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.

Automatic keyphrase generation plays an important role in many text analysis and natural language processing tasks. Many existing methods are bound to select keyphrases from the terms and phrases that are present in the target text. This handicap could be overcome using sequence-to-sequence methods. However, many such methods need huge datasets for training which pose a challenge for low-resource languages such as Persian. Transfer learning where a pre-trained model is adapted to a new task specified with a smaller dataset is very useful in such circumstances. In this paper, we present a sequence-to-sequence method utilizing a transformer model for Persian keyphrase generation. Accordingly, a corpus of 70K Persian scientific abstracts and their corresponding keyphrases have been gathered. A pretrianed MT5 mdel is fine-tuned on this corpus for the task of Persian keyword generation. The resulted model is compared to several other keyphrase generation methods. The results indicate that the proposed method can outperform existing methods at least by 2.71 percent.

In the past decade, the study of human opinions, feelings and tendencies has been very effective in the decision-making of managers and individuals. Machine learning algorithms play an important role in the field of opinion mining, but they suffer from a big problem: most of the machine learning algorithms assume that the feature dimensions and data distribution are equal, but most of real-world applications don't follow these assumptions. In fact, the data that the algorithm will receive in the future may have different dimensions or distributions. In this article, a new method for improving sentiment analysis of opinions is proposed by the aid of featurebased Transfer learning. In the proposed method, initially, the feature or topic of the opinion in the source language domain is identified. Then, by collecting adjectives, adverbs and totally a package of probabilities about that feature and by translating it into the target language, learning from the source language is Transferred into the target language. An analysis of the proposed method on the data available at the Amazon store as the source domain indicates that by creating a pattern of feature Transferring in English, the polarity of 77% of the opinions in Persian (recorded at the Digikala store) can be extracted that outperforms the SCL, SFA and TCA models with 9, 5 and 5 percent respectively.