Static Sensor Research Articles

A collaborative WSN‐IoT‐Animal for large‐scale data collection

AbstractIn recent years, large‐scale data collection systems have developed rapidly in many fields, including agriculture, transport and many others. The internet of things (IoT), whose main platform is wireless sensor networks (WSNs), is behind this development. Comprising thousands of sensors of different kinds, their main purpose is to collect and transmit data. Several data collection techniques have been proposed, including static, mobile and hybrid approaches. The challenges faced by these techniques are considerable, and include energy conservation, planning and trajectory optimisation during data collection, most importantly, the challenges related to the communication between the static sensors generally distributed in a more or less large geographical space and the mobile data collection system (UAV, vehicle, robot etc.). Not to mention the cost, which remains enormous for the agricultural sectors. A hybrid WSN‐IoT‐Animal that is self‐configured to improve data acquisition over large agricultural areas is presented. The main objective and originality of the heterogeneous semi‐modern scheme proposed here oscillating between traditional agriculture and precision agriculture is the use of animals as data collection tools. The main contribution here is the design of a simple and efficient model of data collection that is easily accessible by farmers by adapting the available resources. This model describes and adopts a sensor deployment method based on the notion of the hypergraph, which provides adequate coverage and ensures communication between the mobile sink and a subset of peripheral sensors chosen in alternation. Simulation results verify the effectiveness of the proposed protocol in terms of network lifetime compared to other works. In addition, the amount of data received by the mobile sink demonstrates the importance of this approach in terms of connectivity for large‐scale data collection.

Optimal interference mitigation with deep learningbased channel access in wireless body area networks

SummaryWireless body area networks (WBANs) are essential for medical applications, especially in remote health monitoring, as they transmit crucial and time‐sensitive data collected by nodes positioned around or within the body. However, the coexistence of WBANs with wireless channels can degrade performance due to interference. This study introduces OIM‐DLCAM, an optimal interference mitigation scheme for WBANs, which utilizes a deep learning‐based channel access method. OIM‐DLCAM addresses interference through the multiobjective Hungarian optimization (MOHO) algorithm, considering design constraints such as node transmission power, packet delivery ratio, and interference range. Additionally, it employs a deep probabilistic neural network‐based channel access method (DPNN‐CAM) to effectively mitigate interference by making decisions regarding contention window size, frame length, and buffer size. The proposed OIM‐DLCAM scheme ensures fairness between users while enhancing system performance. Simulation results from both static and dynamic sensor node scenarios demonstrate its effectiveness under various conditions, showcasing its potential to improve WBAN performance in medical applications. The simulations reveal that OIM‐DLCAM outperforms existing state‐of‐the‐art schemes across various scenarios, with efficiency gains of up to 86.187%, 72.452%, and 47.954% for WBAN node density, mobility, and packet arrival rate, respectively. Moreover, it significantly reduces the average end‐to‐end delay and packet drop rate while improving throughput and packet delivery ratio compared with existing schemes. Additionally, comparisons with industry standards, such as the IEEE 802.15.4e norm, validate the suitability of OIM‐DLCAM for cofounded WBANs.

Assessment of Ammonia Concentrations and Climatic Conditions in Calf Housing Using Stationary and Mobile Sensors.

In calf fattening, housing climate conditions are essential for optimal performance and welfare. Validated methods to measure the long-term housing climate are lacking. The present study investigated climate parameters for 14 weeks in Swiss calf fattening housing with two different ammonia (NH3) sensors: six stationary sensors (Dräger Polytron 8100) were installed at animal level and four mobile sensors (Dräger x-AM 5100) were attached to the calves' heads. Temperature, relative humidity, and carbon dioxide (CO2) concentrations were recorded by two stationary data loggers (testo 160 IAQ). Data were analyzed descriptively, and 4 h mean values of maximum NH3 concentrations of mobile and stationary sensors were compared using the Wilcoxon test for paired data. The 4 h mean values of temperature, relative humidity, and CO2 concentrations and the 4 h mean values of maximum NH3 concentrations of stationary and mobile sensors were analyzed by ANOVA in two linear models. The overall 4 h mean of maximum NH3 concentrations ranged between 5.9-9.4 ppm for measurements of stationary sensors and between 11.3-14.7 ppm for measurements of mobile sensors. The NH3 concentrations measured by mobile sensors showed significantly higher peak values and more fluctuations. Additionally, an interaction effect was observed between the NH3 concentrations measured by either sensor and CO2 concentrations (p < 0.01 (mobile sensors); p < 0.0001 (stationary sensors), temperature values (p < 0.0001 (both sensors)), and relative humidity (p < 0.0001 (both sensors)). The measurements of the implemented method showed that corresponding housing climate parameters fluctuated strongly, and NH3 reached high peak values. Validated measurement methods might allow for a detailed assessment of the housing climate in practice, and for further research on suitable management methods for housing climate optimization in the future.

Drive-by modal identification of railway bridges via on-board measurements from a single railroad vehicle

The global railway network spans over one million kilometers of tracks, and this extensive infrastructure is set to expand even further. The objective is to promote rail transportation as an environmentally sustainable solution to address the growing demands of mobility. A significant portion of these tracks spans across bridge structures, which must also accommodate the rising demands for mobility and increased travel speeds, placing additional demands in terms of imposed loads. At the same time, bridges worldwide suffer from aging, leading to the deterioration of their structural integrity. Such combined effects necessitate monitoring the structural health of bridges to ensure the quality and safety of railway networks by detecting possible alterations in their response characteristics. Traditional Structural Health Monitoring (SHM) techniques use stationary sensors affixed to the bridge structure, enabling the direct assessment of the collected data. While such approaches are reliable, they present limitations in the comprehensive inspection of multiple railway bridges within a network. As an alternative, mobile vibration-based sensing, utilizing sensors on passing trains, presents the potential to gather data from multiple railway bridges using only a few sensors installed on board trains. Furthermore, operating the sensor-equipped trains at frequent intervals allows for collecting continuous data, offering valuable insights into the ongoing deterioration of bridges. In light of this, our work proposes a model-based methodology for extracting the modal frequencies of bridges based on acceleration data collected from traversing trains. Our approach hinges on Kalman filtering for estimating the state and input of the train and employs a subspace identification method to ascertain the frequencies of the bridge. The ultimate goal is to develop a drive-by bridge monitoring scheme that accommodates the assessment of the remaining lifespan of bridges as well as timely repairs in the event of damage, ensuring the safety and reliability of rail transportation.

Measurement of the concentration distribution of hydrogen jets using adaptive stream stripe- background oriented schlieren (ASS-BOS)

Hydrogen leakage diagnosis has attracted more and more attention, especially in the high-pressure hydrogen system of fuel cell vehicles, where the chance of deflagration is quite high. Traditional methods for detecting gas leaks rely on stationary sensor measurements and manual inspections. Manual inspections are time and resource-consuming, and it is challenging to achieve real-time, comprehensive inspections in large spaces. In this study, a new Adaptive Stream Stripe-Background Oriented Schlieren (ASS-BOS) method for hydrogen jet visualization is proposed. Three different background patterns, namely random scatter background, checkerboard background, and stripe background, are designed for multiple experiments. The results show that when observing hydrogen jets in the far-field region (low-density gradient), ASS-BOS has higher accuracy and resolution, detects larger background displacements, and shows more turbulence details. In addition, the concentration distribution of the hydrogen jet is reconstructed using ASS-BOS. We compare the concentration of the hydrogen jet obtained from the inversion of the ASS-BOS method with the experimental results measured by the sensor. We find that the average error is 3.45%, indicating that ASS-BOS can accurately reconstruct the concentration distribution of the hydrogen jet.

Analytical study of Restricted Access Window with short slots for fast and reliable data delivery from energy-harvesting sensors

To address the peculiarities of various Internet of Things applications and improve the performance of Wi-Fi-based sensor stations, a recent Wi-Fi HaLow standard introduces a mechanism called Periodic Restricted Access Window (PRAW). PRAW allows mapping groups of stations to periodic time intervals during which only these stations can transmit while the others cannot. This approach reduces contention and saves energy. However, the standard does not provide any recommendations on how to select the PRAW parameters according to scenario-specific requirements, leaving room for the research. A typical IoT scenario considers low-intensity traffic and requires fast and reliable data delivery from energy-harvesting devices while using the channel efficiently: there shall be still time for transmissions of other stations in the network. This paper develops an analytical model of PRAW that evaluates the probability of delivering data in time from every sensor station that harvests energy, accumulates it in small capacitors, and, thus, may not have enough energy for multiple retries. The model allows selecting such parameters of PRAW that minimize the channel resource consumption of a Wi-Fi HaLow network, provided that the delay and energy requirements are satisfied.

Mobile Sensor Path Planning for Kalman Filter Spatiotemporal Estimation.

The estimation of spatiotemporal data from limited sensor measurements is a required task across many scientific disciplines. In this paper, we consider the use of mobile sensors for estimating spatiotemporal data via Kalman filtering. The sensor selection problem, which aims to optimize the placement of sensors, leverages innovations in greedy algorithms and low-rank subspace projection to provide model-free, data-driven estimates. Alternatively, Kalman filter estimation balances model-based information and sparsely observed measurements to collectively make better estimation with limited sensors. It is especially important with mobile sensors to utilize historical measurements. We show that mobile sensing along dynamic trajectories can achieve the equivalent performance of a larger number of stationary sensors, with performance gains related to three distinct timescales: (i) the timescale of the spatiotemporal dynamics, (ii) the velocity of the sensors, and (iii) the rate of sampling. Taken together, these timescales strongly influence how well-conditioned the estimation task is. We draw connections between the Kalman filter performance and the observability of the state space model and propose a greedy path planning algorithm based on minimizing the condition number of the observability matrix. This approach has better scalability and computational efficiency compared to previous works. Through a series of examples of increasing complexity, we show that mobile sensing along our paths improves Kalman filter performance in terms of better limiting estimation and faster convergence. Moreover, it is particularly effective for spatiotemporal data that contain spatially localized structures, whose features are captured along dynamic trajectories.

Improved Grey Wolf Optimization Based Node Localization Approach in Underwater Wireless Sensor Networks

Abstract Underwater Wireless Sensor Networks (UWSNs) are established by Autonomous Underwater Vehicles (AUVs) or static Sensor Nodes (SN) that collect and transmit information over the underwater environment. Localization plays a vital role in the effective deployment, navigation and coordination of these nodes for many applications, namely underwater surveillance, underwater exploration, oceanographic data collection and environmental monitoring. Due to the unique characteristics of underwater transmission and acquisition, this is a fundamental challenge in underwater networks. However, localization in UWSNs is problematic due to the unique features of underwater transmission and the harsh underwater environment. To address these challenges, this paper presents an Improved Grey Wolf Optimization Based Node Localization Approach in UWSN (IGWONL-UWSN) technique. The presented IGWONL-UWSN technique is inspired by the hunting behavior of grey wolves with the Dimension Learning-based Hunting (DLH) search process. The proposed IGWONL-UWSN technique uses the Improved Grey Wolf Optimization Based (IGWO) algorithm to calculate the optimal location of the nodes in the UWSN. Moreover, the IGWONL-UWSN technique incorporates the DLH search process to improve the convergence and accuracy. The simulation results of the IGWONL-UWSN technique are validated using a set of performance measures. The simulation results show the improvements of the IGWONL-UWSN method over other approaches with respect to various metrics.

Vibration Reduction on Circular Disks with Vibroacoustic Metamaterials

Vibroacoustic metamaterials represent an innovative technology developed for broadband vibration reduction. They consist of an array of local resonators and are able to reduce vibrations over a wide frequency range, commonly referred to as a stop band. Vibroacoustic metamaterials may be a promising strategy to reduce out-of-plane vibrations of thin-walled, disk-shaped structures, such as saw blades. However, their behavior in rotating systems has not yet been fully understood. In this study, a vibroacoustic metamaterial integrated into a circular disk for the reduction of out-of-plane vibrations is experimentally investigated in the rotating and non-rotating state. Derived from the predominant frequency range of noise emitted by saw blades, a vibroacoustic metamaterial with a numerically predicted stop band in the frequency range from 2000 Hz to 3000 Hz, suitable for integration into a circular disk, is designed. The resonators of the metamaterial are realized by cutting slots into the disk using a waterjet cutting machine. To experimentally examine the structural dynamic behavior, the disk is excited by an impulse hammer and observed by a stationary optical velocity sensor on a rotor dynamics test stand. The results of the rotating and the non-rotating state are compared. The measurements are carried out at two different radii and at speeds up to 3000 rpm. A distinct stop band characteristic is shown in the desired frequency range from 2000 Hz to 3000 Hz in the rotating and non-rotating state. No significant shift of the stop band frequency range was observed during rotation. However, adjacent modes were observed to propagate into the stop band frequency range. This work contributes to a better understanding of the behavior of vibroacoustic metamaterials in the rotating state and enables future applications of vibroacoustic metamaterials for vibration reduction in rotating, disk-shaped structures such as saw blades, brake disks or gears.

LidPose: Real-Time 3D Human Pose Estimation in Sparse Lidar Point Clouds with Non-Repetitive Circular Scanning Pattern.

In this paper, we propose a novel, vision-transformer-based end-to-end pose estimation method, LidPose, for real-time human skeleton estimation in non-repetitive circular scanning (NRCS) lidar point clouds. Building on the ViTPose architecture, we introduce novel adaptations to address the unique properties of NRCS lidars, namely, the sparsity and unusual rosetta-like scanning pattern. The proposed method addresses a common issue of NRCS lidar-based perception, namely, the sparsity of the measurement, which needs balancing between the spatial and temporal resolution of the recorded data for efficient analysis of various phenomena. LidPose utilizes foreground and background segmentation techniques for the NRCS lidar sensor to select a region of interest (RoI), making LidPose a complete end-to-end approach to moving pedestrian detection and skeleton fitting from raw NRCS lidar measurement sequences captured by a static sensor for surveillance scenarios. To evaluate the method, we have created a novel, real-world, multi-modal dataset, containing camera images and lidar point clouds from a Livox Avia sensor, with annotated 2D and 3D human skeleton ground truth.

A time-varying shockwave speed model for reconstructing trajectories on freeways using Lagrangian and Eulerian observations

Inference of detailed vehicle trajectories is crucial for applications such as traffic flow modeling, energy consumption estimation, and traffic flow optimization. Static sensors can provide only aggregated information, posing challenges in reconstructing individual vehicle trajectories. Shockwave theory is used to reproduce oscillations that occur between sensors. However, as the emerging of connected vehicles grows, probe data offers significant opportunities for more precise trajectory reconstruction. Existing methods rely on Eulerian observations (e.g., data from static sensors) and Lagrangian observations (e.g., data from connected vehicles) incorporating shockwave theory and car-following modeling. Despite these advancements, a prevalent issue lies in the static assignment of shockwave speed, which may not be able to reflect the traffic oscillations in a short time period caused by varying response times and vehicle dynamics. Moreover, driver dynamics while reconstructing the trajectories are ignored. In response, this paper proposes a novel framework that integrates Eulerian and Lagrangian observations for trajectory reconstruction on freeways. The approach introduces a calibration algorithm for time-varying shockwave speed. The shockwave speed calibrated by the CV is then utilized for trajectory reconstruction of other non-connected vehicles based on shockwave theory. Additionally, vehicle and driver dynamics are introduced to optimize the trajectory and estimate energy consumption by applying a vehicle movement model. The proposed method is evaluated using real-world datasets, demonstrating superior performance in terms of trajectory accuracy, reproducing traffic oscillations, and estimating energy consumption.

Design and Optimization of Piezoelectric Pressure Sensor with AlN as piezo electric material for High-Temperature Application using COMSOL 5.3

Dynamic pressure sensors in contrast to static pressure sensors measure pressure changes in liquids or gases generated due to a blast, a propulsion or an explosion, where the temperature is normally high which is above 700°C[1]. Piezoelectric pressure sensors with their inherent advantage of direct transduction capability are drawing attention for high-temperature applications. Lead Zirconate Titanate (PZT) and Zinc Oxide (ZnO) are popular ferroelectric materials for Piezoelectric sensor applications. Aluminum Nitride (AlN) is a suitable candidate for high-temperature applications with its high melting point of 2673 K, the piezoelectric property remaining stable even up to 1423K, the energy band gap of 6.2eV, piezoelectric coefficient d33 of 7pC/N and pressure handling capacity up to 10 MPa. In this study, COMSOL Multiphysics 5.3 was used to analyse the pressure sensing capability of AlN film by optimizing the crystal orientation and the dimension of AlN in addition to studying suitability of using at high temperature. Also a comparison is done on the high temperature performance of pressure sensor using Silicon and Silicon Carbide as diaphragm.

A Novel Non-Contact Method for Monitoring the Acoustic Emission From Mixed Elastohydrodynamic Lubrication Contacts

Abstract Lubricated non-conformal contacts, such as between gear teeth, operate with high levels of mixed lubrication, where the amount of direct asperity contact depends on operating parameters that influence the film thickness. Understanding of the levels of surface interaction is key to optimizing component life, and there is considerable interest in sensitive monitoring methods such as Acoustic Emission (AE). Researchers have shown that AE can detect subtle changes in lubrication conditions, using sensors mounted directly on the rotating gears. However, the use of such sensors is complex and unsuitable for implementation in real gearboxes. The alternative, of using sensors placed on housings, is hampered by signal attenuation and noise. This paper presents a novel, non-contact stationary sensor, coupled by an oil film to the rotating gear, which is shown to be capable of detecting important changes in lubrication conditions with significantly higher consistency and precision than housing-mounted sensors, whilst avoiding the complexities of gear-mounted sensors.

Surrogate-assisted sine Phasmatodea population evolution algorithm applied to 3D coverage of mobile nodes

Deploying static wireless sensor nodes is prone to network coverage gaps, resulting in poor network coverage. In this paper, an attempt is made to improve the network coverage by moving the locations of the nodes. A surrogate-assisted sine Phasmatodea population evolution algorithm (SASPPE) is used to evaluate the network coverage. A 50×50\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$50 \ imes 50$$\\end{document} hill simulation environment was tested for the number of nodes of 30 and 40 and radii of 3, 5 and 7, respectively. The results show that the SASPPE algorithm has the highest coverage, which can be up to 23.624% higher than the PPE algorithm, and up to 5.196% higher than the PPE algorithm, ceteris paribus. The SASPPE algorithm mixes the GSAM with LSAMs, which balances the computational cost of the algorithm and the algorithm’s ability to find optimal results. The use of hierarchical clustering enhances the stable type of the LSAMs. In addition, LSAMs are easy to fall into local optimality when they are modeled with local data, and the use of sine Phasmatodea population evolution algorithm (Sine-PPE) for searching in LSAMs alleviates the time for the algorithm to fall into local optimality. On 30D, 50D, and 100D, the proposed algorithm was tested by 7 test functions. The results show that the algorithm has significant advantages on most functions.

Automated Fall Detection for Disabled Individuals Using Mobile Phone Sensors and Machine Learning: A Survey

Fall risks to health and safety are especially dangerous for those with impairments. An automated fall detection system is necessary, especially in medical and senior care. The elderly and individuals with impairments are particularly susceptible to falls, which frequently result in severe injuries and complications, thereby presenting a considerable threat to their overall health. The early discovery and response to a fall incidence can reduce immobilization and consequent health complications, saving lives. Automatic fall detection systems quickly and reliably indicate falls and dispatch medical or emergency assistance. Researchers have introduced various automatic fall detection methods using machines or deep learning. Most fall detection systems depend on wearable or stationary sensors, which restricts the user's mobility and accessibility. Conversely, mobile sensor-based fall detection leverages the widespread presence of smartphones by obtaining motion information via their integrated accelerometers and gyroscopes. Our primary objective is to develop a reliable fall detection method using a mobile phone sensor and machine learning. This paper examines several methods employed in the identification of falls and emphasizes the significance of utilizing mobile phone sensors in the process of fall detection. It also discusses recent research in this domain and highlights research challenges. This could potentially foster further innovation in the field.

Consensus-Based Information Filtering in Distributed LiDAR Sensor Network for Tracking Mobile Robots.

A distributed state observer is designed for state estimation and tracking of mobile robots amidst dynamic environments and occlusions within distributed LiDAR sensor networks. The proposed novel framework enhances three-dimensional bounding box detection and tracking utilizing a consensus-based information filter and a region of interest for state estimation of mobile robots. The framework enables the identification of the input to the dynamic process using remote sensing, enhancing the state prediction accuracy for low-visibility and occlusion scenarios in dynamic scenes. Experimental evaluations in indoor settings confirm the effectiveness of the framework in terms of accuracy and computational efficiency. These results highlight the benefit of integrating stationary LiDAR sensors' state estimates into a switching consensus information filter to enhance the reliability of tracking and to reduce estimation error in the sense of mean square and covariance.

Robust speed estimation for a moving harmonic acoustic source with a single stationary sensor.

A noise-insensitive cost function was developed for estimating the speed of harmonic acoustic sources in uniform linear motion. This function weighs and integrates the energy distribution of received tones in the time-frequency plane to enhance the robustness of parameter estimation under low signal-to-noise ratio conditions, where weight values are intentionally combined with the law of observed instantaneous frequency. As the cost function is differentiable, the procedure of parameter estimations also has high computing efficiency. Processing data of SWellEx-96 experiments with real ocean noise confirmed the anti-noise capabilities of this cost function to conventional processing methods.

Field Testing of Gamma-Spectroscopy Method for Soil Water Content Estimation in an Agricultural Field.

Gamma-ray spectroscopy (GRS) enables continuous estimation of soil water content (SWC) at the subfield scale with a noninvasive sensor. Hydrological applications, including hyper-resolution land surface models and precision agricultural decision making, could benefit greatly from such SWC information, but a gap exists between established theory and accurate estimation of SWC from GRS in the field. In response, we conducted a robust three-year field validation study at a well-instrumented agricultural site in Nebraska, United States. The study involved 27 gravimetric water content sampling campaigns in maize and soybean and 40K specific activity (Bq kg-1) measurements from a stationary GRS sensor. Our analysis showed that the current method for biomass water content correction is appropriate for our maize and soybean field but that the ratio of soil mass attenuation to water mass attenuation used in the theoretical equation must be adjusted to satisfactorily describe the field data. We propose a calibration equation with two free parameters: the theoretical 40K intensity in dry soil and a, which creates an "effective" mass attenuation ratio. Based on statistical analyses of our data set, we recommend calibrating the GRS sensor for SWC estimation using 10 profiles within the footprint and 5 calibration sampling campaigns to achieve a cross-validation root mean square error below 0.035 g g-1.

Information technologies in the construction of the field of radiation pollution of the locality and forecasting

The article examines the improvement of information technologies in the construction of the field of radiation contamination of the area based on the measured values of the impact factors of a nuclear explosion. Forecasting uses summaries of radioactive contamination centers and meteorological information. This process is quite well formalized and its practical implementation does not present great difficulties in automated systems for monitoring the radiation environment.Studies have shown that with a large heterogeneity of the source data by location (the presence of significant zones in which measurements were not carried out), this approach can unjustifiably overestimate or underestimate the calculated values in these zones. The local interpolation method was used to correct this effect. It is based on the assumption of the presence of local linear dependencies in the source data.In automated radiation monitoring systems, interpolation methods are used in the presence of a widespread network of stationary sensors connected to communication channels.The interpretation of radiation reconnaissance data using interpolation methods does not allow using a priori information about the parameters of the cell and the conditions for the formation of radiation contamination of the area. Joint accounting in the processing of these data allows you to combine the stages of forecasting and detection of the actual situation into a single process.

MLSTL-WSN: machine learning-based intrusion detection using SMOTETomek in WSNs

In the domain of cyber-physical systems, wireless sensor networks (WSNs) play a pivotal role as infrastructures, encompassing both stationary and mobile sensors. These sensors self-organize and establish multi-hop connections for communication, collectively sensing, gathering, processing, and transmitting data about their surroundings. Despite their significance, WSNs face rapid and detrimental attacks that can disrupt functionality. Existing intrusion detection methods for WSNs encounter challenges such as low detection rates, computational overhead, and false alarms. These issues stem from sensor node resource constraints, data redundancy, and high correlation within the network. To address these challenges, we propose an innovative intrusion detection approach that integrates machine learning (ML) techniques with the Synthetic Minority Oversampling Technique Tomek Link (SMOTE-TomekLink) algorithm. This blend synthesizes minority instances and eliminates Tomek links, resulting in a balanced dataset that significantly enhances detection accuracy in WSNs. Additionally, we incorporate feature scaling through standardization to render input features consistent and scalable, facilitating more precise training and detection. To counteract imbalanced WSN datasets, we employ the SMOTE-Tomek resampling technique, mitigating overfitting and underfitting issues. Our comprehensive evaluation, using the wireless sensor network dataset (WSN-DS) containing 374,661 records, identifies the optimal model for intrusion detection in WSNs. The standout outcome of our research is the remarkable performance of our model. In binary classification scenarios, it achieves an accuracy rate of 99.78%, and in multiclass classification scenarios, it attains an exceptional accuracy rate of 99.92%. These findings underscore the efficiency and superiority of our proposal in the context of WSN intrusion detection, showcasing its effectiveness in detecting and mitigating intrusions in WSNs.