Face recognition from digital images is used for surveillance and authentication in cities, organizations, and personal devices. Internet of Things (IoT)-powered face recognition systems use multiple sensors and one or more servers to process data. All sensor data from initial methods was sent to the central server for processing, raising concerns about sensitive data disclosure. The main concern was that all data from all sectors that could contain confidential information was placed in a central server. Federated learning can solve this problem by using several local model training servers for each region and a central aggregation server to form a global model in IoT networks. This article presents a novel approach to optimize data Transfer and convergence time in federated learning for a face recognition task using Non-dominated Sorting Genetic Algorithm II (NSGA II). The aim of the study is to balance the trade-off between training time and model accuracy in a federated learning environment. The results demonstrate the effectiveness of the proposed approach in reducing data Transfer and convergence time, leading to improved performance in face recognition accuracy. This research provides insights for researchers and practitioners to enhance the efficiency of federated learning in real-world applications.

Automatic topic detection seems unavoidable in social media analysis due to big text data which their users generate. Clustering-based methods are one of the most important and up-to-date categories in topic detection. The goal of this research is to have a wide study on this category. Therefore, this paper aims to study the main components of clustering-based-topic-detection, which are embedding methods, distance metrics, and clustering algorithms. Transfer learning and consequently pretrained language models and word embeddings have been considered in recent years. Regarding the importance of embedding methods, the efficiency of five new embedding methods, from earlier to recent ones, are compared in this paper. To conduct our study, two commonly used distance metrics, in addition to five important clustering algorithms in the field of topic detection, are implemented by the authors. As COVID-19 has turned into a hot trending topic on social networks in recent years, a dataset including one-month tweets collected with COVID-19-related hashtags is used for this study. More than 7500 experiments are performed to determine tunable parameters. Then all combinations of embedding methods, distance metrics and clustering algorithms (50 combinations) are evaluated using Silhouette metric. Results show that T5 strongly outperforms other embedding methods, cosine distance is weakly better than other distance metrics, and DBSCAN is superior to other clustering algorithms.

In this paper, the evaluation of the performance of five flood prediction models in the Simineh-Rood River, Lake Urmia basin, Iran, is discussed in detail. To this purpose, the performance of Transfer Function, Saint-Venant equations, Artificial Neural Network, Adaptive Neuro-Fuzzy Inference System, and Support Vector Machine models are evaluated for 2018 and 2019 flood data. Specifically, the models are rated according to their accuracy, computational efficiency, and robustness under different flow regimes and at various forecast times. This now leads to a maximum Nash-Sutcliffe Efficiency of 0.91 for the Saint-Venant equations during the 2019 flood event, followed by ANN with 0.89, ANFIS with 0.87, SVM with 0.85, and lastly, Transfer Function with 0.78. The same is the case for peak flow discharge, which was best predicted by the Saint-Venant model to be 193.80 m³/s while the observed value was 200.83 m³/s. This model maintained its consistency with respect to low, medium, and high flows, where the values of NSE were 0.89, 0.92, and 0.91, respectively. However, compared to the other models, which took 0.5–8 s, it had a much larger computational time, 120 s for a 72-h simulation. The sensitivity analysis returned variable model responses to the quality of the input data; an input variation of 20% reduced the NSE of the Saint-Venant model to 0.73 and that of the Transfer Function to 0.44. This study provides quantitative insight into the choice of flood prediction methods in a semi-arid region, with respect to required accuracy, computational resources, and forecast lead-time.