An intelligent reflecting surface (IRS) can intelligently configure wavefronts such as amplitude, frequency, phase, and even polarization through passive reflections and without requiring any radio frequency (RF) chains. It is predicted to be a revolutionizing technology with the capability to alter wireless communication to enhance both spectrum and energy efficiencies with low expenditure and low energy consumption. Similarly, unmanned aerial vehicle (UAV) communication has attained a significant interest by research fraternity due to high mobility, flexible deployment, and easy integration with other technologies. However, UAV communication can face obstructions and eavesdropping in real-time scenarios. Recently, it is envisaged that IRS and UAV can combine together to achieve unparalleled opportunities in difficult environments. Both technologies can achieve enhanced performance by proactively altering the wireless propagation through maneuver control and smart signal reflections in three-dimensional space. This study briefly discusses IRS-assisted UAV communications. We survey the existing literature on this emerging research topic for both ground and airborne scenarios. We highlight several emerging technologies and application scenarios for future wireless networks. This study goes one step further to elaborate research opportunities to design and optimize wireless systems with low energy footprint and at low cost. Finally, we shed some light on open challenges and future research directions for IRS-assisted UAV communication.

Overall prediction of oral cavity squamous cell carcinoma (OCSCC) remains inadequate, as more than half of patients with oral cavity cancer are detected at later stages. It is generally accepted that the differential diagnosis of OCSCC is usually difficult and requires expertise and experience. Diagnosis from biopsy tissue is a complex process, and it is slow, costly, and prone to human error. To overcome these problems, a computer-aided diagnosis (CAD) approach was proposed in this work. A dataset comprising two categories, normal epithelium of the oral cavity (NEOR) and squamous cell carcinoma of the oral cavity (OSCC), was used. Feature extraction was performed from this dataset using four deep learning (DL) models (VGG16, AlexNet, ResNet50, and Inception V3) to realize artificial intelligence of medial things (AIoMT). Binary Particle Swarm Optimization (BPSO) was used to select the best features. The effects of Reinhard stain normalization on performance were also investigated. After the best features were extracted and selected, they were classified using the XGBoost. The best classification accuracy of 96.3% was obtained when using Inception V3 with BPSO. This approach significantly contributes to improving the diagnostic efficiency of OCSCC patients using histopathological images while reducing diagnostic costs.

Fifth-generation (5G) cellular networks are state-of-the-art wireless technologies revolutionizing all wireless systems. The fundamental goals of 5G are to increase network capacity, improve data rates, and reduce end-to-end latency. Therefore, 5G can support many devices connected to the Internet and realize the Internet of Things (IoT) vision. Though 5 G provides significant features for mobile wireless networks, some challenges still need to be addressed. Although 5 G offers valuable capabilities for mobile wireless networks, specific issues still need to be resolved. This article thoroughly introduces 5G technology, detailing its needs, infrastructure, features, and difficulties. In addition, it summarizes all the requirements and specifications of the 5G network based on the 3rd Generation Partnership Project (3GPP) Releases 15–17. Finally, this study discusses the key specifications challenges of 5G wireless networks.

Electroencephalography (EEG) data serve as a reliable method for fatigue detection due to their intuitive representation of drivers’ mental processes. However, existing research on feature generation has overlooked the effective and automated aspects of this process. The challenge of extracting features from unpredictable and complex EEG signals has led to the frequent use of deep learning models for signal classification. Unfortunately, these models often neglect generalizability to novel subjects. To address these concerns, this study proposes the utilization of a modified deep convolutional neural network, specifically the Inception‐dilated ResNet architecture. Trained on spectrograms derived from segmented EEG data, the network undergoes analysis in both temporal and spatial‐frequency dimensions. The primary focus is on accurately detecting and classifying fatigue. The inherent variability of EEG signals between individuals, coupled with limited samples during fatigue states, presents challenges in fatigue detection through brain signals. Therefore, a detailed structural analysis of fatigue episodes is crucial. Experimental results demonstrate the proposed methodology’s ability to distinguish between alertness and sleepiness, achieving average accuracy rates of 98.87% and 82.73% on Figshare and SEED‐VIG datasets, respectively, surpassing contemporary methodologies. Additionally, the study examines frequency bands’ relative significance to further explore participants’ inclinations in states of alertness and fatigue. This research paves the way for deeper exploration into the underlying factors contributing to mental fatigue.

Solar energy utilization in the industry has grown substantially, resulting in heightened recognition of renewable energy sources from power plants and intelligent grid systems. One of the most important challenges in the solar energy field is detecting anomalies in photovoltaic systems. This paper aims to address this by using various machine learning algorithms and regression models to identify internal and external abnormalities in PV components. The goal is to determine which models can most accurately distinguish between normal and abnormal behavior of PV systems. Three different approaches have been investigated for detecting anomalies in solar power plants in India. The first model is based on a physical model, the second on a support vector machine (SVM) regression model, and the third on an SVM classification model. Grey wolf optimizer was used for tuning the hyper model for all models. Our findings will clarify that the SVM classification model is the best model for anomaly identification in solar power plants by classifying inverter states into two categories (normal and fault).

Since about 1980, a new generation has appeared approximately every decade. Mobile phones started with first-generation (1G), then the successful second generation (2G), and then mixed successful auctions since the launch of 3G. According to business terms, 1G and 2G were providing voice and gradually include data (3G is unsuccessful, 4G is very successful). Today, we are seeing a stir over what 5G will provide. Key expectations currently being discussed include an ultra-high 20 Gb/s bit rate, an ultra-low latency of just 1 millisecond, and a very high capacity. Given the enormous potential of 5G communication networks and their expected evolution, what should 6G include that is not part of 5G or its long-term evolution? 6G communication networks should deliver improved range and data speeds, as well as the ability to connect users from anywhere. This article details possible 6G communication networks. More specifically, the primary influence of this research is to deliver a complete synopsis of the development of wireless communication networks from 1G to 6G.