Application of Bayesian networks to the prediction of the AMEn: a new methodology in broiler nutrition.

Designing balanced rations for broilers depends on precise knowledge of nitrogen-corrected apparent metabolizable energy (AMEn) and the chemical composition of the feedstuffs. The equations that include the measurements of the chemical composition of the feedstuff can be used in the prediction of AMEn. In the literature, there are studies that obtained prediction equations through multiple regression, meta-analysis, and neural networks. However, other statistical methodologies with promising potential can be used to obtain better predictions of energy values. The objective of the present study was to propose and evaluate the use of Bayesian networks (BN) to the prediction of the AMEn values of energy and protein feedstuffs of vegetable origin used in the formulation of broiler rations. In addition, verify that the predictions of energy values using this methodology are the most accurate and, consequently, are recommended to Animal Science professionals area for the preparation of balanced feeds. BN are models that consist of graphical and probabilistic representations of conditional and joint distributions of the random variables. BN uses machine learning algorithms, being a methodology of artificial intelligence. The bnlearn package in R software was used to predict AMEn from the following covariates: crude protein, crude fiber, ethereal extract, mineral matter, as well as food category, i.e., energy (corn, corn by-products, and others) or protein (soybean, soy by-products, and others) and the type of animal (chick or cockerel). The data come from 568 feeding experiments carried out in Brazil. Additional data from metabolic experiments were obtained from the Federal University of Lavras (UFLA) - Lavras, Minas Gerais, Brazil. The model with the highest accuracy (mean squared error = 66529.8 and multiple coefficients of determination = 0.87) was fitted with the max-min hill climbing algorithm (MMHC) using 80% and 20% of the data for training and test sets, respectively. The accuracy of the models was evaluated based on their values of mean squared error, mean absolute deviation, and mean absolute percentage error. The equations proposed by a new methodology in avian nutrition can be used by the broiler industry in the determination of rations.

Inclusion of Madagascar cockroach (Gromphadorhina portentosa) meal in the diet of cockatiels (Nymphicus hollandicus) in captivity: Influences on offspring development.

The use of unconventional food for animals is becoming more common. The objective was to evaluate the inclusion of Madagascar cockroach (Gromphadorhina portentosa) meal in the diet of cockatiel (Nymphicus hollandicus) chicks in captivity. Twenty-eight cockatiel chicks were used during 90 days of experiment. The animals were divided into two groups: a control group (receiving commercial feed + seed mixture) and a test group (receiving a control diet supplemented with Madagascar cockroach meal). The cockroach meal was mixed into commercial feed at a ratio of 14:1 (commercial feed: cockroach meal; 6.6% inclusion). Parents of the chicks were fed the experimental diets 30 days before egg laying to evaluate the influence of the cockroach meal on offspring development in the nest (1 to 30 days of age). Body development of the birds was evaluated every three days from the first to the 30th day of age and then every 15 days from the 31st to the 90th day of age. The cockroach meal did not influence (P > .05) the growth characteristics, body weight, total length or length of the animal's beaks, wings or tails, but increased seed consumption from the 31st to the 90th day of age. It is concluded that the cockroach meal can be used in the diet of growing cockatiels at an addition level of 6.6%.

Influence of different types of lamps on the reproductive development of male Japanese quail (Coturnix coturnix japonica).

Reproductive tract development during puberty is critical to reproductive performance, and the light is crucial in this process in birds. However, in male quail, there is little information on the effects of types of lamps, more specifically the wavelength emitted. Thus, the objective was to evaluate the effects of types of lamps on the reproductive performance of male Japanese quail (Coturnix coturnix japonica). Two hundred and forty male quail were exposed to six different types of lamp (incandescent, white fluorescent, or blue, white, red or green LED). The experimental design was completely randomized with six treatments and five replicates of one quail. Quail were slaughtered on days 35, 47, 57, 71 and 123 to evaluate the development of testes. On day 117, semen samples were analyzed and fertilized eggs were incubated. Body weight of the quails was influenced (P < 0.01) by lamps only until the 47 days of age. Higher body weight until this age were observed with incandescent, blue and green LED bulbs. Fluorescent and red LED bulbs propitiated (P < 0.05) early testicular development of quails but, at 57 days of age, higher testicular development was obtained (P < 0.01) whit white LED bulbs. Lower testicular development was observed (P < 0.01) at 123 days of age with the red LED. No influence of different types of lamps was observed (P > 0.05) on the quality of semen nor on the fertility rates of quail. It is concluded that lamps can influence the histological reproductive characteristics of male quails, but without influencing the semen quality. Fluorescent bulbs and red LED seem to anticipate the sexual maturity, but the white LED results in higher testicular development at 57 days of age.

Effect of the type of farrowing room on the welfare and productive performance of lactating sows and of piglets during tropical winter.

The objective of this study was to evaluate the behavior and performance of sows and piglets kept in different types of farrowing rooms: conventional farrowing room with jugglers and cages (CFR), CFR with a heated floor for the piglets alongside the sows (CFR+HF) and semi-outdoor farrowing room without a cage or heating floor but with access to a fenced field (SFR) during the tropical winter. Twenty-seven multiparous sows were allocated in three treatments and nine repetitions during 21 days. The relative humidity was higher at CFR and CFR+HF. The temperature of thigh and chest in contact with the floor and the neck were higher (P<0.01) in conventional systems. Sows maintained in the CFR spent (P<0.01) more time feeding and drinking. The heating floor increased (P<0.01) the nursing behavior but did not affect (P>0.09) the sows' and piglets' performances. SFR decreased the backfat thickness (P=0.03) and lactation efficiency, but did not affect milk production (P>0.12) or piglet performance (P>0.09). It is concluded that during tropical winter, conventional farrowing systems ensure better piglet performance compared to SFR but this last seems to improve the behavior of sows. The heating floor favors nursing and does not affect the welfare of sows.