RESUMEN
Seed-borne diseases reduce not only the seed germination and seedling growth but also seed quality, resulting in the significant yield loss in crop production. Plant seed harbors diverse microbes termed endophytes other than pathogens inside it. However, their roles and application to agricultures were rarely understood and explored to date. Recently, we had isolated from soybean seeds culturable endophytes exhibiting in-vitro antagonistic activities against common bacterial and fungal seed-borne pathogens. In this study, we evaluated effects of seed treatment with endophytes on plant growth and protection against the common seed-borne pathogens: four fungal pathogens (Cercospora sojina, C. kikuchii, Septoria glycines, Diaporthe eres) and two bacterial pathogens (Xanthomonas axonopodis pv. glycines, Pseudomonas syringae pv. tabaci). Our experiments showed that treatment of soybean seeds with seed endophytes clearly offer protection against seed-borne pathogens. We also found that some of the endophytes promote plant growth in addition to the disease suppression. Taken together, our results demonstrate agricultural potential of seed endophytes in crop protection.
RESUMEN
Animal activity recognition (AAR) using wearable sensor data has gained significant attention due to its applications in monitoring and understanding animal behavior. However, two major challenges hinder the development of robust AAR models: domain variability and the difficulty of obtaining labeled datasets. To address this issue, this study intensively investigates the impact of unsupervised domain adaptation (UDA) for AAR. We compared three distinct types of UDA techniques: minimizing divergence-based, adversarial-based, and reconstruction-based approaches. By leveraging UDA, AAR classifiers enable the model to learn domain-invariant features, allowing classifiers trained on the source domain to perform well on the target domain without labels. We evaluated the effectiveness of UDA techniques using dog movement sensor data and additional data from horses. The application of UDA across sensor positions (neck and back), sizes (middle-sized and large-sized), and gender (female and male) within the dog data, as well as across species (dog and horses), exhibits significant improvements in the classification performance and reduced the domain discrepancy. The results highlight the potential of UDA to mitigate the domain shift and enhance AAR in various settings and for different animal species, providing valuable insights for practical applications in real-world scenarios where labeled data is scarce.
RESUMEN
Accelerometer data collected from wearable devices have recently been used to monitor physical activities (PAs) in daily life. While the intensity of PAs can be distinguished with a cut-off approach, it is important to discriminate different behaviors with similar accelerometry patterns to estimate energy expenditure. We aim to overcome the data imbalance problem that negatively affects machine learning-based PA classification by extracting well-defined features and applying undersampling and oversampling methods. We extracted various temporal, spectral, and nonlinear features from wrist-, hip-, and ankle-worn accelerometer data. Then, the influences of undersampilng and oversampling were compared using various ML and DL approaches. Among various ML and DL models, ensemble methods including random forest (RF) and adaptive boosting (AdaBoost) exhibited great performance in differentiating sedentary behavior (driving) and three walking types (walking on level ground, ascending stairs, and descending stairs) even in a cross-subject paradigm. The undersampling approach, which has a low computational cost, exhibited classification results unbiased to the majority class. In addition, we found that RF could automatically select relevant features for PA classification depending on the sensor location by examining the importance of each node in multiple decision trees (DTs). This study proposes that ensemble learning using well-defined feature sets combined with the undersampling approach is robust for imbalanced datasets in PA classification. This approach will be useful for PA classification in the free-living situation, where data imbalance problems between classes are common.
RESUMEN
Gom-chwi (Ligularia fischeri) is severely infected with Phytophthora drechsleri, the causal organism of Phytophthora root rot, an economically important crop disease that needs management throughout the cultivation period. In the present study, Phytophthora root rot was controlled by using bacterial isolates from rhizosphere soils collected from various plants and screened for antagonistic activity against P. drechsleri. A total of 172 bacterial strains were isolated, of which, 49 strains showed antagonistic activities by dual culture assay. In the seedling assay, six out of the 49 strains showed a predominant effect on suppressing P. drechsleri. Among the six strains, the ObRS-5 strain showed remarkable against P. drechsleri when treated with seed dipping or soil drenching. The ObRS-5 strain was identified as Enterobacter asburiae based on 16S ribosomal RNA gene sequences analysis. The bacterial cells of E. asburiae ObRS-5 significantly suppressed sporangium formation and zoospore germination in P. drechsleri by 87.4% and 66.7%, respectively. In addition, culture filtrate of E. asburiae ObRS-5 also significantly inhibited sporangium formation and zoospore germination by 97.0% and 67.6%, respectively. Soil drenched bacterial cells, filtrate, and culture solution of E. asburiae ObRS-5 effectively suppressed Phytophthora root rot by 63.2%, 57.9%, and 81.1%, respectively. Thus, E. asburiae ObRS-5 could be used as a potential agent for the biological control of Phytophthora root rot infecting gom-chwi.
