Semi-supervised learning with concept drift using particle dynamics applied to network intrusion detection data

Concept drift, which refers to non stationary learning problems over time, has increasing importance in machine learning and data mining. Many concept drift applications require fast response, which means an algorithm must always be (re)trained with the latest available data. But the process of data labeling is usually expensive and/or time consuming when compared to acquisition of unlabeled data, thus usually only a small fraction of the incoming data may be effectively labeled. Semi-supervised learning methods may help in this scenario, as they use both labeled and unlabeled data in the training process. However, most of them are based on assumptions that the data is static. Therefore, semi-supervised learning with concept drifts is still an open challenging task in machine learning. Recently, a particle competition and cooperation approach has been developed to realize graph-based semi-supervised learning from static data. We have extend that approach to handle data streams and concept drift. The result is a passive algorithm which uses a single classifier approach, naturally adapted to concept changes without any explicit drift detection mechanism. It has built-in mechanisms that provide a natural way of learning from new data, gradually "forgetting" older knowledge as older data items are no longer useful for the classification of newer data items. The proposed algorithm is applied to the KDD Cup 1999 Data of network intrusion, showing its effectiveness.

Effects of high and low volume of strength training on muscle strength, muscle volume and lipid profile in postmenopausal women

Changes in lipid profile are considered a risk factor for cardiovascular disease (CVD), especially in postmenopausal woman who have been associated with age-related loss of muscle mass. The beneficial role of aerobic exercise in the prevention of CVD has been well documented. However, the effect of strength training has not been established. The purpose of this study was to determine the changes of lipoprotein levels after 12 weeks of different volumes of strength training and its correlation with strength and muscle volume in postmenopausal women. The participants were randomized into three groups: low volume (LVST; n = 12, 1 set) and high volume of strength training (HVST; n = 11, 3 sets), or control group (n = 12). Training groups performed 12 weeks of supervised strength exercises, 15 maximum repetitions, five times a week, 20 minutes for LVST and 40 minutes for HVST for each training session. Measurements included body composition, strength and muscle volume, as well as blood analysis (glucose, total cholesterol, triglycerides, low-density lipoprotein, and high-density lipoprotein) pre- and post-training. The HVST and LVST improved the one-repetition maximum knee extension strength (p < 0.001), maximal dynamic strength (p < 0.001), and muscle volume (p = 0.048). Post-training triglyceride was lower in HVST when compared to LVST and the control group (p = 0.047). Even though they present the same neuromuscular and morphological adaptations in postmenopausal women, the HVST is more effective than LVST in improving the lipid profile of postmenopausal woman, and can be considered as an ideal program of intervention to reverse changes in lipid metabolism commonly found in this group. Copyright (C) 2014, The Society of Chinese Scholars on Exercise Physiology and Fitness. Published by Elsevier (Singapore) Pte Ltd. All rights reserved.

Exercise training in juvenile dermatomyositis

Objective. To investigate the effects of a supervised exercise training program on health parameters, physical capacity, and health-related quality of life in patients with mild and chronic juvenile dermatomyositis (DM). Methods. This was a prospective longitudinal study following 10 children with mild and chronic juvenile DM (disease duration >1 year). The exercise program consisted of twice-a-week aerobic and resistance training. At baseline and after the 12-week intervention, we assessed muscle strength and function, aerobic conditioning, body composition, juvenile DM scores, and health-related quality of life. Results. Child self-report and parent proxy-report Pediatric Quality of Life Inventory scores were improved after the intervention (-40.3%; P = 0.001 and -48.2%; P = 0.049, respectively). Importantly, after exercise, the Disease Activity Score was reduced (-26.9%; P = 0.026) and the Childhood Muscle Assessment Scale was improved (+2.5%; P = 0.009), whereas the Manual Muscle Test presented a trend toward statistical significance (+2.2%; P = 0.081). The peak oxygen consumption and time-to-exhaustion were increased by 13.3% (P = 0.001) and 18.2% (P = 0.003), respectively, whereas resting heart rate was decreased by 14.7% (P = 0.006), indicating important cardiovascular adaptations to the exercise program. Upper and lower extremity muscle strength and muscle function were also significantly improved after the exercise training (P < 0.05). Both the whole-body and the lumbar spine bone mineral apparent density were significantly increased after training (1.44%; P = 0.044 and 2.85%; P = 0.008, respectively). Conclusion. We showed for the first time that a 12-week supervised exercise program is safe and can improve muscle strength and function, aerobic conditioning, bone mass, disease activity, and health-related quality of life in patients with active and nonactive mild and chronic juvenile DM with near normal physical function and quality of life.

Semi-supervised dimensionality reduction based on partial least squares for visual analysis of high dimensional data

Dimensionality reduction is employed for visual data analysis as a way to obtaining reduced spaces for high dimensional data or to mapping data directly into 2D or 3D spaces. Although techniques have evolved to improve data segregation on reduced or visual spaces, they have limited capabilities for adjusting the results according to user's knowledge. In this paper, we propose a novel approach to handling both dimensionality reduction and visualization of high dimensional data, taking into account user's input. It employs Partial Least Squares (PLS), a statistical tool to perform retrieval of latent spaces focusing on the discriminability of the data. The method employs a training set for building a highly precise model that can then be applied to a much larger data set very effectively. The reduced data set can be exhibited using various existing visualization techniques. The training data is important to code user's knowledge into the loop. However, this work also devises a strategy for calculating PLS reduced spaces when no training data is available. The approach produces increasingly precise visual mappings as the user feeds back his or her knowledge and is capable of working with small and unbalanced training sets.

Diaphragmatic Breathing Training Program Improves Abdominal Motion During Natural Breathing in Patients With Chronic Obstructive Pulmonary Disease: A Randomized Controlled Trial

Yamaguti WP, Claudino RC, Neto AP, Chammas MC, Gomes AC, Salge TM, Moriya HT, Cukier A, Carvalho CR. Diaphragmatic breathing training program improves abdominal motion during natural breathing in patients with chronic obstructive pulmonary disease: a randomized controlled trial. Arch Phys Med Rehabil 2012;93:571-7. Objective: To investigate the effects of a diaphragmatic breathing training program (DBTP) on thoracoabdominal motion and functional capacity in patients with chronic obstructive pulmonary disease. Design: A prospective, randomized controlled trial. Setting: Academic medical center. Participants: Subjects (N=30; forced expiratory volume in Is, 4270 +/- 13% predicted) were randomly allocated to either a training group (TG) or a control group (CG). Interventions: Subjects in the TG completed a 4-week supervised DBTP (3 individualized weekly sessions), while those in the CG received their usual care. Main Outcome Measures: Effectiveness was assessed by amplitude of the rib cage to abdominal motion ratio (RC/ABD ratio) (primary outcome) and diaphragmatic mobility (secondary outcome). The RC/ABD ratio was measured using respiratory inductive plethysmography during voluntary diaphragmatic breathing and natural breathing. Diaphragmatic mobility was measured by ultrasonography. A 6-minute walk test and health-related quality of life were also evaluated. Results: Immediately after the 4-week DBTP, the TG showed a greater abdominal motion during natural breathing quantified by a reduction in the RC/ABD ratio when compared with the CG (F=8.66; P<.001). Abdominal motion during voluntary diaphragmatic breathing after the intervention was also greater in the TG than in the CG (F=4.11; P<.05). The TG showed greater diaphragmatic mobility after the 4-week DBTP than did the CG (F=15.08; P<.001). An improvement in the 6-minute walk test and in health-related quality of life was also observed in the TG. Conclusions: DBTP for patients with chronic obstructive pulmonary disease induced increased diaphragm participation during natural breathing, resulting in an improvement in functional capacity.

Exercise training in childhood-onset systemic lupus erythematosus: a controlled randomized trial

Abstract Introduction Exercise training has emerged as a promising therapeutic strategy to counteract physical dysfunction in adult systemic lupus erythematosus. However, no longitudinal studies have evaluated the effects of an exercise training program in childhood-onset systemic lupus erythematosus (C-SLE) patients. The objective was to evaluate the safety and the efficacy of a supervised aerobic training program in improving the cardiorespiratory capacity in C-SLE patients. Methods Nineteen physically inactive C-SLE patients were randomly assigned into two groups: trained (TR, n = 10, supervised moderate-intensity aerobic exercise program) and non-trained (NT, n = 9). Gender-, body mass index (BMI)- and age-matched healthy children were recruited as controls (C, n = 10) for baseline (PRE) measurements only. C-SLE patients were assessed at PRE and after 12 weeks of training (POST). Main measurements included exercise tolerance and cardiorespiratory measurements in response to a maximal exercise (that is, peak VO2, chronotropic reserve (CR), and the heart rate recovery (ΔHRR) (that is, the difference between HR at peak exercise and at both the first (ΔHRR1) and second (ΔHRR2) minutes of recovery after exercise). Results The C-SLE NT patients did not present changes in any of the cardiorespiratory parameters at POST (P > 0.05). In contrast, the exercise training program was effective in promoting significant increases in time-to-exhaustion (P = 0.01; ES = 1.07), peak speed (P = 0.01; ES = 1.08), peak VO2 (P = 0.04; ES = 0.86), CR (P = 0.06; ES = 0.83), and in ΔHRR1 and ΔHRR2 (P = 0.003; ES = 1.29 and P = 0.0008; ES = 1.36, respectively) in the C-SLE TR when compared with the NT group. Moreover, cardiorespiratory parameters were comparable between C-SLE TR patients and C subjects after the exercise training intervention, as evidenced by the ANOVA analysis (P > 0.05, TR vs. C). SLEDAI-2K scores remained stable throughout the study. Conclusion A 3-month aerobic exercise training was safe and capable of ameliorating the cardiorespiratory capacity and the autonomic function in C-SLE patients. Trial registration NCT01515163.

A semi-supervised classification technique based on interacting forces

Semi-supervised learning is a classification paradigm in which just a few labeled instances are available for the training process. To overcome this small amount of initial label information, the information provided by the unlabeled instances is also considered. In this paper, we propose a nature-inspired semi-supervised learning technique based on attraction forces. Instances are represented as points in a k-dimensional space, and the movement of data points is modeled as a dynamical system. As the system runs, data items with the same label cooperate with each other, and data items with different labels compete among them to attract unlabeled points by applying a specific force function. In this way, all unlabeled data items can be classified when the system reaches its stable state. Stability analysis for the proposed dynamical system is performed and some heuristics are proposed for parameter setting. Simulation results show that the proposed technique achieves good classification results on artificial data sets and is comparable to well-known semi-supervised techniques using benchmark data sets.

Effect of 6-month supervised exercise on low-density lipoprotein apolipoprotein B kinetics in patients with type 2 diabetes mellitus

Although low-density lipoprotein (LDL) cholesterol is often normal in patients with type 2 diabetes mellitus, there is evidence for a reduced fractional catabolic rate and consequently an increased mean residence time (MRT), which can increase atherogenic risk. The dyslipidemia and insulin resistance of type 2 diabetes mellitus can be improved by aerobic exercise, but effects on LDL kinetics are unknown. The effect of 6-month supervised exercise on LDL apolipoprotein B kinetics was studied in a group of 17 patients with type 2 diabetes mellitus (mean age, 56.8 years; range, 38-68 years). Patients were randomized into a supervised group, who had a weekly training session, and an unsupervised group. LDL kinetics were measured with an infusion of 1-(13)C leucine at baseline in all groups and after 6 months of exercise in the patients. Eight body mass index-matched nondiabetic controls (mean age, 50.3 years; range, 40-67 years) were also studied at baseline only. At baseline, LDL MRT was significantly longer in the diabetic patients, whereas LDL production rate and fractional clearance rates were significantly lower than in controls. Percentage of glycated hemoglobin A(1c), body mass index, insulin sensitivity measured by the homeostasis model assessment, and very low-density lipoprotein triglyceride decreased (P < .02) in the supervised group, with no change in the unsupervised group. After 6 months, LDL cholesterol did not change in either the supervised or unsupervised group; but there was a significant change in LDL MRT between groups (P < .05) that correlated positively with very low-density lipoprotein triglyceride (r = 0.51, P < .04) and negatively with maximal oxygen uptake, a measure of fitness (r = -0.51, P = .035), in all patients. The LDL production and clearance rates did not change in either group. This study suggests that a supervised exercise program can reduce deleterious changes in LDL MRT.

Impact of surgical training on incidence of surgical site infection

BACKGROUND: Despite availability of other training forms, tutorial assistance cannot be entirely replaced in surgical education. Concerns exist that tutorial assistance may lead to an increased rate of surgical site infection (SSI). The purpose of the present study was to investigate whether the risk of SSI is higher after surgery with tutorial assistance than after surgery performed autonomously by a fully trained surgeon. METHODS: All consecutive visceral, vascular, and traumatological inpatient procedures at a Swiss University Hospital were prospectively recorded during a 24-month period, and the patients were followed for 12 months to ascertain the occurrence of SSI. Using univariable and multivariable logistic regressions, we assessed the association of tutorial assistance surgery with SSI in 6,103 interventions. RESULTS: Autonomously performed surgery was associated with SSI in univariable analysis (5.36% SSI vs. 3.81% for tutorial assistance, p = 0.006). In multivariable analysis, the odds of SSI for tutorial assistance was no longer significantly lower (Odds Ratio [OR] = 0.82; 95% Confidence Interval [CI]: 0.62-1.09; p = 0.163). CONCLUSIONS: Surgical training does not lead to higher SSI rate if trainees are adequately supervised and interventions are carefully selected. Although other forms of training are useful, tutorial assistance in the operating room continues to be the mainstay of surgical education.

Evaluating retraining rules for semi-supervised learning in neural network based cursive word recognition

Training a system to recognize handwritten words is a task that requires a large amount of data with their correct transcription. However, the creation of such a training set, including the generation of the ground truth, is tedious and costly. One way of reducing the high cost of labeled training data acquisition is to exploit unlabeled data, which can be gathered easily. Making use of both labeled and unlabeled data is known as semi-supervised learning. One of the most general versions of semi-supervised learning is self-training, where a recognizer iteratively retrains itself on its own output on new, unlabeled data. In this paper we propose to apply semi-supervised learning, and in particular self-training, to the problem of cursive, handwritten word recognition. The special focus of the paper is on retraining rules that define what data are actually being used in the retraining phase. In a series of experiments it is shown that the performance of a neural network based recognizer can be significantly improved through the use of unlabeled data and self-training if appropriate retraining rules are applied.

Adaptive neuro-fuzzy inference systems (ANFIS) for supervised classification of competence in MIS based on psychomotor skills

INTRODUCTION: Objective assessment of motor skills has become an important challenge in minimally invasive surgery (MIS) training.Currently, there is no gold standard defining and determining the residents' surgical competence.To aid in the decision process, we analyze the validity of a supervised classifier to determine the degree of MIS competence based on assessment of psychomotor skills METHODOLOGY: The ANFIS is trained to classify performance in a box trainer peg transfer task performed by two groups (expert/non expert). There were 42 participants included in the study: the non-expert group consisted of 16 medical students and 8 residents (< 10 MIS procedures performed), whereas the expert group consisted of 14 residents (> 10 MIS procedures performed) and 4 experienced surgeons. Instrument movements were captured by means of the Endoscopic Video Analysis (EVA) tracking system. Nine motion analysis parameters (MAPs) were analyzed, including time, path length, depth, average speed, average acceleration, economy of area, economy of volume, idle time and motion smoothness. Data reduction was performed by means of principal component analysis, and then used to train the ANFIS net. Performance was measured by leave one out cross validation. RESULTS: The ANFIS presented an accuracy of 80.95%, where 13 experts and 21 non-experts were correctly classified. Total root mean square error was 0.88, while the area under the classifiers' ROC curve (AUC) was measured at 0.81. DISCUSSION: We have shown the usefulness of ANFIS for classification of MIS competence in a simple box trainer exercise. The main advantage of using ANFIS resides in its continuous output, which allows fine discrimination of surgical competence. There are, however, challenges that must be taken into account when considering use of ANFIS (e.g. training time, architecture modeling). Despite this, we have shown discriminative power of ANFIS for a low-difficulty box trainer task, regardless of the individual significances between MAPs. Future studies are required to confirm the findings, inclusion of new tasks, conditions and sample population.

Supervised classification of minimally invasive surgery psychomotor competence based on instruments motion analysis

Background Objective assessment of psychomotor skills has become an important challenge in the training of minimally invasive surgical (MIS) techniques. Currently, no gold standard defining surgical competence exists for classifying residents according to their surgical skills. Supervised classification has been proposed as a means for objectively establishing competence thresholds in psychomotor skills evaluation. This report presents a study comparing three classification methods for establishing their validity in a set of tasks for basic skills’ assessment. Methods Linear discriminant analysis (LDA), support vector machines (SVM), and adaptive neuro-fuzzy inference systems (ANFIS) were used. A total of 42 participants, divided into an experienced group (4 expert surgeons and 14 residents with >10 laparoscopic surgeries performed) and a nonexperienced group (16 students and 8 residents with <10 laparoscopic surgeries performed), performed three box trainer tasks validated for assessment of MIS psychomotor skills. Instrument movements were captured using the TrEndo tracking system, and nine motion analysis parameters (MAPs) were analyzed. The performance of the classifiers was measured by leave-one-out cross-validation using the scores obtained by the participants. Results The mean accuracy performances of the classifiers were 71 % (LDA), 78.2 % (SVM), and 71.7 % (ANFIS). No statistically significant differences in the performance were identified between the classifiers. Conclusions The three proposed classifiers showed good performance in the discrimination of skills, especially when information from all MAPs and tasks combined were considered. A correlation between the surgeons’ previous experience and their execution of the tasks could be ascertained from results. However, misclassifications across all the classifiers could imply the existence of other factors influencing psychomotor competence.

Adaptaciones cardiacas hemodinámicas, estructurales y funcionales a un programa de ejercicio físico supervisado durante el embarazo: ensayo clínico aleatorizado = Hemodynamic, structural and functional cardiac adaptations in a supervised physical exercise program during pregnancy: a randomized controlled trial

Introducción: Diversos cambios ocurren en el sistema cardiovascular materno durante el embarazo, lo que genera un gran estrés sobre este sistema especialmente durante el tercer trimestre, pudiendo acentuarse en presencia de determinados factores de riesgo. Los objetivos de este estudio fueron, valorar las adaptaciones cardiovasculares producidas por un programa específico de ejercicio físico; su seguridad sobre el sistema cardiovascular materno y los resultados del embarazo; y su eficacia en el control de los factores de riesgo cardiovascular. Material y métodos: El diseño del estudio fue un ensayo clínico aleatorizado. 151 gestantes sanas fueron evaluadas mediante un ecocardiograma y un electrocardiograma en la semana 20 y 34 de gestación. Un total de 89 gestantes participaron en un programa de ejercicio físico (GE) desde el primer hasta el tercer trimestre de embarazo, constituido principalmente por 25-30 minutos de trabajo aeróbico (55-60% de la frecuencia cardiaca de reserva), trabajo de fortalecimiento general y específico, y un trabajo de tonificación del suelo pélvico; desarrollado 3 días a la semana con una duración de 55-60 minutos cada sesión. Las gestantes aleatoriamente asignadas al grupo de control (GC; n=62) permanecieron sedentarias durante el embarazo. El estudio fue aprobado por el Comité Ético de investigación clínica del Hospital Universitario de Fuenlabrada. Resultados: Las características basales fueron similares entre ambos grupos. A diferencia del GC, las gestantes del GE evitaron el descenso significativo del gasto cardiaco indexado, entre el 2º y 3ºT de embarazo, y conservaron el patrón geométrico normal del ventrículo izquierdo; mientras que en el GC cambió hacia un patrón de remodelado concéntrico. En la semana 20, las gestantes del GE presentaron valores significativamente menores de frecuencia cardiaca (GC: 79,56±10,76 vs. GE: 76,05±9,34; p=0,04), tensión arterial sistólica (GC: 110,19±10,23 vs. GE: 106,04±12,06; p=0,03); tensión arterial diastólica (GC: 64,56±7,88 vs. GE: 61,81±7,15; p=0,03); tiempo de relajación isovolumétrica (GC: 72,94±14,71 vs. GE: 67,05±16,48; p=0,04); y un mayor tiempo de deceleración de la onda E (GC: 142,09±39,11 vs. GE: 162,10±48,59; p=0,01). En la semana 34, el GE presentó valores significativamente superiores de volumen sistólico (GC: 51,13±11,85 vs. GE: 56,21±12,79 p=0,04), de llenado temprano del ventrículo izquierdo (E) (GC: 78,38±14,07 vs. GE: 85,30±16,62; p=0,02) y de tiempo de deceleración de la onda E (GC: 130,35±37,11 vs. GE: 146,61±43,40; p=0,04). Conclusión: La práctica regular de ejercicio físico durante el embarazo puede producir adaptaciones positivas sobre el sistema cardiovascular materno durante el tercer trimestre de embarazo, además de ayudar en el control de sus factores de riesgo, sin alterar la salud materno-fetal. ABSTRACT Background: Several changes occur in the maternal cardiovascular system during pregnancy. These changes produce a considerable stress in this system, especially during the third trimester, which can be increased in presence of some risk factors. The aims of this study were, to assess the maternal cardiac adaptations in a specific exercise program; its safety on the maternal cardiovascular system and pregnancy outcomes; and its effectiveness in the control of cardiovascular risk factors. Material and methods: A randomized controlled trial was designed. 151 healthy pregnant women were assessed by an echocardiography and electrocardiography at 20 and 34 weeks of gestation. A total of 89 pregnant women participated in a physical exercise program (EG) from the first to the third trimester of pregnancy. It consisted of 25-30 minutes of aerobic conditioning (55-60% of their heart rate reserve), general and specific strength exercises, and a pelvic floor muscles training; 3 times per weeks during 55-60 minutes per session. Pregnant women randomized allocated to the control group (CG) remained sedentary during pregnancy. The study was approved by the Research Ethics Committee of Hospital Universitario de Fuenlabrada. Results: Baseline characteristics were similar between groups. Difference from the CG, pregnant women from the EG prevented the significant decrease of the cardiac output index, between the 2nd and 3rd trimester of pregnancy, and preserved the normal left ventricular pattern; whereas in the CG shifted to concentric remodeling pattern. At 20 weeks, women in the EG had significant lower heart rate (CG: 79,56±10,76 vs. EG: 76,05±9,34; p=0,04), systolic blood pressure (CG: 110,19±10,23 vs. EG: 106,04±12,06; p=0,03); diastolic blood pressure (CG: 64,56±7,88 vs. EG: 61,81±7,15; p=0,03); isovolumetric relaxation time (GC: 72,94±14,71 vs. GE: 67,05±16,48; p=0,04); and a higher deceleration time of E Wave (GC: 142,09±39,11 vs. GE: 162,10±48,59; p=0,01). At 34 weeks, the EG had a significant higher stroke volume (CG: 51,13±11,85 vs. EG: 56,21±12,79 p=0,04), early filling of left ventricular (E) (CG: 78,38±14,07 vs. EG: 85,30±16,62; p=0,02) and deceleration time of E wave (CG: 130,35±37,11 vs. EG:146,61±43,40; p=0,04). Conclusion: Physical regular exercise program during pregnancy may produce positive maternal cardiovascular adaptations during the third trimester of pregnancy. In addition, it helps to control the cardiovascular risk factors without altering maternal and fetus health.

Postoperative Analgesia Following Sciatic Nerve Blockade Administered by Nurse Anesthetists Supervised by Regional Anesthesia Faculty in an Academic Hospital

Introduction: Assessment of expertise in regional anesthesia techniques is traditionally based upon quota fulfillment of procedures during training. Validation of practitioner proficiency in performing procedures in surgical specialties has moved from simple measurement of technical skills to evaluation of global patient outcomes. Complete absence of pain as a result of nerve blockade is the most important clinical endpoint but patient, technical and procedural factors influence results. The purpose of this study was to measure the postoperative pain scores and associated analgesic medication requirements for patients administered sciatic nerve blockade by nurse anesthetists and determine patient or procedural factors that influenced this outcome. Methods: Either nerve stimulator or ultrasound guided sciatic nerve blockade was administered by nurse anesthetists under the supervision of regional anesthesia faculty. Patient demographic data that was collected included gender, body mass index, surgical procedure, and pre-existing chronic pain with associated opioid use. Patient self-reported pain scores and opioid analgesic dosages in the preoperative, intraoperative, immediate postoperative and 24 hour post procedure intervals were recorded. Results: 22 nurse anesthetists administered sciatic nerve blockade to 48 patients during a 36 month interval. Transition from a nerve stimulator to ultrasound guided sciatic nerve block technique resulted in lower mean pain scores. Patients reporting chronic opioid use were observed to have elevated perioperative opioid analgesic requirements and pain scores compared to opioid naïve patients. Conclusion: Effective analgesia is a prime measure for assessing expertise in regional anesthesia and continuous evaluation of this outcome in everyday practice is proposed.

Graph-based Semi-Supervised Learning in Acoustic Modeling for Automatic Speech Recognition

Thesis (Ph.D.)--University of Washington, 2016-06