Research in the recognition of human activities of daily living has significantly improved using deep learning techniques. Traditional human activity recognition techniques often use handcrafted features from heuristic processes from single sensing modality. The development of deep learning techniques has addressed most of these problems by the automatic feature extraction from multimodal sensing devices to recognise activities accurately. In this paper, we propose a deep learning multi-channel architecture using a combination of convolutional neural network (CNN) and Bidirectional long short-term memory (BLSTM). The advantage of this model is that the CNN layers perform direct mapping and abstract representation of raw sensor inputs for feature extraction at different resolutions. The BLSTM layer takes full advantage of the forward and backward sequences to improve the extracted features for activity recognition significantly. We evaluate the proposed model on two publicly available datasets. The experimental results show that the proposed model performed considerably better than our baseline models and other models using the same datasets. It also demonstrates the suitability of the proposed model on multimodal sensing devices for enhanced human activity recognition.

Data are being generated and used to support all aspects of healthcare provision, from policy formation to the delivery of primary care services. Particularly, with the change of emphasis from curative to preventive medicine, the importance of data-based research such as data mining and machine learning has emphasized the issues of class distributions in datasets. In typical predictive modeling, the inability to effectively address a class imbalance in a real-life dataset is an important shortcoming of the existing machine learning algorithms. Most algorithms assume a balanced class in their design, resulting in poor performance in predicting the minority target class. Ironically, the minority target class is usually the focus in predicting processes. The misclassification of the minority target class has resulted in serious consequences in detecting chronic diseases and detecting fraud and intrusion where positive cases are erroneously predicted as not positive. This paper presents a new attribute selection technique called variance ranking for handling imbalance class problems in a dataset. The results obtained were compared to two well-known attribute selection techniques: the Pearson correlation and information gain technique. This paper uses a novel similarity measurement technique ranked order similarity-ROS to evaluate the variance ranking attribute selection compared to the Pearson correlations and information gain. Further validation was carried out using three binary classifications: logistic regression, support vector machine, and decision tree. The proposed variance ranking and ranked order similarity techniques showed better results than the benchmarks. The ROS technique provided an excellent means of grading and measuring the similarities where other similarity measurement techniques were inadequate or not applicable.

Managing resource allocation for optimum effectiveness at various levels of maintenance activities is always a challenging task. Optimizing maintenance resources enables an organization to set priorities towards achieving certain goals which are availability and reliability of the equipment for operational excellence. The purpose of this analysis is to determine the optimum resources allocation proportions among the failure modes and to identify the failure modes that have the greatest cumulative effect on the equipment's downtime. This paper presents a methodology using the Pareto analysis in conjunction with failure mode effect and criticality Analysis in maintenance resources optimization. The approach is based on ensuring all failure mode criticality number are considered to obtain the significant failures mode that you should focus on as a priority. The analysis shows that failure mode; FM5, FM 3, FM 2, FM 12, FM 7 and FM 13 are confirmation to the Pareto principle, identifying that most of the downtime of the Instrumentation Air Compressors originated from these failure modes.

Imbalanced classes in multi-classed datasets is one of the most salient hindrances to the accuracy and dependable results of predictive modeling. In predictions, there are always majority and minority classes, and in most cases it is difficult to capture the members of item belonging to the minority classes. This anomaly is traceable to the designs of the predictive algorithms because most algorithms do not factor in the unequal numbers of classes into their designs and implementations. The accuracy of most modeling processes is subjective to the ever-present consequences of the imbalanced classes. This paper employs the variance ranking technique to deal with the real-world class imbalance problem. We augmented this technique using one-versus-all re-coding of the multi-classed datasets. The proof-of-concept experimentation shows that our technique performs better when compared with the previous work done on capturing small class members in multi-classed datasets.

Antennas and filters are two key components that make up the configuration of the radio frequency (RF) front end of any wireless communication system. While the antenna is responsible for transmitting and receiving signals in the system, the filter is tasked with selecting signals that fall within the system’s operating frequency band, while also rejecting spurious (out‐of‐band) signals from the system. Following the recent increasing trend toward device simplicity and miniaturization, it is desirable to integrate the antenna and the filter into a single component that achieves both the radiating (i.e., transmitting and receiving) and the filtering functions simultaneously. This integrated component is what is now known as a filtering antenna (or filtenna). The filtenna reduces a system’s prefiltering requirements and improves the noise performance of the system. It also finds application in overcoming the insufficiency of stand‐alone bandpass filters in suppressing interference in sidebands. This article covers the review of the current state of the art in the design and implementation of filtennas, the practical applications, recent developments, and challenges. Emerging research and future opportunities in filtering antenna design and implementation techniques are also investigated and reported.

Flooding remains one of the most destructive natural disasters, causing loss of life, property damage, and economic disruption. It is a persistent challenge in Nigeria, with Mokwa Local Government Area (LGA) in Niger State being particularly vulnerable due to its location in the Lower Niger River Basin, influenced by both the River Niger and the Kaduna tributary. This study presents a hybrid convolutional neural network–long short‐term memory (CNN–LSTM) model integrated with an automated intervention system for real‐time flood forecasting, prediction, and proactive control. The CNN component extracts spatial correlations across a network of 16 hydrometeorological, geospatial, and sensor‐based variables (including rainfall, river discharge, soil moisture, and flood risk indices), while the LSTM captures long‐term dependencies to enhance time‐series prediction accuracy. The model was trained on historical records prior to 2000, with validation and operational testing using daily observations and simulated sequences from 2000 to 2025, totaling 9125 daily records; flood events were labeled when water levels exceeded 3.5 m. The proposed model achieved 96% forecast accuracy, a precision of 0.93, a recall of 0.89, and an F 1 score of 0.91. The hybrid framework demonstrated robustness to noise, faster convergence, and improved recall for extreme flood events. Automated intervention simulations showed a 72% reduction in peak water levels, confirming the framework′s effectiveness in mitigating flood severity. Comparative analysis against conventional machine learning models highlighted the system′s superiority in covering the full flood management cycle of data acquisition, forecasting, prediction, and automated response, enabling timely decision‐making and reducing delays from human intervention. This CNN–LSTM automation approach provides a scalable, AI‐driven solution for proactive flood management in riverine communities such as Mokwa, with potential applicability to other flood‐prone regions.