Browsing by Author "Dias, Jorge"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
- Comparing Bayesian Networks to Classify Facial ExpressionsPublication . Simplício, Carlos; Prado, José; Dias, JorgeIn this paper are presented two distinct Bayesian networks to analyse human beings' facial expressions. Both classifiers are completely defined: structure of the networks, belief variables and respective events, likelihoods, initial priors and procedure to change dynamically priors. The performance (relatively to the convergence) of the two approaches is compared. For both networks, the classification is done associating the facial expression to the probabilities of five emotional states: anger, fear, happy, sad and neutral. A justification for the usage of this set is presented: it is based in emotional states presented by human beings during social relationships. Classifiers as these described here can be used in Human Robot Interation. We believe that this interaction shall be done in a similar way of that used by human beings to communicate between them and, after all, facial expressions is one of the main non-verbal means of communication used by human.
- Evaluation of antimicrobials residues in farmed gilthead seabream (Sparus aurata) after administration through medicated feedPublication . Rosa, João; Leston, Sara; Castro, Maria; Freitas, Andreia; Barbosa, Jorge; Pardal, Miguel Ângelo; Rema, Paulo; Dias, Jorge; Ramos, FernandoThe use of antimicrobials in aquaculture is a well-known fact and merits the focus of the scientific community. In the present study, five drugs (oxytetracycline, sulfadiazine, trimethoprim, oxolinic acid and flumequine) were selected to assess their retention in muscle tissues from gilthead seabream (Sparus aurata). Fish were placed in 150 L tanks at 18 °C, and fed for 7 days with experimental diets containing two concentrations of each antimicrobial (ranging from 5.51 to 131.16 mg kg−1). Edible tissues were then analyzed through a validated multi-class quantification method (UHPLC-MS/MS). The results indicate that sulfadiazine concentrations were the highest immediately after the feeding period and decreased towards day 3. Flumequine was only detected on the first day with concentrations below the MRL. Both trimethoprim and oxolinic acid concentrations were below the MRLs 3 days after the feeding period was over (oxolinic acid was not detected in muscle samples at day 14 for prophylaxis and day 28 for both treatments). Oxytetracycline residues in muscle tissues were the highest through time, with concentrations above the MRL for 7 days (Cday7 of 111.2 and 157.2 μg kg−1 for both dosages). Results suggest that these antimicrobials can be present in gilthead seabream muscle samples for longer periods than previously reported, when realistic conditions are tested. With the exception of oxytetracycline, concentrations were below the MRLs established 3 days after the feeding trial was over meaning that adverse effects related to human consumption are not likely. Nevertheless, allergic reactions or resistance to antimicrobials can be developed if low concentrations of such compounds are ingested on a frequent basis, as is the case of the Mediterranean diet.
- A Face Attention Technique for a Robot Able to Interpret Facial ExpressionsPublication . Simplício, Carlos; Prado, José; Dias, JorgeAutomatic facial expressions recognition using vision is an important subject towards human-robot interaction. Here is proposed a human face focus of attention technique and a facial expressions classifier (a Dynamic Bayesian Network) to incorporate in an autonomous mobile agent whose hardware is composed by a robotic platform and a robotic head. The focus of attention technique is based on the symmetry presented by human faces. By using the output of this module the autonomous agent keeps always targeting the human face frontally. In order to accomplish this, the robot platform performs an arc centered at the human; thus the robotic head, when necessary, moves synchronized. In the proposed probabilistic classifier the information is propagated, from the previous instant, in a lower level of the network, to the current instant. Moreover, to recognize facial expressions are used not only positive evidences but also negative.
- Robot Emotional State through Bayesian Visuo-Auditory PerceptionPublication . Prado, José Augusto; Simplício, Carlos; Dias, JorgeIn this paper we focus on auditory analysis as the sensory stimulus, and on vocalization synthesis as the output signal. Our scenario is to have one robot interacting with one human through vocalization channel. Notice that vocalization is far beyond speech; while speech analysis would give us what was said, vocalization analysis gives us how was said. A social robot shall be able to perform actions in different manners according to its emotional state. Thus we propose a novel Bayesian approach to determine the emotional state the robot shall assume according to how the interlocutor is talking to it. Results shows that the classification happens as expected converging to the correct decision after two iterations.
- Tissue depletion of five antibiotic residues in farmed European seabass (Dicentrarchus labrax)Publication . Rosa, João; Leston, Sara; Freitas, Andreia; Barbosa, Jorge; Rema, Paulo; Dias, Jorge; Lemos, Marco F. L.; Pardal, Miguel Ângelo; Ramos, FernandoConcerns about antibiotic use led to stricter legislations and overall better practices in aquaculture production. However, depletion time periods in tissues vary greatly with different antimicrobials, fish species, or experimental setup. In the present work, five drugs (sulfadiazine (SDZ), trimethoprim (TRI), flumequine (FLU), oxolinic acid (OXO), and oxytetracycline (OTC)) were incorporated into medicated feed, and their retention in European seabass muscle tissues assessed. Juveniles were placed in 300 L tanks at 18 °C and were manually fed with medicated feeds for a 7 day period (two concentrations per antimicrobial, ranging from 6 to 220 mg kg−1 , which were based on previous studies on the occurrence of these antimicrobials). Residues were analyzed through a multi-class quantification method (UHPLC-MS/MS). Data on residues concentration through time followed a one-compartment model, with TRI concentrations above the established Maximum Residue Level (MRL) throughout the experiment. Similarly, OTC concentrations at the highest dose were also above 100 μg kg−1 up to 14 days after the medication period. Results obtained for TRI may indicate the presence of a dose dependency for this antimicrobial. FLU concentrations in muscle samples were the lowest through time (Cday7 of 279.70 and 386.63 μg kg−1 , for prophylactic and therapeutic treatments, respectively). Half-life values of 14.37, 10.87, 5.36, 7.20, and 27.22 h (prophylactic treatment), and 20.95, 8.41, 5.61, 11.22, and 17.99 h (therapeutic treatment), were determined for SDZ, TRI, FLU, OXO, and OTC, respectively. Withdrawal times of 0, 2, and 5 days were determined for FLU, OXO, and SDZ, but sampling times for OTC and TRI should be longer, since antimicrobial concentrations were above the MRL 14 days after the end of the feeding period with medicated feed. Therefore, special attention should be given since they are the most used antibiotics in aquaculture and European seabass plays a major part in human nutrition in the Mediterranean region.