A Deep-Learning Model for Subject-Independent Human Emotion Recognition Using Electrodermal Activity Sensors.

One of the main objectives of Active and Assisted Living (AAL) environments is to ensure that elderly and/or disabled people perform/live well in their immediate environments; this can be monitored by among others the recognition of emotions based on non-highly intrusive sensors such as Electrodermal Activity (EDA) sensors. However, designing a learning system or building a machine-learning model to recognize human emotions while training the system on a specific group of persons and testing the system on a totally a new group of persons is still a serious challenge in the field, as it is possible that the second testing group of persons may have different emotion patterns. Accordingly, the purpose of this paper is to contribute to the field of human emotion recognition by proposing a Convolutional Neural Network (CNN) architecture which ensures promising robustness-related results for both subject-dependent and subject-independent human emotion recognition. The CNN model has been trained using a grid search technique which is a model hyperparameter optimization technique to fine-tune the parameters of the proposed CNN architecture. The overall concept's performance is validated and stress-tested by using MAHNOB and DEAP datasets. The results demonstrate a promising robustness improvement regarding various evaluation metrics. We could increase the accuracy for subject-independent classification to 78% and 82% for MAHNOB and DEAP respectively and to 81% and 85% subject-dependent classification for MAHNOB and DEAP respectively (4 classes/labels). The work shows clearly that while using solely the non-intrusive EDA sensors a robust classification of human emotion is possible even without involving additional/other physiological signals.

Three-year results following regenerative periodontal surgery of advanced intrabony defects with enamel matrix derivative alone or combined with a synthetic bone graft.

OBJECTIVES: This study aims to compare the clinical outcomes of a combination of enamel matrix derivatives (EMD) and a synthetic bone graft (biphasic calcium phosphate) with EMD alone in wide and deep one- and two-wall intrabony defects 36 months after treatment. MATERIAL AND METHODS: Thirty patients with chronic periodontitis and one wide (≥ 2 mm) and deep (≥ 4 mm) intrabony defect had been recruited in three centres in Germany. During surgery, defects were randomly assigned to EMD/synthetic bone graft (SBG) (test) or EMD (control). Assessments at baseline, after 6, 12 and 36 months, included bone sounding, relative clinical attachment levels, probing pocket depths and recessions. RESULTS: After 36 months, defects in both groups were significantly improved (p < 0.001) with regard to defect fill, attachment gain and probing pocket reduction. In the EMD/SBG group, a mean defect fill of 2.6 mm (±1.7) was measured, and in the EMD group, the defect fill was 2.3 mm (±1.5). A mean gain in clinical attachment of 4.1 mm (±3.6) and 3.8 mm (±2.2) was observed in the test and in the control group, respectively. There were no statistically significant differences in any of the investigated parameters between the two treatment modalities. CONCLUSIONS: The clinical improvements of advanced intrabony defects obtained with both regenerative modalities could be maintained over a period of 3 years. The combination of EMD with SBG did not show any advantage compared to the use of EMD alone.

Clinical outcomes after treatment of periodontal intrabony defects with nanocrystalline hydroxyapatite (Ostim) or enamel matrix derivatives (Emdogain): a randomized controlled clinical trial.

INTRODUCTION: Periodontitis is an inflammatory process in response to dental biofilm and leads to periodontal tissue destruction. The aim of this study was the comparison of outcomes using either an enamel matrix derivative (EMD) or a nanocrystalline hydroxyapatite (NHA) in regenerative periodontal therapy after 6 and 12 months. METHODS: Using a parallel group, prospective randomized study design, we enrolled 19 patients in each group. The primary outcome was bone fill after 12 months. Attachment gain, probing pocket depth (PPD) reduction, and recession were secondary variables. Additionally, early wound healing and adverse events were assessed. Data analysis included test of noninferiority of NHA group (test) compared to EMD group (reference) in bone fill. Differences in means of secondary variables were compared by paired t-test, frequency data by exact χ(2) test. RESULTS: Both groups showed significant bone fill, reduction of PPD, increase in recession, and gain of attachment after 6 and 12 months. No significant differences between groups were found at any time point. Adverse events were comparable between both groups with a tendency of more complaints in the NHA group. CONCLUSION: The clinical outcomes were similar in both groups. EMD could have some advantage compared to NHA regarding patients comfort and adverse events. The trial is registered with ClinicalTrials.gov NCT00757159.

Er:YAG laser treatment in supportive periodontal therapy.

OBJECTIVE: To assess clinical and microbiological outcomes of an Er:YAG laser in comparison with sonic debridement in the treatment of persistent periodontal pockets in a prospective randomized controlled multicentre study design. MATERIAL AND METHODS: A total of 78 patients in supportive periodontal therapy with two residual pockets were included, 58 were available for the whole follow-up period. Root surfaces were instrumented either with a sonic scaler (Sonicflex(®) 2003 L) or with an Er:YAG laser (KEY Laser(®) 3). Clinical attachment levels (CAL), Probing depths (PD), Plaque control record (PCR) and Bleeding on probing (BOP) were assessed at baseline, 13 and 26 weeks after treatment. In addition, microbiological analysis was performed employing a DNA diagnostic test kit (micro-IDent(®) Plus). RESULTS: Probing depths and CAL were significantly reduced in both groups over time (p < 0.05), without significant differences between the groups (p > 0.05). BOP frequency values decreased significantly within both groups (p < 0.05), with no difference between the laser and the sonic treatment (p > 0.05). PCR frequency values did not change during the observation period (p > 0.05). Microbiological analysis failed to expose any significant difference based on treatment group or period. CONCLUSION: Employing both sonic and laser treatment procedures during supportive periodontal care, similar clinical and microbiological outcomes can be expected.

In vitro evaluation of two whitening regimens using color-analyzing methods.

OBJECTIVES: To determine in vitro the effect of prophylaxis before tooth whitening and to evaluate a paint-on home whitening product using two methods of color analysis. METHOD AND MATERIALS: Ninety extracted human maxillary anterior teeth were randomly separated into a prophylaxis group or nonprophylaxis group of 45 teeth. The prophylaxis group received debridement and polishing before whitening. The two groups were randomly separated into three subgroups of 15 teeth each: placebo group, test group (Easy White, Dental Kosmetik), and positive control group (Colgate Simply White, Colgate-Palmolive). The 2-week whitening treatment consisted of applying one of the three gels twice daily according to the manufacturers' instructions. In vitro measurements included tooth color assessment using digital imaging analysis and evaluation of tooth shade by a colorimeter. Measurements were taken at baseline, after prophylaxis, and after whitening. RESULTS: While whitening was effective with or without prophylaxis, prior prophylaxis contributed to improved posttreatment outcomes. Both test gel and positive control gel resulted in greater shade reductions and tooth color improvements compared to placebo gel (P<.05). The positive control gel was not superior to test gel. CONCLUSIONS: Prophylaxis is highly recommended before use of paint-on home whitening gels. Colorimetric measurements and digital imaging analysis with a gray card are options to record the efficacy of whitening products. Digital imaging analysis has advantages: Numeric data can be evaluated, and an image of the outcome of the whitening procedure is available.