Scaling natural language processing (NLP) to low‐resourced languages to improve machine translation (MT) performance remains enigmatic. This research contributes to the domain on a low‐resource English‐Twi translation based on filtered synthetic‐parallel corpora. It is often perplexing to learn and understand what a good‐quality corpus looks like in low‐resource conditions, mainly where the target corpus is the only sample text of the parallel language. To improve the MT performance in such low‐resource language pairs, we propose to expand the training data by injecting synthetic‐parallel corpus obtained by translating a monolingual corpus from the target language based on bootstrapping with different parameter settings. Furthermore, we performed unsupervised measurements on each sentence pair engaging squared Mahalanobis distances, a filtering technique that predicts sentence parallelism. Additionally, we extensively use three different sentence‐level similarity metrics after round‐trip translation. Experimental results on a diverse amount of available parallel corpus demonstrate that injecting pseudoparallel corpus and extensive filtering with sentence‐level similarity metrics significantly improves the original out‐of‐the‐box MT systems for low‐resource language pairs. Compared with existing improvements on the same original framework under the same structure, our approach exhibits tremendous developments in BLEU and TER scores.

As one of the fast evolution of remote sensing and spectral imagery techniques, hyperspectral image (HSI) classification has attracted considerable attention in various fields, including land survey, resource monitoring, and among others. Nonetheless, due to a lack of distinctiveness in the hyperspectral pixels of separate classes, there is a recurrent inseparability obstacle in the primary space. Additionally, an open challenge stems from examining efficient techniques that can speedily classify and interpret the spectral‐spatial data bands within a more precise computational time. Hence, in this work, we propose a 3D‐2D convolutional neural network and transfer learning model where the early layers of the model exploit 3D convolutions to modeling spectral‐spatial information. On top of it are 2D convolutional layers to handle semantic abstraction mainly. Toward simplicity and a highly modularized network for image classification, we leverage the ResNeXt‐50 block for our model. Furthermore, improving the separability among classes and balance of the interclass and intraclass criteria, we engaged principal component analysis (PCA) for the best orthogonal vectors for representing information from HSIs before feeding to the network. The experimental result shows that our model can efficiently improve the hyperspectral imagery classification, including an instantaneous representation of the spectral‐spatial information. Our model evaluation on five publicly available hyperspectral datasets, Indian Pines (IP), Pavia University Scene (PU), Salinas Scene (SA), Botswana (BS), and Kennedy Space Center (KSC), was performed with a high classification accuracy of 99.85%, 99.98%, 100%, 99.82%, and 99.71%, respectively. Quantitative results demonstrated that it outperformed several state‐of‐the‐arts (SOTA), deep neural network‐based approaches, and standard classifiers. Thus, it has provided more insight into hyperspectral image classification.

Convolutional neural networks (CNNs), one of the most successful models for visual identification, have shown excellent performance outcomes in different visual recognition challenges, attracting much interest in recent years. However, deploying CNN models to hyperspectral imaging (HSI) data continues to be a challenge due to the strongly correlated bands and insufficient training sets. Furthermore, HSI categorization is hugely dependent on spectral-spatial information. Hence, a 2D-CNN is a possible technique to analyze these features. However, because of the volume and spectral dimensions, a 3D CNN can be an option but is more computationally expensive. Furthermore, the models underperform in areas with comparable spectrums due to their inability to extract feature maps of high quality. This work, therefore, proposes a 3D/2D CNN combined with the MobineNetV2 model that uses both spectral-spatial feature maps to achieve competitive performance. First, the HSI data cube is split into small overlapping 3-D batches using the principal component analysis (PCA) to get the desired dimensions. These batches are then processed to build 3-D feature maps over many contiguous bands using a 3D convolutional kernel function, which retains the spectral properties. The performance of our model is validated using three benchmark HSI data sets (i.e., Pavia University, Indian Pines, and Salinas Scene). The results are then compared with different state-of-the-art (SOTA) methods.

Hurricane occurrence exploration is a heavy task that requires sophisticated methods to accurately determine the occurrence and the impact of damage on the tropical environs. To control massive damage, several techniques have been developed to measure the accuracy of track forecasting. The accurate analysis and exploration of the occurrence of hurricanes are very crucial for the affected environs evaluation within a short time to minimize the loss of human life and property. Nevertheless, the exact analysis and exploration of these hurricanes is challenging and time-consuming. Therefore, this study proposed a statistical model whereby the analysis of variance (ANOVA) a linear regression scientific data statistical analysis model is applied on the dataset of Atlantic hurricane database (HURDAT2) for the exploration of hurricane occurrence and damage in the tropical environs. The best tracks of a 6 hour interval, location (latitude, and longitude), wind speed, central pressure of all identified hurricanes and subtropical typhoons from the year 2008 to 2017 (10 year period) are used to determine the R² coefficient, which measures the goodness and fitness of the model to reveal the variability of the real data. Statistical significance and reliability of the data are tested on significance P-value <0.05 where four different parameters are considered for the analysis in order to determine the destructive of these hurricanes in the tropical environs; latitude (x₁), longitude (x₂), the wind speed (x₃), and central pressure. The results of our model proved significant with an accuracy of 99.3%, and a mean standard error (MSE) of 1.4952 for all the hurricanes that were analyzed, and the year 2012 was established as a year that had much damage.

Intravenous (IV) therapy is widely used in hospitals for administering fluids, medications, and nutrients, yet conventional manual monitoring may lead to delayed intervention, fluid depletion, reverse blood flow, and other patient-safety risks. This study proposes an Intelligent IoT-Based IV Drip System (IBIVDS) for real-time monitoring of IV fluid levels and reverse blood flow. The system integrates a NodeMCU ESP8266 microcontroller, load-cell weight sensor, LCD, buzzer, and Node-RED platform, supported by Arduino IDE, FreeRTOS, Python, HTML, JavaScript, and Django. The system continuously monitors IV fluid status and automatically sends alerts to healthcare personnel when predefined thresholds are reached. Notifications are generated at 50% remaining fluid and again at 20%, with the latter accompanied by an audible buzzer alert. Experimental evaluation showed that the proposed system achieved an average notification delay of approximately 0.01 min, substantially lower than the approximately 1 min delay reported for the baseline Smart Infusion Pump System under comparable conditions. The system also provides room and patient identifiers to facilitate rapid clinical response. The novelty of this study lies in integrating real-time IV level monitoring, reverse blood-flow prevention, multi-threshold alerting, and remote IoT-based notification within a single low-cost monitoring framework. The findings indicate that IBIVDS can improve the responsiveness, reliability, and consistency of IV therapy monitoring while reducing dependence on continuous manual observation.