WCL: Client Selection in Federated Learning with a Combination of Model Weight Divergence and Client Training Loss for Internet Traffic Classification

Internet traffic classification (TC) is a critical technique in network management and is widely applied in various applications. In traditional TC problems, the edge devices need to send the raw traffic data to the server for centralized processing, which not only generates a lot of communication overhead but also leads to the privacy leakage and information security issues. Federated learning (FL) is a new distributed machine learning paradigm that allows multiple clients to train a global model collaboratively without raw traffic data sharing. The TC in a FL framework preserves the user privacy and data security by keeping the raw traffic data local. However, because of the different user behaviours and user preferences, traffic data heterogeneity emerges. The existing FL solutions introduce bias in model training by averaging the local model parameters from all heterogeneous clients, which degrades the classification accuracy of the learnt global classification model. To improve the classification accuracy in heterogeneous data environment, this paper proposes a novel client selection algorithm, namely, WCL, in federated paradigm based on a combination of model weight divergence and local model training loss. Extensive experiments on the public traffic dataset QUIC and ISCX have proved that the WCL algorithm obtains, compared to CMFL, superior performance in improving model accuracy and convergence speed on low heterogeneous traffic data and high heterogeneous traffic data, respectively.

Effects of Dipsacus asperoides and Phlomis umbrosa Extracts in a Rat Model of Osteoarthritis

The implementation of the Nagoya Protocol highlighted the importance of identifying alternative herbal products that are as effective as traditional medicine. Dipsacus asperoides and Phlomis umbrosa, two species used in the Korean medicine ‘Sok-dan’, are used for the treatment of bone- and arthritis-related diseases, and they are often mixed or misused. To identify herbal resources with similar efficacy, we compared the effects of D. asperoides extract (DAE) and P. umbrosa extract (PUE) on osteoarthritis (OA) in a monosodium iodoacetate (MIA)-induced OA rat model. Weight-bearing distribution, serum cytokines, histopathological features, and the expression of matrix metalloproteinases (MMPs) of knee joint tissues were examined in the OA rats treated with DAE and PUE (200 mg/kg) for 21 days. DAE and PUE restored weight-bearing distribution, inhibited the production of serum cytokines, and alleviated the histopathological features of the OA knee tissue. DAE or PUE treatment decreased OA-induced overexpression of MMP-2, MMP-9, and MMP-13 in the knee joint tissue. This study demonstrated the efficacy of both DAE and PUE in an MIA-induced OA model, providing a basis for the clinical use of these products in traditional Korean medicine.

Anti-Obesity Effect of Hot Water Extract of Barley Sprout through the Inhibition of Adipocyte Differentiation and Growth

Barley sprouts are known to have several effective physiological activities. In this study, the anti-obesity effect of a barley sprout hot water extract (BSE) was confirmed. Saponarin was quantitatively analyzed in BSE using HPLC, and the inhibitory effect on 3T3-L1 pre-adipocyte differentiation into adipocytes was confirmed by Oil Red O staining, TG assay, and Western blotting. In addition, the inhibitory effect of BSE on adipocyte growth was confirmed through glucose uptake and lipolysis of adipocytes. C57/BL/6N mice were induced to obesity with a high-fat diet, and BSE was administered to confirm the effect on an animal model. Weight gain, morphological changes in adipose tissue, changes in the food efficiency ratio, and blood biochemical changes were observed, and an improvement effect on fatty liver was confirmed. As a result, the anti-obesity effect of BSE was confirmed in vitro, and it was confirmed that this effect was also effective in vivo and that it could be helpful in the treatment of obesity-related diseases.

Instance Segmentation of Microscopic Foraminifera

Foraminifera are single-celled marine organisms that construct shells that remain as fossils in the marine sediments. Classifying and counting these fossils are important in paleo-oceanographic and -climatological research. However, the identification and counting process has been performed manually since the 1800s and is laborious and time-consuming. In this work, we present a deep learning-based instance segmentation model for classifying, detecting, and segmenting microscopic foraminifera. Our model is based on the Mask R-CNN architecture, using model weight parameters that have learned on the COCO detection dataset. We use a fine-tuning approach to adapt the parameters on a novel object detection dataset of more than 7000 microscopic foraminifera and sediment grains. The model achieves a (COCO-style) average precision of 0.78 on the classification and detection task, and 0.80 on the segmentation task. When the model is evaluated without challenging sediment grain images, the average precision for both tasks increases to 0.84 and 0.86, respectively. Prediction results are analyzed both quantitatively and qualitatively and discussed. Based on our findings we propose several directions for future work and conclude that our proposed model is an important step towards automating the identification and counting of microscopic foraminifera.

Instance Segmentation of Microscopic Foraminifera

Foraminifera are single-celled marine organisms that construct shells that remain as fossils in the marine sediments. Classifying and counting these fossils are important in e.g. paleo-oceanographic and -climatological research. However, the identification and counting process has been performed manually since the 1800s and is laborious and time-consuming. In this work, we present a deep learning-based instance segmentation model for classifying, detecting, and segmenting microscopic foraminifera. Our model is based on the Mask R-CNN architecture, using model weight parameters that have learned on the COCO detection dataset. We use a fine-tuning approach to adapt the parameters on a novel object detection dataset of more than 7000 microscopic foraminifera and sediment grains. The model achieves a (COCO-style) average precision of 0.78±0.00 on the classification and detection task, and 0.80±0.00 on the segmentation task. When the model is evaluated without challenging sediment grain images, the average precision for both tasks increases to 0.84±0.00 and 0.86±0.00, respectively. Prediction results are analyzed both quantitatively and qualitatively and discussed. Based on our findings we propose several directions for future work, and conclude that our proposed model is an important step towards automating the identification and counting of microscopic foraminifera.

122 A Mechanistic Model of Growth and Amino Acid Deposition in the Pregnant Sow: Model Development, Evaluation, and Application

A mechanistic model was developed with the objective to characterize weight gain and essential amino acid (EAA) deposition in the different tissue pools that make up the pregnant sow: placenta, allantoic fluid, amniotic fluid, fetus, uterus, mammary gland, and maternal body were considered. The data used in this modelling approach were obtained from published scientific articles reporting weights, crude protein (CP), and EAA composition in the previously mentioned tissues; studies reporting not less than 5 datapoints across gestation were considered. A total of 12 scientific articles published between 1977 and 2020 were selected for the development of the model and the model was validated using 11 separate scientific papers. The model consists of three connected sub-models: protein deposition (Pd) model, weight gain model, and EAA deposition model. Weight gain, Pd, and EAA deposition curves were developed with nonparametric statistics using splines regression. The validation of the model showed a strong agreement between observed and predicted growth (r2 = 0.92, root mean square error = 3%). The proposed model also offered descriptive insights into the weight gain and Pd during gestation. The model suggests that the definition of time-dependent Pd is more accurately described as an increase in fluid deposition during mid-gestation coinciding with a reduction in Pd. In addition, due to differences in CP composition between pregnancy-related tissues and maternal body, Pd by itself may not be the best measurement criteria for the estimation of EAA requirement in pregnant sows. The proposed model also captures the negative maternal Pd that occurs in late gestation and indicates that litter size influences maternal tissue mobilization more than parity. The model predicts that the EAA requirements in early and mid-gestation are 75, 55 and 50% lower for primiparous sows than parity 2, 3 and 4+ sows, respectively, which suggest the potential benefits of parity segregated feeding.

Weight effects on stress: lexicon and grammar

This thesis examines weight effects on stress and proposes a probabilistic approach based on the notion that weight is gradient, not categorical. Arguments for this proposal are divided into three main chapters, which examine and statistically model weight in the lexicon (Chapter 1), weight in the grammar (Chapter 2), and the interaction of weight and footing (Chapter 3). The statistical analyses in Chapters 2 and 3 also discuss how our linguistic expectations regarding weight effects can be incorporated in statistical models through the use of mildly informative priors, and to what extent the fit of such models compare with that of models based on non-informative priors.

Food Chain Length Associated with Environmental Factors Affected by Large Dam along the Yangtze River

Food chain length (FCL) is a critical measure of food web complexity that influences the community structure and ecosystem function. The FCL of large subtropical rivers affected by dams and the decisive factors are far beyond clear. In this study, we used stable isotope technology to estimate the FCL of fish in different reaches of the main stream in the Yangtze River and explored the key factors that determined the FCL. The results showed that FCL varied widely among the studied areas with a mean of 4.09 (ranging from 3.69 to 4.31). The variation of FCL among river sections in the upstream of the dam was greater than that in the downstream. Regression analysis and model selection results revealed that the FCL had a significant positive correlation with ecosystem size as well as resource availability, and FCL variation was largely explained by ecosystem size, which represented 72% of the model weight. In summary, our results suggested that ecosystem size plays a key role in determining the FCL in large subtropical rivers and large ecosystems tend to have a longer food chain. Additionally, the construction of the Three Gorges Dam has been speculated to increase the FCL in the impoundment river sections.