One of the key functions of global water resource management authorities is river water quality (WQ) COD assessment. A water quality index (WQI) is developed for water assessments considering numerous quality-related variables. WQI assessments typically take a long time and are prone to errors during sub-indices generation. This can be tackled through the latest machine learning (ML) techniques that are renowned for superior accuracy. In this study, water samples were taken from the wells in the study area (North Pakistan) to develop WQI prediction models. Four standalone algorithms, i.e., random trees (RT), random forest (RF), M5P, and reduced error pruning tree (REPT), were used in this study. In addition, 12 hybrid data-mining algorithms (combination of standalone, bagging (BA), cross-validation parameter selection (CVPS), and randomizable filtered classification (RFC)) were also used. Using the 10-fold cross-validation technique, the data were separated into two groups (70:30) for algorithm creation. Ten random input permutations were created using Pearson correlation coefficients to identify the best possible combination of datasets for improving the algorithm prediction. The variables with very low correlations performed poorly, whereas hybrid algorithms increased the prediction capability of numerous standalone algorithms. Hybrid RT-Artificial Neural Network (RT-ANN) with RMSE = 2.319, MAE = 2.248, NSE = 0.945 and PBIAS = -0.64, outperformed all other algorithms. Most algorithms overestimated WQI values except for BA-RF, RF, BA-REPT, REPT, RFC-M5P, RFC-REPT, and ANN- Adaptive Network-Based Fuzzy Inference System (ANFIS).

Autonomous vehicles (AVs) are getting popular because of their usage in a wide range of applications like delivery systems, self-driving taxis, and ambulances. AVs utilize the power of machine learning (ML) and deep learning (DL) algorithms to improve their self-driving learning experiences. The sudden surge in the number of AVs raises the need for distributed learning ecosystem to optimize their self-driving experiences at a rapid pace. Toward this goal, federated learning (FL) benefits, which can create a distributed learning environment for AVs. But, the traditional FL transfers the raw input data directly to a server, which leads to privacy concerns among the end-users. The concept of blockchain helps us to protect privacy, but it requires additional computational infrastructure. The extra infrastructure increases the operational cost for the company handling and maintaining the AVs. Motivated by this, in this paper, the authors introduced the concept of gradient encryption in FL, which preserves the users’ privacy without the additional computation requirements. The computational power present in the edge devices helps to fine-tune the local model and encrypt the input data to preserve privacy without any drop in performance. For performance evaluation, the authors have built a German traffic sign recognition system using a convolutional neural network (CNN) algorithm-based classification system and GeFL . The simulation process is carried out over a wide range of input parameters to analyze the performance at scale. Simulation results of GeFL outperform the conventional FL-based algorithms in terms of accuracy, i.e., 2% higher. Also, the amount of data transferred among the devices in the network is nearly three times less in GeFL compared to the traditional FL.

Unmanned aerial vehicles (UAVs) play a crucial role in remote environmental applications of the Low-Power Internet of Things (IoT) network. However, the interaction between a large number of consumer electronics products integrated with TinyML (CEP-TML) may lead to serious interference and overlap issues in Low-Power IoT networks, which still pose challenges to the lifespan of UAVs. To address this issue, this paper proposes an interference hypergraph-based energy harvesting resource allocation (IH-EHRA) algorithm in UAV-assisted CEP-TML communication (UAV-CEPC-TML) networks, aimed at ensuring effective resource management in overlapping interference scenarios. Firstly, we established an interference hypergraph model to analyze the types and relationships of interference in a Low-Power IoT network, to reduce interference and optimize spectrum resource utilization. Then, in the overlapping interference scenario, we propose an EH optimization model with imperfect channel state information (CSI), aiming to maximize network throughput while improving the service life of UAVs. Finally, we optimize the model into two subproblems and apply learning theory to reduce the impact of imperfect CSI to obtain the optimal solution to the problem. The simulation results show that the algorithm can effectively ensure the EH requirements of UAVs, and improve the interference efficiency and throughput of the network.

The security of wireless communications is increasingly threatened by eavesdropping and jamming attacks. This paper proposes a novel framework for enhancing secure transmission using hybrid active-passive Reconfigurable Intelligent Surfaces (RIS). By combining active and passive elements, the hybrid RIS can dynamically adjust the amplitude and phase of reflected signals, providing a robust defense against eavesdropping and jamming. The key challenge lies in optimizing the beamforming at the base station (BS) and the hybrid RIS configuration in real time. To tackle this, we employ a Deep Reinforcement Learning (DRL) approach using the Deep Deterministic Policy Gradient (DDPG) algorithm, enabling efficient and dynamic optimization. Simulation results demonstrate that the proposed DRL-based method significantly improves the secrecy rate compared to conventional passive RIS and benchmark methods. Our results indicate that the system can achieve substantial security gains even with a limited number of active RIS elements, making it a viable solution for next-generation wireless networks.

A fall detection system is vital for the safety of older people, as it contacts emergency services when it detects a person has fallen. There have been various approaches to detect falls, such as using a single tri-axial accelerometer to detect falls or fixing sensors on the walls of a room to detect falls in a particular area. These approaches have two major drawbacks: either (i) they use a single sensor, which is insufficient to detect falls, or (ii) they are attached to a wall that does not detect a person falling outside its region. Hence, to provide a robust method for detecting falls, the proposed approach uses three different sensors for fall detection, which are placed at five different locations on the subject’s body to gather the data used for training purposes. The UMAFall dataset is used to attain sensor readings to train the models for fall detection. Five models are trained corresponding to the five sensors models, and a majority voting classifier is used to determine the output. Accuracy of 93.5%, 93.5%, 97.2%, 94.6%, and 93.1% is achieved on each of the five sensors models, and 92.54% is the overall accuracy achieved by the majority voting classifier. The XAI technique called LIME is incorporated into the system in order to explain the model’s outputs and improve the model’s interpretability.

In underwater acoustic wireless sensor networks (UAWSNs), energy harvesting either enhances the lifetime of a network by increasing the battery power of sensor nodes or ensures battery-less operation of nodes. This, in effect, results in sustainable and reliable operation of the network deployed for various underwater applications. This work provides a survey of the energy harvesting techniques for UAWSNs. Our work is unique than the existing work on underwater energy harvesting in that it includes state-of-the art techniques designed in the last decade. It analyzes every harvesting scheme in terms of its main idea, merits, demerits and the extent of the harvested power (energy). The description of the merits results in selection of the suitable scheme for the suitable underwater applications. The demerits of the addressed schemes provide an insight to their future enhancement and improvement. Moreover, the harvested techniques are classified into various categories depending upon the involved energy harvesting mechanism and compared based on the maximum and minimum amount of harvested power, which helps in selection of the suitable category keeping in view the power budget of an underwater network before deployment. The challenges in energy harvesting and in UAWSNs are described to provide an insight to them and to address them for further enhancement in the harvested extent. Finally, research directions are specified for future investigation.