inrush currents and possible abnormal symptoms of the power transformer can be identified. The feasibility and effectiveness of the proposed method have been proved by detailed theoretical studies and comprehensive simulations carried out in this study . It is worth to note that with some modifications the proposed method can be further developed into a real-time diagnosis and protection system for the power transformers .
CHIU, TIEN-DENG, and 邱登殿. "Semantic recognition based on artificial intelligent for assisting diagnosis of dermatological symptoms." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/vbh4u4.
Full text國立高雄科技大學
電子工程系
107
Purpose: Semantic recognition based on artificial intelligent method to assist the diagnosis of dermatological symptoms. To verify word vector combined with the knowledge map of medical aided diagnosis is a simple and effective semantic recognition method. Materials and method: This study first establishes a knowledge map of dermatological symptoms and diseases. The description of the medical symptoms is a sentence with only one keyword, and assigned to the corresponding site of occurrence, and then establish the association and probability of this disease may occur. The second is to create a word embedding by using the open library Jieba Word Segmentation and removing some stop words, and the Word2vec utility provided by Thomas Mikolov to learn huge WiKi articles. After establishing the word vector of Chinese common words, to compare the similarity between the symptom sentences input by the user and the symptom description statements of the medical knowledge map. The most likely similar symptom description with its corresponding site of occurrence is used to improve the accuracy of the judgment, and to achieve the application of semantic recognition to assist the diagnosis of dermatology. Results: This study developed an application that establishes a database of associations between dermatological symptoms and diseases, and a similarity calculation for word vectors, providing users with the input of dermatological symptoms to show the percentage of related diseases. As well, it is aimed at the six diseases of dermatology to verify the training models of the word vector which is suitable in the semantic recognition of medical symptom sentences. The Skip-gram model has a maximum error of 0.228 and a minimum of 0.086. The maximum error of CBOW (Continuous Bag of Word) model is 0.617 and the minimum is 0.138, so the Skip-gram model is superior to the CBOW model in the semantic recognition of medical sentences. Conclusions: This study proposes a very effective and simple semantic recognition applied to assist in the diagnosis of dermatological symptoms. Also, this method can be easily extended to different medical departments and even various professional fields. As long as the knowledge map of the professional field and the trained word vector are established. The semantics of the sentence can be effectively recognized.
Naidu, Rekha. "Childhood depression: recognition of behavioural symptoms and management guidelines for Primary Schools." Thesis, 2008. http://hdl.handle.net/10530/78.
Full textResearch indicates that the prevalence of childhood depression is increasing, the onset of depression is occurring earlier in life, and that depression coexists with other mental health problems such as anxiety and disruptive behaviour disorders. Teachers are more responsive to behavioural manifestations such as hyperactivity, disruptive behaviour and aggression. They are less responsive to interpersonal difficulties and less disruptive behaviours such as withdrawal and social isolation. While they can correctly recognize that internalizing symptoms such as withdrawal and sadness are indicators of depression, they are unable to correctly recognize that externalizing behaviours such as disruptiveness and aggression can also be indicators of depression. Since many of these symptoms of depression manifest in the school, it is imperative that teachers are able to correctly identify the symptoms of depression. The correct management of the child prevents the depression from worsening and leading to disastrous consequences. The purpose of this study was to establish whether teachers were fully knowledgeable about the behavioural symptoms of depression. A former purpose was to determine the management strategies used at school, and to develop a guideline document for teachers. Survey methodology and interview techniques were used to collect data for the study. These methods provided quantitative and qualitative data. The participants comprised 56 primary school teachers from three randomly selected schools. Two questionnaires were specially designed to gather data for the study. The results of the study revealed that teachers were not fully knowledgeable about the behavioural symptoms of depression and that they lacked the depth of knowledge required to recognize the significance of the diagnostic criteria of depression "which manifest as behavioural symptoms in school. The results showed mat more than 57 % of participants felt that parents and home factors were responsible for depression. Results also indicated that the majority of participants were not able to recognize the multiplicity of factors that could cause and result in depression. In the perceived absence of psychological support from the Department of Education, participants indicated a need for guidelines for identification and management of symptoms of depression. There was overwhelming support for the implementation of a self-esteem programme at schools. At the conclusion of the study, a document which outlined recognition and management of the behavioural symptoms of depression, was developed by the researcher. As a result of the findings of the study, recommendations were made to teachers, the schools' management team, as well as to the Department of Education. Recommendations made to teachers included training the child in social skills and cognitive strategies, and maintaining contact with parents. One important recommendation to the schools' management was the timely referral of depressed children to mental health professionals. Recommendations made to the Department of Education included the facilitation of the formation of multidisciplinary teams which would comprise teachers, management staff, parents and school psychologists. These multidisciplinary teams would manage the successful implementation of programmes that will foster healthy social and emotional development of all children.
Chen, Yi-Wei, and 陳宜緯. "Diabetic Retinopathy Recognition with Fusion of Supervised Deep Learning Features and Segmented Symptoms." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/b67gzs.
Full text國立交通大學
電子研究所
107
Diabetic retinopathy is the primary cause of blindness in the working-age population of the developed world. Diagnosing the disease heavily relies on imaging studies, which is a time consuming and a manual process performed by trained clinicians. Enhancing the accuracy and speed of the detection process can potentially have a significant impact on population health via early diagnosis and intervention. Besides the prevention, how to keep tracking the treatment effect for the patient with diabetic retinopathy is another crucial issue in personalized healthcare. Motivated by this, we propose a recognition framework, based on deep convolutional neural networks. Our recognition system predicts not only the severity levels of DR but also the location of symptoms at the pixel level. With the combination of DR severity levels and the segmented DR symptoms, our system can predict the severity levels of DR more accurately which could potentially provide another measurement to monitor the progression or regression of retinopathy with therapeutic intervention. For the classification of DR severity levels, the proposed lightweight network, DRNet-cla-v1 improves the classification performance in two aspects: (1) Without any fine-tuning, DRNet-cla-v1, combined with seven other boosting methods achieved 0.961 and 0.967 AUROC on the Messidor dataset for referable and non-referable screening, which outperforms state of the art (0.921 and 0.957). (2) Compared with CKML Net, VNXK, and Zoom-in-Net, DRNet-cla-v1 is more memory efficient with at least 5.23x fewer in total parameters and requires lower computation cost with at least 1.24x fewer in total FLOPs. For the segmentation of DR symptoms, the proposed network, DRNet-seg-v1, achieves 0.6894 average AUPRC on the IDRiD test dataset and outperforms the start of the art (0.6693). Finally, we use the linear SVM to fuse features extracted from the DRNet-cla-v1 and DRNet-seg-v1 and achieves the average accuracy 0.7281 on the IDRiD test dataset, which also outperforms the start of the art (0.6311).
Su, Yi-min, and 蘇逸民. "Machine Learning Classification based on image recognition for study of face symptoms in patients with Down''s syndrome." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/7359vb.
Full text國立中山大學
應用數學系研究所
103
In recent years, both facial recognition system and machine learning are developed rapidly. In these two areas, each has many commonly used methods. In this work, we use a two-stage approach on images for classification. First, we transform the facial image data into multi-dimensional data form, and then apply appropriate multivariate analysis and data mining methods on it. Methodologies such as Multilinear principal component analysis (MPCA), Regularized Discriminant Analysis (RDA), Random Forest are adopted. We aim at finding factors that are important in identifying different types of images. Although facial features are different for individuals, but most people with Down''s syndrome can be discriminated from the outlooks whether he or she has the disease or not. These variations sometimes can be seen from their facial features. For example, the features such as facial proportion, ear appearance, nose shape and eye contour and so on, can help to determine if a person has the disease or not. This thesis discusses how to use multivariate analysis and machine learning methods based on the facial image data to identify Down''s syndrome patients. According to some of the sample images from those with Down''s syndrome or not, we find the important areas on the facial image which are useful in discriminating Down''s syndrome patients. In the end, after restoring the important areas of the facial image, it is expected that the above methodology is helpful as one of the main criteria for the doctors to identify the Down’s syndrome symptoms with high accuracies.
Hilmes-Wingerter, Constanze. "Geruchswahrnehmung und -interpretation schizophrener PatientInnen: Evaluation im Rahmen einer multizentrischen Querschnittserhebung." Doctoral thesis, 2018. http://hdl.handle.net/11858/00-1735-0000-002E-E45B-8.
Full text