Hybrid Model-Based Emotion Contextual Recognition for Cognitive Assistance Services.

Endowing ubiquitous robots with cognitive capabilities for recognizing emotions, sentiments, affects, and moods of humans in their context is an important challenge, which requires sophisticated and novel approaches of emotion recognition. Most studies explore data-driven pattern recognition techniques that are generally highly dependent on learning data and insufficiently effective for emotion contextual recognition. In this article, a hybrid model-based emotion contextual recognition approach for cognitive assistance services in ubiquitous environments is proposed. This model is based on: 1) a hybrid-level fusion exploiting a multilayer perceptron (MLP) neural-network model and the possibilistic logic and 2) an expressive emotional knowledge representation and reasoning model to recognize nondirectly observable emotions; this model exploits jointly the emotion upper ontology (EmUO) and the n-ary ontology of events HTemp supported by the NKRL language. For validation purposes of the proposed approach, experiments were carried out using a YouTube dataset, and in a real-world scenario dedicated to the cognitive assistance of visitors in a smart devices showroom. Results demonstrated that the proposed multimodal emotion recognition model outperforms all baseline models. The real-world scenario corroborates the effectiveness of the proposed approach in terms of emotion contextual recognition and management and in the creation of emotion-based assistance services.

Echographic renal dimensions can predict glomerular filtration rate of potential living kidney donors.

In potential living kidney donors, glomerular filtration rate (GFR) is often evaluated from the creatinine clearance (Ccr) or is predicted using formulas based on serum creatinine (SCr) or cystatin C (SCys) concentration. Ultrasonography is used to evaluate renal structure and dimensions. The objective of the present study was to evaluate the possibility of estimation of GFR from echographic renal dimensions in 66 potential live kidney donors (46 women and 20 men; age range, 25-73 years). The GFR was measured as the renal clearance of technetium 99m diethylenetriamine pentaacetic acid. The GFR was also estimated from the SCr concentration using the Cockcroft-Gault (CG-Ccr) and Modification of Diet in Renal Disease (MDRD-GFR) formulas and from SCys (Cys-GFR). Renal diameters were measured using conventional gray-scale renal ultrasound to estimate total and parenchymal renal volume using ellipsoid formulas. The GFR was predicted from renal dimensions on the basis of their relationship to measured GFR. Estimates of GFR obtained using renal volume more close correlated with measured GFR than did CG-Ccr, MDRD-GFR, or Cys-GFR. The mean difference from measured GFR was null. The GFR estimated from renal volume demonstrated better agreement with measured GFR and a lower prediction error vs values from the other prediction formulas (18.3 vs 22-34 mL/min). The GFR values predicted from renal volume were quite accurate as indicators of GFR less than 80 mL/min. In potential living kidney donors, sonographic renal volume provided more accurate estimates of GFR, with lower prediction error, compared with formulas based on SCr or SCys.

Living kidney transplantation: evaluation of renal function and morphology of potential donors.

The evaluation of potential living kidney donors requires an accurate study of renal function and morphology. The gold standard to assess renal function is the measurement of glomerular filtration rate (GFR). However, GFR is often estimated from serum creatinine (SCr), cystatin C (SCys), or creatinine clearance (CCr). Otherwise, GFR is predicted using formulas based on SCr or SCys. Ultrasound scanning evaluates morphology and dimensions, while scintigraphy provides information on morphofunctional symmetry of kidneys. The aim of this study in 79 potential donors was to assess the accuracy of the tests employed to estimate GFR and the utility of renal ultrasound and scintigraphy for morphofunctional evaluation of potential donors. GFR (clearance of (99m)Tc-DTPA) was compared with estimates obtained with Cockcroft and Gault (CG-CCr) and Modification of Diet in Renal Disease (MDRD-GFR) formulas, and from SCys (Cys-GFR). The correlation with GFR was statistically significant for SCys and for all estimates, but not for SCr. CCr showed a poor agreement with GFR, with a large range of agreement and a marked and significant overestimation of GFR (33.8 mL/min). The accuracy of CG-CCr and MDRD-GFR as indicators of a GFR < 80 mL/min was better than that of Cys-GFR and CCr. However, their mean prediction errors versus GFR were relevant. Renal dimensions, particularly renal volume, showed a good correlation with GFR. The correlation was higher than that of all prediction equations. The direct measurement of GFR remains the reference method to assess renal function in potential kidney donors. The measurement of renal dimensions can provide useful information also on renal function.

Kidney dimensions at sonography are correlated with glomerular filtration rate in renal transplant recipients and in kidney donors.

The gold standard to assess renal function is the measurement of glomerular filtration rate (GFR). For practical reasons, renal function is often evaluated from serum creatinine (S Cr) or cystatin C (S Cys), and GFR is predicted from SCr. Ultrasound scanning of the kidneys is used only to evaluate renal morphology. The aim of this study was to evaluate the relationship between sonographic renal dimensions and GFR in renal transplant recipients and in kidney donors. GFR (urinary clearance of (99m)Tc-DTPA), S Cr, and S Cys were measured in 33 donors (28 females [F], 5 males [M]; SCr, 0.81-1.90 mg/dL) and 30 recipients (8 F, 22 M; SCr, 0.96-2.42 mg/dL). GFR was also predicted using the Cockcroft and Gault (CG) formula and with the simplified Modification of Diet in Renal Disease (MDRD) formula. Length, width, and depth of kidneys and renal sinus were measured using renal sonography. Among sonographic measurements, kidney length showed the best correlation with GFR. A closer correlation with GFR was found in donors (r = 0.639; P < .00007) than in recipients (r = 0.511; P < .005). In either case, the correlation of kidney length with GFR was greater than that of S Cr or S Cys, and similar to that of CG or MDRD GFR. Accuracy of kidney length as an indicator of GFR impairment was not statistically different from laboratory tests. Only in donors did CG show better accuracy. In conclusion, renal dimensions at sonography closely correlated with GFR. Thus, renal sonography can give information also on the function of the renal graft and of the remaining kidney of living donors.