Coping with imbalanced data problem in digital mapping of soil classes

An unsolved problem in the digital mapping of categorical soil variables and soil types is the imbalanced number of observations, which leads to reduced accuracy and the loss of the minority class (the class with a significantly lower number of observations compared to other classes) in the final map. So far, synthetic over- and under-sampling techniques have been explored in soil science; however, more efficient approaches that do not have the drawbacks of these techniques and guarantee retention of the minority classes in the produced map are essentially required. Such approaches suggested in the present study for digital mapping of soil classes include machine learning models of ensemble gradient boosting, cost-sensitive learning and one-class classification (OCC) of the minority class combined with multi-class classification. In this regard, extreme gradient boosting (XGB) as an ensemble gradient learner, a cost-sensitive decision tree (CSDT) within the C5.0 algorithm, and a one-class support vector machine combined with multi-class classification (OCCM) were investigated to map eight soil great groups with a naturally imbalanced frequency of observations in northwest Iran. A total of 453 profile data points were used for mapping the soil great groups of the study area. A data split was done manually for each class separately, which resulted in an overall 70% of the data for calibration and 30% for validation. The bootstrapping approach of calibration (with 10 runs) was performed to produce multiple maps for each model. The 10 bootstraps were evaluated against the hold-out validation dataset. The average values of accuracy measures, including Kappa (K), overall accuracy (OA), producer's accuracy (PA) and user's accuracy (UA), were explored. In addition, the results of this study were compared with a previous study in the same area, in which resampling techniques were used to deal with imbalanced data for digital soil class mapping. The findings show that all three suggested methods can deal well with the imbalanced classification problem, with OCCM showing the highest K (= 0.76) and OA (= 82) in the validation stage. Also, this model can guarantee the retention of the minority classes in the final map. Comparing the present approaches with the previous study approach demonstrates that the three newly suggested methods can remarkably increase both overall and individual class accuracy for mapping.     

Evaluation of bone healing in canine tibial defects filled with cortical autograft,commercial-DBM,calf fetal DBM,omentum and omentum-calf fetal DBM

The present study was conducted to compare the effects of xenogenic bovine fetal demineralized bone matrix (DBM), commercial DBM, omentum, omentum-calf fetal DBM, cortical autograft and xenogenic cartilage powder on the healing of tibial defects in a dog model to determine the best material for bone healing. Seven male adult mongrel dogs, weighing 26.2 ± 2.5 kg, were used in this study. Seven holes with a diameter of 4-mm were created and then filled with several biomaterials. Radiographs were taken postoperatively on day 1 and weeks 2, 4, 6, 8. The operated tibias were removed on the 56th postoperative day and histopathologically evaluated. On postoperative days 14, 42 and 56, the lesions of the control group were significantly inferior to those in the other group (p < 0.05). On the 28th postoperative day, the autograft group was significantly superior to the control and omentum groups (p < 0.05). Moreover, calf fetal DBM was significantly superior to the control group. There was no significant difference between the histopathological sections of all groups. Overall, the omentum and omentum-DBM groups were superior to the control group, but inferior to the autograft, commercial-DBM, calf fetal DBM and calf fetal cartilage groups.     

Comparison of Synthetic Oviductal Fluid and G1/G2 Medium under Low‐1 Oxygen Atmosphere on Embryo Production and Pregnancy Rates in Nelore (Bos indicus) Cattle

In this work, we evaluated whether embryo development and pregnancy rates would be affected by culturing bovine Bos indicus embryos in Synthetic Oviductal Fluid with amino acids (SOFaa) or G1/G2 sequential medium under a low‐oxygen atmosphere. Using Ovum Pick Up, we obtained 1,538 oocytes, divided into G1/G2 (n = 783) and SOFaa (n = 755). No difference was observed for blastocyst development among the groups (27.8% ± 14.6 and 34.9% ± 20.0 for G1/G2 and SOFaa respectively, p > 0.05). Transferring the embryos (n = 450) from both groups to recipients resulted in similar pregnancy rates for the G1/G2 (38.4% n = 78/203) compared to the SOFaa (39.7% n = 98/247). Our findings confirm that Bos indicus embryos cultured in SOFaa and G1/G2 under low‐oxygen atmosphere have similar in vitro (blastocyst rate) and in vivo (pregnancy rate) developmental capacity. However, embryos cultured in G1/G2 medium have higher cleavage than those cultured in SOFaa medium.     

Repeatability of ultrasound-predicted percentage of intramuscular fat in feedlot cattle.

We used data from 144 bulls, heifers, and steers to determine the repeatability of ultrasound-predicted percentage of intramuscular fat and to study the effect of repeated measurements on the standard error of prediction. Animals were scanned at an average age of 433 d by a certified technician. Individual bulls, heifers, and steers were scanned five to six times each with two Aloka 500-V machines, and the percentage of intramuscular fat was predicted from two regions of interest within an image. Variance components and repeatability values were computed for the overall data and by machine, region of interest, and sex. Animals were broadly divided into two groups based on mean ultrasound-predicted percentage of intramuscular fat. Variance components and repeatability values were then estimated within each group. The overall repeatability of ultrasound-predicted percentage of intramuscular fat was .63 +/- .03. Differences in the repeatability values between machines and between regions of interest were not different from zero (P > .05). Bulls showed a lower within-animal SD of .82% as compared to .97 and 1.02% for steers and heifers, respectively. However, steer ultrasound-predicted percentage of intramuscular fat measures were more repeatable (P < .05) than those of bulls and heifers. The difference in repeatability between bull and heifer measures was not important (P > .05). Animals with mean ultrasound-predicted percentage of intramuscular fat less than 4.79% showed less repeatable measures (P < .05) than those with means above 4.79%. The image variance contributed to nearly 70% of the total variance of observations within an animal. Standard error of animal mean measures showed a 50% reduction when the number of images per animal increased to four. Therefore, we concluded that increasing the number of images per animal plays a more significant role in reducing the standard error of prediction than taking multiple measurements within a single image.     

Comparative study on the efficiency of dry and green manuring of certain plant leaves againstMeloidogyne javanica andRotylenchulus reniformis infecting sunflower

Five different dry and five green plant leaves were tested against Meloidogyne javanica and Rotylenchulus reniformis, as bio-agents in controlling these nematodes infecting sunflower. Data generally, indicated that all the tested manures significantly (P≤0.05) reduced the total number of nematodes in root and soil. The best materials were datura dry leaves on M. javanica and lime dry leaves on R. reniformis which gave very good results against nematodes (86.4 and 95.1% female reduction, respectively). Plant growth was significantly (P≤0.05) better, in most cases, in shoots, roots and flowering discs weight.     

Prevalence,intensity and histopathology of Zeylanicobdella arugamensis infestation on groupers reared on different aquaculture systems

The marine leech, Zeylanicobdella arugamensis, is a major threat to aquaculture in grouper-producing countries including Indonesia. This study aimed at investigating prevalence, intensity and histopathology of the ectoparasite in humpback and hybrid groupers cultured in different rearing systems. A total of 260 groupers (60 humpback groupers and 200 hybrid groupers) were used for samples. The marine leech was observed on skin, fins, gills and mouth, followed by histopathological assay on the skin tissue. The results showed that prevalence of the leech in both groupers was higher when they were cultured in the floating net cages compared with the hatchery, p < .05. Furthermore, humpback grouper had a higher prevalence than hybrid grouper when they were cultured in a similar system, p < .05. Meanwhile, there was no significant difference in intensity between the two groupers, p > .05. Within the hybrid groupers, the highest prevalence was obtained from hybrid groupers reared in the earthen ponds. Histopathological studies showed that the infected groupers exhibited inflammation, congestion and erosion of the epidermis layer. Hybrid grouper had more severe histopathological lesions in the skin tissues. These results suggested that species and type of aquaculture system had significantly determined the prevalence, intensity and severity of lesion in Z. arugamensis infestation.