Natural disasters, such as floods, can cause significant damage to both the environment and human life. Rapid and accurate identification of affected areas is crucial for effective disaster response and recovery efforts. In this paper, we aimed to evaluate the performance of state-of-the-art (SOTA) computer vision models for flood image classification, by utilizing a semi-supervised learning approach on a dataset named FloodNet. To achieve this, we trained son 11 state-of-the-art (SOTA) models and modified them to suit the classification task at hand. Furthermore, we also introduced a technique of varying the uncertainty offset $\lambda$ in the models to analyze its impact on the performance. The models were evaluated using standard classification metrics such as Loss, Accuracy, F1 Score, Precision, Recall, and ROC-AUC. The results of this study provide a quantitative comparison of the performance of different CNN architectures for flood image classification, as well as the impact of different uncertainty offset $\lambda$. These findings can aid in the development of more accurate and efficient disaster response and recovery systems, which could help in minimizing the impact of natural disasters.

Despite a few attempts to automatically crawl Ewe text from online news portals and magazines, the African Ewe language remains underdeveloped despite its rich morphology and complex "unique" structure. This is due to the poor quality, unbalanced, and religious-based nature of the crawled Ewe texts, thus making it challenging to preprocess and perform any NLP task with current transformer-based language models. In this study, we present a well-preprocessed Ewe dataset for low-resource text classification to the research community. Additionally, we have developed an Ewe-based word embedding to leverage the low-resource semantic representation. Finally, we have fine-tuned seven transformer-based models, namely BERT-based (cased and uncased), DistilBERT-based (cased and uncased), RoBERTa, DistilRoBERTa, and DeBERTa, using the preprocessed Ewe dataset that we have proposed. Extensive experiments indicate that the fine-tuned BERT-base-cased model outperforms all baseline models with an accuracy of 0.972, precision of 0.969, recall of 0.970, loss score of 0.021, and an F1-score of 0.970. This performance demonstrates the model’s ability to comprehend the low-resourced Ewe semantic representation compared to all other models, thus setting the fine-tuned BERT-based model as the benchmark for the proposed Ewe dataset.

Technology advancements have led to the emergence of edge devices, wearable sensors, and IoT that have revolutionized how we interact with technology. These devices enable real-time monitoring and analysis of human activities, leading to wearable sensor-based Human activity recognition (HAR). Several recognition models are proposed for federated learning to protect users’ privacy and improve the efficiency of activity recognition predictive models. However, these models have large parameters, yet their prediction results require improvement. In addition, these previous federated learning works do not consider the frame-wise classification of activity sensor data. This work presents an Efficient Graph and Temporal Convolution Network (EGTCN) model that guarantees better recognition performance with less computation cost. In addition, EGTCN parallelly predicts activities of sensor segments just as other state-of-the-art methods and performs frame-wise prediction of the sensor data. EGTCN comprises the encoder, decoder, and classifier modules. The encoder, constructed from Multi-Graph Convolution (MGC) and Multi-Temporal Convolution (MTC) modules, mines essential features from the segment input. The decoder takes the encoder output to reconstruct and predict the activities of each frame within a segment. Similarly, the classifier module uses the encoder output to predict the activity category of the segment input as a whole. Moreover, we design a federated learning system (FLS) that ensures user privacy and improves the performance of activity recognition models. Benchmark sensor datasets, namely WISDM, UCI-HAR, PAMAP2, RealWorld, and USCHAD, are utilized to evaluate the performance of our method. The results indicate that our EGTCN and FLS outperform state-of-the-art methods.