Session Variability Research Articles

Factors influencing the development of artificial intelligence in orthodontics.

Since developing AI procedures demands significant computing resources and time, the implementation of a careful experimental design is essential. The purpose of this study was to investigate factors influencing the development of AI in orthodontics. A total of 162 AI models were developed, with various combinations of sample sizes (170, 340, 679), input variables (40, 80, 160), output variables (38, 76, 154), training sessions (100, 500, 1000), and computer specifications (new vs. old). The TabNet deep-learning algorithm was used to develop these AI models, and leave-one-out cross-validation was applied in training. The goodness-of-fit of the regression models was compared using the adjusted coefficient of determination values, and the best-fit model was selected accordingly. Multiple linear regression analyses were employed to investigate the relationship between the influencing factors. Increasing the number of training sessions enhanced the effectiveness of the AI models. The best-fit regression model for predicting the computational time of AI, which included logarithmic transformation of time, sample size, and training session variables, demonstrated an adjusted coefficient of determination of 0.99. The study results show that estimating the time required for AI development may be possible using logarithmic transformations of time, sample size, and training session variables, followed by applying coefficients estimated through several pilot studies with reduced sample sizes and reduced training sessions.

ANALYSIS OF HEALTH EDUCATION FAMILY DEVELOPMENT SESSION WITH STUNTING IN PANGKAJENE AND ISLANDS REGENCY, INDONESIA: CROSS-SECTIONAL STUDY

Background: Stunting is a growth disorder experienced by young people whose length or height is not appropriate to their age according to the standards set by the WHO. UNICEF data for 2018 showed that almost 3 out of 10 young children have stunts or are too short for their age. Pangkajene and the Islands Regency showed a stunting prevalence of 29.10% or the highest in South Sulawesi Province in 2018. The Hope Family Program (PKH) is a conditional social assistance program that aims to improve the standard of living of KPM through access to education, health and welfare services as well as reducing the burden of expenditure and increasing the income of poor and vulnerable families. Purpose: To find out the relationship between Family Development Session health education and stunting incidents in Family Hope Program recipients in Pangkajene and the Islands regency. Methods: This study used an observational research approach with a crosectional model. The data was collected using a questionnaire with Family Development Session variables, food management pattern and BBLR history. The data collected was then analyzed using chi-square analysis. Results: Out of 71 respondents who came from recipients of the Hope Family Program, 36 children (51%) suffered stunting and 35 children (49%) did not. Conclusion: There is a significant link between health education Family Development Session, food management pattern and LBW history with stunting incidents in Pangkajene and the Islands Regency (p < 0.05).

OFFICE BLOOD PRESSURE VARIABILITY: WITHIN SESSION STABILITY ACROSS CONSECUTIVE MEASUREMENTS USING OSCILLOMETRIC DEVICES

Objective: Blood pressure (BP) is routinely monitored by healthcare providers and during drug development. For improvement in accuracy, several oscillometric devices perform multiple sequential inflations, rather than relying on a single inflation, to determine a mean systolic and diastolic blood pressure (SBP, DBP). Blood pressure is known to vary physiologically throughout a day, and over the course of days and weeks, due to intrinsic and extrinsic factors. Little data has been published describing the variability of SBP and DBP recorded minutes apart using oscillometric methods (i.e. within session variability). Design and method: We investigated the stability of within session SBP and DBP across 4 datasets by evaluating differences between 3 consecutive inflations recorded 1-2 minutes apart using a clinically validated oscillometric BP monitor that passed the ANSI/AAMI/ISO 2013, ESH-IP 2002 and BHS 1993 protocols (Table 1). These datasets included patients with controlled or uncontrolled hypertension. Results: Data were available from over 10.000 measurement pairs. The differences between inflation 1 and 2 were within ±10, 20 and 30 mmHg for 78.1, 94.4 and 97.9% of the SBP measurements, respectively. For the DBP, 90.7, 95.5 and 97.3 % of the differences between inflation 1 and 2 were within ±10, 15 and 20 mmHg, respectively. A similar trend was seen between inflation 2 and 3. Table 1: Categorical Analysis of BP changes between consecutive inflations. Conclusions: Our data demonstrate substantial variability between consecutive oscillometric BP measurements performed a few minutes apart. Over 20% of the time, consecutive inflations show an absolute change in SBP of at least 10 mmHg. It is unclear whether this represents true physiologic changes in BP or is partly artefactual due to failure of a device's algorithm to determine BP accurately from the oscillometric waveform. These data suggest that criteria for within session variability for automated oscillometric blood pressure devices should be established, including a threshold for repeating the session after 10 minutes of rest.

Mapping the Impact of Approximate Gradient Nonlinearity Fields Correction on Tractography.

Nonlinear gradients impact diffusion weighted MRI by introducing spatial variation in estimated diffusion tensors. Recent studies have shown that increasing signal-to-noise ratios and the use of ultra-strong gradients may lead to clinically significant impacts on analyses due to these nonlinear gradients in microstructural measures. These effects can potentially bias tractography results and cause misinterpretation of data. Herein, we characterize the impact of an "approximate" gradient nonlinearity correction technique in tractography using empirically derived gradient nonlinear fields. This technique scales the diffusion signal by the change in magnitude due to the gradient nonlinearities, without concomitant correction of gradient direction errors. The impact of this correction on tractography is assessed through white matter bundle segmentation and connectomics via bundle-wise volume, fractional anisotropy, mean diffusivity, radial diffusivity, axial diffusivity, primary eigenvector, and length; as well as the modularity, global efficiency, and characteristic path length connectomics graph measures. We investigate the differences between (1) these measures directly and (2) the within session variability of these measures before and after approximate correction in 61 subjects from the MASiVar pediatric reproducibility dataset. We find approximate correction results is little to no differences on the population level, but large differences on the subject-specific level for both the measures directly and their within session variability. Thus, this study suggests though approximate correction of gradient nonlinearities may not change tractography findings on the population level, subject-specific interpretations may exhibit large fluctuations. A limitation is the lack of comparison with the empirical voxel-wise gradient table correction.

The voice as a material clue: a new forensic Algerian Corpus.

Dialects have received bigger interest in recent years as they are increasingly used on the web and social media. Because Algerian Arabic dialects suffer from a lack of appropriate speech corpora for speech recognition, a rich dialect corpus is needed to approach Algerian Accent recognition. The latter remains a key feature in the field of Forensic Voice Comparison (FVC) systems. This paper presents a new large-scale forensic Algerian speech corpus called Sawt El-Djazaïr. An important criterion in dealing with forensic corpora is the presence of session variability. For this purpose, we collected celebrity recordings in various regions of Algeria, from different social networks, in various scenarios, and at different times. In addition, we also recorded 87 participants using cellular calls and voice over IP (VoIP) applications including Viber, WhatsApp, and Google Meet. The corpus of approximately 50hours covers various speech topics and is spoken in twelve Algerian sub-dialects. The design guidelines of the proposed corpus are described along with the grouping of dialects across different geographical locations. Sawt El-Djazaïr is available to the research community upon request.

Which therapist perceptions best predict client outcomes? A naturalistic examination.

Examining associations between therapists' perceptions of therapy sessions and client-reported outcomes in naturalistic settings (real-life therapy settings) can provide valuable guidance for the assessment, treatment, and monitoring of clients. This study included data of 1334 sessions from 127 clients (86 individual and 41 couple cases) and 15 therapists, collected at a therapy training center. Clients reported their personal functioning and individual symptoms before each session. Therapists rated clients' participation, receptivity, session progress, goal progress, and therapeutic alliance at the end of each therapy session. Multilevel Structural Equation Modeling analyses revealed that therapist-rated client participation and goal progress predicted better personal functioning, beyond clients' previous personal functioning scores. In contrast, none of therapist-rated session variables predicted clients' individual symptoms, beyond previous symptom scores. Power analyses suggested sufficient statistical power to detect small effect sizes. Findings of the current study have clinical implications for treatment planning and progress monitoring.

Take the extra steps: Within- and between session variability of spatiotemporal and kinematic variables of individuals with a transfemoral amputation

Take the extra steps: Within- and between session variability of spatiotemporal and kinematic variables of individuals with a transfemoral amputation

Seismocardiographic Signal Variability During Regular Breathing And Breath Holding

<h3>Introduction</h3> Seismocardiography signals (SCG) are acoustic vibrations generated by heart activity and measured non-invasively at the chest surface. The potential utility of SCG for HF diagnosis and monitoring may be limited by signal variability. Respiration is a known, yet not well understood, source of variability. The objective of this pilot study was to quantify the SCG variability during breathing maneuvers. <h3>Methods</h3> SCG, electrocardiography (ECG) and airflow signals were acquired in two healthy subjects during normal breathing and breath holding (at end-inspiration and end-expiration while the glottis remained open). Data recording was repeated three times, while subjects resting on a 45 degree-elevated tilt table. The SCG events were detected and segmented utilizing the ECG R wave. Although the waveform varied, using unsupervised machine learning (k-medoid clustering) one could separate SCG waveforms during breathing into two "clusters" of similar events. The SCG variability was calculated using Dynamic Time Warping (DTW). The time interval between SCG1 and SCG 2 (which corresponds to the heart-sound ejection-period or HSEP) was also calculated. <h3>Results</h3> Table 1 shows the mean and standard deviation (SD) of the following SCG features: intra-cluster variability, inter-session variability and HSEP during regular breathing, breath hold at end inspiration and end expiration. SCG average intra-cluster and inter session variability was 27% and 24% lower, respectively, during breath holding for both end-inspiration and end-expiration compared to normal breathing. In addition, HSEP was 12% lower during breath holding compared to normal breathing. <h3>Conclusion</h3> Appropriate accounting for SCG variability introduced by breathing appears to account for a significant portion of the signal variability. Hence algorithms integrating respiratory changes may lead to more robust SCG analysis for HF diagnosis and monitoring. In addition, the observed respiration-dependent variability may prove to be a useful feature for HF management. Further studies are needed to confirm these findings in HF patients.

The Effects of Neurosculpting® Meditation on Stress, Anxiety and Sleep on one group of college students

Objective: The purpose of this study was to examine if 11 weeks of Neurosculpting® meditation improved sleep and other variables in college aged students. Participants: Fifteen undergraduate students. Methods: Subjects were evaluated at the beginning and end of the semester using two tools: The Pittsburg Sleep Quality Index and the Depression Anxiety Stress Scale. During each session, heart rate and heart rate variability were measured using a smartphone app, fingertip sensor, and HRV monitor. Subjects received 60 minutes of Neurosculpting® Meditation, one time per week, for 11 weeks. Results: The average score of both the DASS and PSQI decreased (p = .54) and (p = .08) respectively. Within each session, average HR decreased and average HRV increased. However, neither variable showed significant changes from the beginning to the end of the semester. Conclusions: This study demonstrated that consistent Neurosculpting® meditation sessions may improve heart rate variability and sleep in college aged students.

Strain by virtual extensometers and video-imaging optical coherence tomography as a repeatable metric for IOP-Induced optic nerve head deformations

PurposeTo determine if in vivo strain response of the Optic Nerve Head (ONH) to IOP elevation visualized using Optical Coherence Tomography (OCT) video imaging and quantified using novel virtual extensometers was able to be provided repeatable measurements of tissue specific deformations. MethodsThe ONHs of 5 eyes from 5 non-human primates (NHPs) were imaged by Spectralis OCT. A vertical and a horizontal B-scan of the ONH were continuously recorded for 60 s at 6 Hz (video imaging mode) during IOP elevation from 10 to 30 mmHg. Imaging was repeated over three imaging sessions. The 2D normal strain was computed by template-matching digital image correlation using virtual extensometers. ANOVA F-test (F) was used to compare inter-eye, inter-session, and inter-tissue variability for the prelaminar, Bruch's membrane opening (BMO), lamina cribrosa (LC) and choroidal regions (against variance the error term). F-test of the ratio between inter-eye to inter-session variability was used to test for strain repeatability across imaging sessions (FIS). ResultsVariability of strain across imaging session (F = 0.7263, p = 0.4855) and scan orientation was not significant (F = 1.053, p = 0.3066). Inter session variability of strain was significantly lower than inter-eye variability (FIS = 22.63, p = 0.0428) and inter-tissue variability (FIS = 99.33 p = 0.00998). After IOP elevation, strain was highest in the choroid (−18.11%, p < 0.001), followed by prelaminar tissue (−11.0%, p < 0.001), LC (−3.79%, p < 0.001), and relative change in BMO diameter (−0.57%, p = 0.704). ConclusionsVirtual extensometers applied to video-OCT were sensitive to the eye-specific and tissue-specific mechanical response of the ONH to IOP and were repeatable across imaging sessions.

HiLAM-aligned kernel discriminant analysis for text-dependent speaker verification

Probabilistic Linear Discriminant Analysis (PLDA) has been a commonly used backend classifier for many text-dependent speaker verification (TDSV) systems. Lately, PLDA projections have been integrated with the traditional Dynamic Time Warping (DTW) template matching framework, resulting in the DTW Online i-vector/PLDA system. The system is shown to achieve state-of-the-art performance for TDSV task. PLDA model serves to train a subspace that compensates for channel and session variabilities. It assumes linear separability between speaker-phrase information and other components. However, this relationship is known to be non-linear. The non-linearity is more prominent in case of short speech extracts, as in the case of the online i-vectors. This results in loss of vital speaker-phrase information at PLDA modeling. To this end, this work explores Kernel Discriminant Analysis (KDA) for TDSV task. It further proposes to use Hierarchical Multi-Layer Acoustic Model (HiLAM) to complement KDA with a more effective speaker-text class definition. The proposed system is hypothesized to benefit on three counts — non-linear modeling ability of KDA, speaker idiosyncrasy information associated with HiLAM-defined speaker-text units and modeling of the exact context of the pass-phrase, as offered by HiLAM. It shows a relative Equal Error Rate (EER) reduction of up to 50.63% on Part 1 of the RSR2015 database when compared to the baseline DTW Online i-vector/PLDA system.

Therapist Interventions and Skills as Predictors of Dropout in Outpatient Psychotherapy

The current study employed machine learning to investigate whether the inclusion of observer-rated therapist interventions and skills in early sessions of psychotherapy improved dropout prediction beyond intake assessments. Patients were treated by postgraduate clinicians at a university outpatient clinic. Psychometric instruments were assessed at intake and therapeutic interventions and skills in the third session were routinely rated by independent observers. After variable preselection, an elastic net algorithm was used to build two dropout prediction models, one including and one excluding observer-rated session variables. The best model included observer-rated variables and was significantly superior to the model including intake variables only. Alongside intake variables, two observer-rated variables significantly predicted dropout: therapist use of feedback and summaries and treatment difficulty. Although not retained in the final prediction model, the observer-rated use of cognitive techniques was also significantly correlated with dropout. Observer ratings of therapist interventions and skills in early sessions of psychotherapy improve predictors of dropout from psychotherapy beyond intake variables alone. Future research could work toward personalizing dropout predictions to the specific dyad, thereby improving their validity and aiding therapists to recognize and react to increased dropout risk.

Speaker-Phrase-Specific Adaptation of PLDA Model for Improved Performance in Text-Dependent Speaker Verification

The i-vector/probabilistic linear discriminant analysis (PLDA) framework has been popularly used in the field of speaker verification for a long time. Lately, the introduction of online i-vectors and its integration with dynamic time warping template matching technique have significantly improved the performance of text-dependent speaker verification system. The PLDA model learns to discriminate among instances of different speaker-phrase classes and also compensates for channel and session variability. However, when exposed to unseen speakers and text, the variability compensation model turns less than optimal, leading to substantial verification error. In this paper, PLDA adaptation, in order to incorporate the idea of speaker-phrase-dependent variability in the ivector/PLDA technique, has been proposed. The adapted model gets specifically tuned to particular speaker-phrase class, leading to a more optimal solution. Two adaptation techniques, namely interpolation and weighted likelihood, have been explored in this work. Experiments have been performed on Part 1 of the RSR2015 database, and relative equal error rate (EER) reductions of up to 58.22% and 45% have been observed for interpolation and weighted likelihood techniques, respectively. The use of speaker-phrase-specific mean and whitening parameters has led to further improvement, resulting in EER reduction of up to 20% relative to that of the adapted models.

Factors Associated With Seizure Adequacy Along the Course of Electroconvulsive Therapy.

Eliciting a generalized seizure is essential to electroconvulsive therapy (ECT), but there is still a need to understand how patient and session variables interact to generate a seizure of adequate quality. Here, we investigate factors associated with motor seizure length as a measure of quality in a large database of patients who underwent ECT. This is a retrospective cohort including data from all adult inpatients who underwent ECT at a university hospital in Brazil from 2009 to 2015. We used linear mixed models to investigate the effects of patient, session, and medication on seizure length. Session information was available for 387 patients, a total of 3544 sessions and 4167 individual stimulations. Multiple stimulations were necessary in 12.4% of sessions. Median seizure length was 30 seconds. Seizure length was directly correlated with stimulus dosage and inversely correlated with the session number, patient age, prescription of anticonvulsants in the day before and β-blockers during the session, and the thiopental dose. Use of benzodiazepines was not associated with a shorter seizure duration, irrespective of dose. We demonstrate here how motor seizure length evolves during a course of ECT. With a large number of sessions, we are able to integrate a host of factors in a prediction model. Seizure quality was influenced by a number of the studied factors, many of which are potentially modifiable and could be assessed before initiating and handled during treatment.

ECG biometric verification system: An i-vector to overcome variability factors

Dealing with signal and session variability is a common problem in biometric recognition system since biometric signal is frequently inconsistent over time. Health, aging, emotional conditions and different recording settings are some of the factors that contribute to the variability issue. This cause the two samples of the same subject tends to be different from each other hence giving a mismatch effect between the enrolments and testing condition. Over the years, solving the variability problem by subspace representation concept has become prevalent. Hence, it motivates us to validate a recognition algorithm based on factor analysis perspective and we use electrocardiogram (ECG) signal for our experimental data as it is subject to change over time and sensitive to different sensors. We first model each supervectors extracted from Gaussian Mixture Model (GMM) into two different factors which are subject and session independent supervectors based on Joint Factor Analysis (JFA) algorithm. For the second model which is based on i-vector approach, the supervectors extracted from GMM is first modelled to be a single total factor and a compensation method is then employed to compensate the variability effect. Three compensation methods for the i-vector are employed which are Probabilistic Linear Discriminate Analysis (PLDA), Linear Discriminate Analysis (LDA) and Within Class Covariance Normalization (WCCN). The ECG-ID database obtained from physionet database consists of 90 subjects with a total of 310 ECG recordings; each recorded for 20 seconds are used in this study. Experimental results reveal the robustness of the i-vectors PLDA approach by giving 2.156% and 2.155% of Equal Error Rate (EER) for protocol 1 and 2, respectively.

A fuzzy‐clustering‐based hierarchical i‐vector/probabilistic linear discriminant analysis system for text‐dependent speaker verification

AbstractIn the i‐vector/probabilistic linear discriminant analysis (PLDA) technique, the PLDA backend classifier is modelled on i‐vectors. PLDA defines an i‐vector subspace that compensates the unwanted variability and helps to discriminate among speaker‐phrase pairs. The channel or session variability manifested in i‐vectors are known to be nonlinear in nature. PLDA training, however, assumes the variability to be linearly separable, thereby causing loss of important discriminating information. Besides, the i‐vector estimation, itself, is known to be poor in case of short utterances. This paper attempts to address these issues using a simple hierarchy‐based system. A modified fuzzy‐clustering technique is employed to divide the feature space into more characteristic feature subspaces using vocal source features. Thereafter, a separate i‐vector/PLDA model is trained for each of the subspaces. The sparser alignment owing to subspace‐specific universal background model and the relatively reduced dimensions of variability in individual subspaces help to train more effective i‐vector/PLDA models. Also, vocal source features are complementary to mel frequency cepstral coefficients, which are transformed into i‐vectors using mixture model technique. As a consequence, vocal source features and i‐vectors tend to have complementary information. Thus using vocal source features for classification in a hierarchy tree may help to differentiate some of the speaker‐phrase classes, which otherwise are not easily discriminable based on i‐vectors. The proposed technique has been validated on Part 1 of RSR2015 database, and it shows a relative equal error rate reduction of up to 37.41% with respect to the baseline i‐vector/PLDA system.

Analysis of publications of a scientific periodic: evaluation by the tool SPC

The work consists of analyzing the historical evolution of an international scientific journal, which is characterized by publications via the web and the Open Journal System (OJS) software. In data collection it was necessary to use Google analytics between the years 2014 and 2017, based on the access / session variables and their respective averages. By means of Excel, a statistical analysis was performed based on Statistical Process Control (SPC). The research method selected was the case study, with data and information complemented by bibliographical and documentary research. As a result, the research identified that the international scientific journal presents mostly male users with Brazilian or foreign nationality. Moreover, in the stratification of the journal users by sex and titration it was possible to perceive that doctors are responsible for the greater number of records, both male and female. Finally, there is an increase in the number of views in the international scientific journal, thus confirming that there is a significant importance among academic researchers in seeking access to publications made available via the web.

Subspace techniques for task-independent EEG person identification.

There has been a growing interest in studying electroencephalography signals (EEG) as a possible biometric. The brain signals captured by EEG are rich and carry information related to the individual, tasks being performed, mental state, and other channel/measurement noise due to session variability and artifacts. To effectively extract person-specific signatures present in EEG, it is necessary to define a subspace that enhances the biometric information and suppresses other nuisance factors. i-vector and x-vector are state-of-art subspace techniques used in speaker recognition. In this paper, novel modifications are proposed for both frameworks to project person-specific signatures from multi-channel EEG into a subspace. The modified i-vector and x-vector systems outperform baseline i-vector and x-vector systems with an absolute improvement of 10.5% and 15.9%, respectively.

A bilevel framework for joint optimization of session compensation and classification for speaker identification

The i-vector framework based system is one of the most popular systems in speaker identification (SID). In this system, session compensation is usually employed first and then the classifier. For any session-compensated representation of i-vector, there is a corresponding identification result, so that both the stages are related. However, in current SID systems, session compensation and classifier are usually optimized independently. An incomplete knowledge about the session compensation to the identification task may lead to involving uncertainties. In this paper, we propose a bilevel framework to jointly optimize session compensation and classifier to enhance the relationship between the two stages. In this framework, we use the sparse coding (SC) to obtain the session-compensated feature by learning an overcomplete dictionary, and employ the softmax classifier and support vector machine (SVM) in classifying respectively. Moreover, we present a joint optimization of the dictionary and classifier parameters under a discriminative criterion for classifier with conditions for SC. In addition, the proposed methods are evaluated on the King-ASR-010, VoxCeleb and RSR2015 databases. Compared with typical session compensation techniques, such as linear discriminant analysis (LDA) and nonparametric discriminant analysis (NDA), our methods can be more robust to complex session variability. Moreover, compared with the typical classifiers in i-vector framework, i.e. the cosine distance scoring (CDS) and probabilistic linear discriminant analysis (PLDA), our methods can be more suitable for SID (multiclass task).

Prediction of Brain Connectivity Map in Resting-State fMRI Data Using Shrinkage Estimator.

Introduction:In recent years, brain functional connectivity studies are extended using the advanced statistical methods. Functional connectivity is identified by synchronous activation in a spatially distinct region of the brain in resting-state functional Magnetic Resonance Imaging (MRI) data. For this purpose there are several methods such as seed-based correlation analysis based on temporal correlation between different Regions of Interests (ROIs) or between brain’s voxels of prior seed.Methods:In the current study, test-retest Resting State functional MRI (rs-fMRI) data of 21 healthy subjects were analyzed to predict second replication connectivity map using first replication data. A potential estimator is “raw estimator” that uses the first replication data from each subject to predict the second replication connectivity map of the same subject. The second estimator, “mean estimator” uses the average of all sample subjects' connectivity to estimate the correlation map. Shrinkage estimator is made by shrinking raw estimator towards the average connectivity map of all subjects' first replicate. Prediction performance of the second replication correlation map is evaluated by Mean Squared Error (MSE) criteria.Results:By the employment of seed-based correlation analysis and choosing precentral gyrus as the ROI over 21 subjects in the study, on average MSE for raw, mean and shrinkage estimator were 0.2169, 0.1118, and 0.1103, respectively. Also, percent reduction of MSE for shrinkage and mean estimator in comparison with raw estimator is 49.14 and 48.45, respectively.Conclusion:Shrinkage approach has the positive effect on the prediction of functional connectivity. When data has a large between session variability, prediction of connectivity map can be improved by shrinking towards population mean.