Owing to limited storage and battery power, wireless sensor nodes often face challenges in maintaining long-term energy sustainability. To address this, only a subset of sensors remains active to monitor different sensor parameters while others get predicted to minimize sensor node energy consumption. In prediction, not all active parameters are equally important, as low-correlated parameters increase computational complexity and decrease accuracy. Researchers use highly correlated active parameters, though existing solutions often use polynomial time and don’t ensure optimal parameter set. This paper proposes a cross-correlation-based parameter selection approach, ensuring the selected parameter set is stable and Pareto-optimal. Simulations are performed on nine publicly available datasets of environmental data collected from different places and at different sampling intervals to validate the effectiveness of the approach. It has been observed that approach selects a subset of active parameters faster than existing approaches and reduces energy consumption at the edge node ranges from - in the prediction of sleep sensor parameters on various datasets.

The popularity of edge computing has risen due to the widespread use of online services on IoT and mobile devices. This technology provides geographically distributed edge servers to reduce delays, energy consumption, and bandwidth requirements. However, edge computing faces challenges due to limited computing resources on edge servers and the dynamic density of IoT and mobile device users. In this article, we propose a distributed edge resource allocation approach that can accommodate the dynamic user population on the limited computing resources of edge servers. Our proposed approach aims to balance the loads of edge servers to maximize resource utilization by moving users from overloaded edge servers to underutilized ones. This way, edge computing resources can serve the maximum number of users. In addition, the proposed approach identifies bottleneck resources on edge servers to maintain the quality of service (QoS) provided by the edge servers. Thus, this approach ensures that users' experience remains consistent and meets the required QoS standards. We also validate the performance of the proposed algorithm by simulating it and simulation results show that the approach achieves its objectives and improves the efficiency of edge computing resources compared to state-of-the-art approaches.

The significance of effective insect repellents is underscored by the substantial threat posed by mosquito-borne diseases to global health. Machine learning (ML) algorithms have garnered attention as a potential approach for classifying insect repellents and evaluating their effectiveness. In this study, we explore the application of decision tree (DT), random forest (RF), logistic regression (LR), K-Nearest Neighbor (KNN), Naive Bayes (NB), AdaBoost (AB), Multilayer Perceptron (MLP), and Support Vector Machine (SVM) algorithms for categorizing insect repellents. ML techniques are employed to classify mosquito repellents by training various ML classification models using a labeled dataset in which each repellent is assigned a specific effectiveness level. These algorithms can identify patterns and determine the efficacy of a particular repellent by analyzing a range of features such as chemical composition, concentration, duration of protection, and environmental conditions. E-Nose technology offers several advantages, including high sensitivity, selectivity, rapid analysis, non-invasiveness, portability, extensive data analysis capabilities, cost-effectiveness, and versatility. In this research, we propose the use of a non-selective gas sensor array comprising eight MQ series elements, combined with ML analytics, to distinguish the type, concentration, and application of four different types of mosquito repellents commonly used in real-world scenarios. The sensor node prototype was exposed to each of the potential mosquito repellents for 15 to 20 minutes individually to create the experimental dataset. Subsequently, various ML models were trained using this dataset to accurately classify unknown data samples. SVM and MLP models achieved model accuracy scores of 98.01% and 98.10%, respectively, while DT, RF, and KNN models achieved training accuracies of 98.99%, 98.98%, and 98.61%, respectively. Classification performance error was also assessed using Mean Absolute Error (MAE), R2 Score, and Mean Squared Error (MSE).

Edge computing is a new paradigm that reduces latency and saves bandwidth by deploying edge servers in different geographic locations. This technology plays a crucial role in the rapidly growing app market for IoT devices as app vendors can hire computing resources on edge servers to serve their app users. An effective allocation of edge computing resources to different apps is needed to maximize resource utilization and serve the most app users at the lowest cost. We refer to this as an Edge Resource Allocation (ERA) problem. In this paper, we propose an Edge Resource Allocation Game (ERAGame), a game-theoretic approach that formulates the ERA problem by appropriately pricing the multi-tenant edge servers. The proposed approach gives a Pure Nash Equilibrium (PNE) solution to the ERA problem. For this, we design an ERA algorithm using ERAGame under which the system converges to PNE. For fast convergence to PNE, the edge servers are partitioned into different groups, enabling the ERA algorithm to run in parallel on all edge servers within each group. We prove that ERAGame is a potential game that guarantees at least one PNE under the ERA algorithm. We evaluate that the price of stability of ERAGame is at most O (log n). The performance of the proposed algorithm is examined through simulation.