Dual-band millimetre wave MIMO antenna with reduced mutual coupling based on optimized parasitic structure and ground modification.

In this study, a high-isolation dual-band (28/38 GHz) multiple-input-multiple-output (MIMO) antenna for 5G millimeter-wave indoor applications is presented. The antenna consists of two interconnected patches. The primary patch is connected to the inset feed, while the secondary patch is arc-shaped and positioned over the main patch, opposite to the feed. Both patches function in the lower 28 GHz band, while the primary patch is accountable for inducing the upper 38 GHz band. An expedited trust-region (TR) algorithm is employed to optimize the dimensions of the antenna components, ensuring the antenna operates efficiently with high reflection at both bands. The antenna demonstrates a gain exceeding 7 dBi at both frequencies. An array of four antennas is configured orthogonally to create a MIMO system with isolation surpassing 19 dB. The isolation is further enhanced through the addition of a circular parasitic patch at the front and modifications made to the ground. The TR method is employed again to optimize their parameters and achieve the desired isolation, exceeding 32 dB at both bands. The MIMO system demonstrates outstanding diversity performance at both frequencies, characterized by low values of the envelope correlation coefficient (ECC) (< 10 - 4), channel capacity loss (CCL) (< 0.03 bit/s/Hz), and total active reflection coefficient (TARC) (< - 10 dB). Additionally, it secures a diversity gain (DG) exceeding 9.99 dB. The MIMO system is manufactured and tested, showing good alignment between simulation and measurement data for all performance metrics.

Antenna optimization using machine learning with reduced-dimensionality surrogates.

In modern times, antenna design has become more demanding than ever. The escalating requirements for performance and functionality drive the development of intricately structured antennas, where parameters must be meticulously adjusted to achieve peak performance. Often, global adjustments to geometry are necessary for optimal results. However, direct manipulation of antenna responses evaluated with full-wave electromagnetic (EM) simulation models using conventional nature-inspired methods entails significant computational costs. Alternatively, surrogate-based techniques show promise but are impeded by dimensionality-related challenges and nonlinearity of antenna outputs. This study introduces an innovative technique for swiftly optimizing antennas. It leverages a machine learning framework with an infill criterion employing predicted enhancement of the merit function, utilizing a particle swarm optimizer as the primary search engine, and employs kriging for constructing the underlying surrogate model. The surrogate model operates within a reduced-dimensionality domain, guided by directions corresponding to maximum antenna response variability identified through fast global sensitivity analysis, tailored explicitly for domain determination. Operating within this reduced domain enables building dependable metamodels at a significantly lower computational cost. To address accuracy loss resulting from dimensionality reduction, the global optimization phase is supplemented by local sensitivity-based parameter adjustment. Extensive comparative experiments involving various planar antennas demonstrate the competitive operation of the presented technique over machine learning algorithms operating in full-dimensionality space and direct EM-driven bio-inspired optimization techniques.

Fast machine-learning-enabled size reduction of microwave components using response features.

Achieving compact size has emerged as a key consideration in modern microwave design. While structural miniaturization can be accomplished through judicious circuit architecture selection, precise parameter tuning is equally vital to minimize physical dimensions while meeting stringent performance requirements for electrical characteristics. Due to the intricate nature of compact structures, global optimization is recommended, yet hindered by the excessive expenses associated with system evaluation, typically conducted through electromagnetic (EM) simulation. This challenge is further compounded by the fact that size reduction is a constrained problem entailing expensive constraints. This paper introduces an innovative method for cost-effective explicit miniaturization of microwave components on a global scale. Our approach leverages response feature technology, formulating the optimization problem based on a set of characteristic points derived from EM-analyzed responses, combined with an implicit constraint handling approach. Both elements facilitate handling size reduction by transforming it into an unconstrained problem and regularizing the objective function. The core search engine employs a machine-learning framework with kriging-based surrogates refined using the predicted improvement in the objective function as the infill criterion. Our algorithm is demonstrated using two miniaturized couplers and is shown superior over several benchmark routines, encompassing both conventional (gradient-based) and population-based procedures, alongside a machine learning technique. The primary strengths of the proposed framework lie in its reliability, computational efficiency (with a typical optimization cost ranging from 100 to 150 EM circuit analyses), and straightforward setup.

A compact circularly polarized dielectric resonator antenna with MIMO characterizations for UWB applications.

Ultra-wideband (UWB) technology is extensively used in indoor navigation, medical applications, and Internet of Things devices due to its low power consumption and resilience against multipath fading and losses. This paper examines a multiple-input multiple-output (MIMO), circularly polarized (CP) dielectric resonator antenna for UWB systems. Compact form factor, high gain, wideband response, improved port isolation, and high data rates are the major design goals. This arrangement consists of two identical DRAs with self-decoupled orthogonal orientations eliminating the need for extra decoupling structures while achieving an impressive maximum isolation of 43 dB. The corner-edge feeding mechanism of the extended feedline generates two orthogonal E-fields, facilitating circular polarization. Additionally, a printed hook-shaped stub integrated with the ground plane enhances CP performance across the two operating bands without altering the DR structure. Fabrication and testing exhibit an impressive 133 % impedance bandwidth (2.5-14 GHz) with high port isolation. For a 3 dB axial ratio reference, the single-element design exhibits axial ratio bandwidths (ARBW) of 1.2 GHz (3.6-4.8 GHz) and 0.8 GHz (9.3-10.1 GHz). Remarkably, the MIMO configuration achieves a single ARBW of 0.5 GHz (3.9-4.4 GHz). Detailed investigations of MIMO performance parameters, including diversity gain, envelope correlation coefficient, channel capacity loss, and total active reflection coefficient, underscore the design's efficacy, making it a good choice for UWB wireless applications.

A low-profile 3-D printable metastructure for performance improvement of aperture antennas.

In order to increase the radiation performance of aperture-type antennas, this paper demonstrates a low-profile, planar, single-layer, three-dimensional (3-D) printable metastructure. The proposed hybridized metastructure is highly transparent as it is made out of novel hybrid meta-atoms having transmission coefficient magnitudes greater than - 0.72 dB and fully complies with the near-field phase transformation principle. The hybridized design approach makes the metastructure planar, low-profile, light in weight, and compatible with additive printing technology. For the proof-of-concept, such metastructure is developed and numerically verified to enhance the radiation performance of a resonant cavity antenna (RCA). With the proposed metastructure, the peak directivity of the RCA is improved by 8.6 dBi (from 11.4 dBi to 20 dBi) at the operating frequency of 12.4 GHz. The aperture efficiency and 3-dB directivity bandwidth of the RCA with the metastructure are 41.46% and 16.5%, respectively. Using readily accessible thermoplastics or polymers and copper with cost-effective fused deposition modeling (FDM) 3-D printing technology, the proposed planar hybridized metastructure can be prototyped commercially.

Improved efficacy behavioral modeling of microwave circuits through dimensionality reduction and fast global sensitivity analysis.

Behavioral models have garnered significant interest in the realm of high-frequency electronics. Their primary function is to substitute costly computational tools, notably electromagnetic (EM) analysis, for repetitive evaluations of the structure under consideration. These evaluations are often necessary for tasks like parameter tuning, statistical analysis, or multi-criterial design. However, constructing reliable surrogate models faces several challenges, including the nonlinearity of circuit characteristics and the vast size of the parameter space, encompassing both dimensionality and design variable ranges. Additionally, ensuring the validity of the model across broad geometry/material parameter and frequency ranges is crucial for its utility in design. The purpose of this paper is to introduce an innovative approach to cost-effective and dependable behavioral modeling of microwave passives. Central to our method is a fast global sensitivity analysis (FGSA) procedure, which is devised to identify correlations between design parameters and quantify their impacts on circuit characteristics. The most significant directions identified through FGSA are utilized to establish a reduced-dimensionality domain. Within this domain, the model may be constructed using a limited amount of data samples while capturing a significant portion of the circuit response variability, rendering it suitable for design purposes. The outstanding predictive capability of the proposed model, its superiority over traditional techniques, and its readiness for design applications are demonstrated through the analysis of three microstrip circuits of diverse characteristics.

Millimeter wave negative refractive index metamaterial antenna array.

In this paper, a novel negative refractive index metamaterial (NIM) is developed and characterized. The proposed metamaterial exhibits negative effective permittivity (εeffe) and negative effective permeability (µeffe) at millimeter wave frequency of 28 GHz. This attractive feature is utilized to enhance the gain of a microstrip patch antenna (MPA). Two thin layers of 5 × 5 subwavelength unit cell array of NIM are placed above a single MPA to enhance the gain of the antenna. Each unit cell has an area of 3.4 × 3.4 mm2. A gain increase of 7.9 dBi has been observed when using the proposed NIM as a superstrate. Furthermore, the NIM array is placed over a 2 × 2 array of MPAs with four ports to demonstrate versatility of the metamaterial. The total size of the 2 × 2 antenna array system with N-MTM is about 61.1 × 34 × 16mm3 (5.71λ × 3.18λ × 1.5λ, where λ is the free-space wavelength at 28 GHz). The measurement result indicate that the maximum gain of the antenna array is 13.5dBi. A gain enhancement of 7.55 dB in E-Plane and 7.25 dB in H-Plane at the resonant frequency of 28 GHz is obtained. The proposed antenna structure is suitable for 5G millimeter wave communications, in particular, for possible implementation in future millimeter wave access points and cellular base stations.

Unequally-spaced slot strategy for radiation null reduction in single SIW-embedded antenna element.

The incorporation of higher-order modes (HOMs) can substantially augment the antenna gain and bandwidth, but this improvement is typically accompanied by compromised radiation performance including radiation nulls and higher side lobe levels. In this study, an inventive strategy is introduced to reduce the radiation nulls and the side lobe levels of a single antenna element by positioning multiple slots of the radiating element at unequal spacing. Dual hybrid HOMs are analyzed inside a substrate integrated waveguide-based cavity to design a wide band, enhanced gain dual-polarized antenna. The radiating element of the antenna is designed with multiple slots positioned at unequal spacing but symmetrical along the origin. This methodology provides three-fold advantages: a reduction of side lobes, an adjustment of phase center, and a significant reduction of radiation nulls. The antenna has been fabricated, and experimentally validated. The antenna exhibits a reduction in radiation null to - 0.5 dB, a phase adjustment of the main lobe to 0°, and a reduction in side lobe level from - 14.4 dB (N = 2, equal spacing) and - 15.5 dB (N = 4, equal spacing) a maximum of - 19.7 dB (N = 4, unequal spacing) at 12.35 GHz in the phi-0 plane. Excellent agreement between measured and simulated results corroborates the efficacy of the proposed approach. The significant improvement in the radiation performance of the single-element antenna design sets the antenna design apart from the state-of-the-art solutions.

Design and experimental validation of a metamaterial-based sensor for microwave imaging in breast, lung, and brain cancer detection.

This study proposes an innovative geometry of a microstrip sensor for high-resolution microwave imaging (MWI). The main intended application of the sensor is early detection of breast, lung, and brain cancer. The proposed design consists of a microstrip patch antenna fed by a coplanar waveguide with a metamaterial (MTM) layer-based lens implemented on the back side, and an artificial magnetic conductor (AMC) realized on as a separate layer. The analysis of the AMC's permeability and permittivity demonstrate that the structure exhibits negative epsilon (ENG) qualities near the antenna resonance point. In addition, reflectivity, transmittance, and absorption are also studied. The sensor prototype has been manufactures using the FR4 laminate. Excellent electrical and field characteristics of the structure are confirmed through experimental validation. At the resonance frequency of 4.56 GHz, the realized gain reaches 8.5 dBi, with 3.8 dBi gain enhancement contributed by the AMC. The suitability of the presented sensor for detecting brain tumors, lung cancer, and breast cancer has been corroborated through extensive simulation-based experiments performed using the MWI system model, which employs four copies of the proposed sensor, as well as the breast, lung, and brain phantoms. As demonstrated, the directional radiation pattern and enhanced gain of the sensor enable precise tumor size discrimination. The proposed sensor offers competitive performance in comparison the state-of-the-art sensors described in the recent literature, especially with respect to as gain, pattern directivity, and impedance matching, all being critical for MWI.

Height and integration in proximity networks among Tanzanian Hadza men.

In recent years there has been much interest in investigating the extent to which social status or prestige are related to an individual's degree of integration in social networks. It has been shown that, among hunter-gatherers, social characteristics of an individual based on social status or prestige, such foraging reputation, friendship popularity, and pro-social reputation, can influence the extent to which an individual is embedded in a social network. However, little is known regarding the extent to which height, a physical trait that in Western societies is often associated with social status, is associated in integration in social networks among small-scale hunter gatherers. Here, we investigated the relationship between height and a position an individual occupies in proximity networks among Hadza men (n = 30), hunter-gatherers living in Northern Tanzania. The results of our study show that height is not related to the position an individual maintains in proximity networks. We argue that, in a relatively egalitarian small-scale hunter-gatherer societies such as the Hadza, social interactions driving proximity networks might be influenced by social traits, such as popularity and hunting reputation, rather than physical traits, such as height.

Design and implementation of multi-band reflectarray metasurface for 5G millimeter wave coverage enhancement.

A compact low-profile multi-band millimeter-wave (mm-wave) reflectarray metasurface design is presented for coverage enhancement in 5G and beyond cellular communication. The proposed single-layer metasurface exhibits a stable reflection response under oblique incidence angles of up to 60 ∘ at 24 and 38 GHz, and transmission response at 30 GHz, effectively covering the desired 5G mm-wave frequency bands. The proposed reflectarray metasurface is polarization insensitive and performs equally well under TE and TM polarized incident waves due to the symmetric pattern. In addition, the low profile of the proposed metasurface makes it appropriate for conformal applications. In comparison to the state-of-the-art, the proposed reflectarray metasurface unit cell design is not only compact (3.3  ×  3.3 mm 2 ) but also offers two reflections and one transmission band based on a single-layer structure. It is easy to reconfigure the proposed metasurface unit cell for any other frequency band by adjusting a few design parameters. To validate the concept of coverage enhancement, a 32  ×  x32 unit-cell prototype of the proposed reflectarray metasurface is fabricated and measured under different scenarios. The experimental results demonstrate that a promising signal enhancement of 20-25 dB is obtained over the entire 5G mm-wave n258, n259, and n260 frequency bands. The proposed reflectarray metasurface has a high potential for application in mm-wave 5G networks to improve coverage in dead zones or to overcome obstacles that prevent direct communication linkages.

Variable data structures and customized deep learning surrogates for computationally efficient and reliable characterization of buried objects.

In this study, in order to characterize the buried object via deep-learning-based surrogate modeling approach, 3-D full-wave electromagnetic simulations of a GPR model have been used. The task is to independently predict characteristic parameters of a buried object of diverse radii allocated at different positions (depth and lateral position) in various dispersive subsurface media. This study has analyzed variable data structures (raw B-scans, extracted features, consecutive A-scans) with respect to computational cost and accuracy of surrogates. The usage of raw B-scan data and the applications for processing steps on B-scan profiles in the context of object characterization incur high computational cost so it can be a challenging issue. The proposed surrogate model referred to as the deep regression network (DRN) is utilized for time frequency spectrogram (TFS) of consecutive A-scans. DRN is developed with the main aim being computationally efficient (about 13 times acceleration) compared to conventional network models using B-scan images (2D data). DRN with TFS is favorably benchmarked to the state-of-the-art regression techniques. The experimental results obtained for the proposed model and second-best model, CNN-1D show mean absolute and relative error rates of 3.6 mm, 11.8 mm and 4.7%, 11.6% respectively. For the sake of supplementary verification under realistic scenarios, it is also applied for scenarios involving noisy data. Furthermore, the proposed surrogate modeling approach is validated using measurement data, which is indicative of suitability of the approach to handle physical measurements as data sources.

Growth status and age at peak height velocity among youth participants in several sports: the Cracow longitudinal study.

BACKGROUND: Studies addressing age at peak height velocity (PHV) in longitudinal samples of participants in sports are relatively limited. PURPOSE: To compare the growth status and estimated ages at PHV of longitudinal samples girls and boys active in sport with peers not active in sport, and to compare estimated ages at PHV among longitudinal samples of Polish youth active in sport. METHODS: Records from the Cracow Longitudinal Study, which measured youth annually from 8 to 18 years, were screened to identify individuals regularly active in sport. Participants in athletics (22 girls, 10 boys), soccer (12 boys), and other team (6 girls, 7 boys) and individual (6 girls, 9 boys) sports were identified; 107 girls and 172 boys were not active in sport. Heights and weights of participants in sports and non-involved peers were compared. Longitudinal height records of individuals were fit with the SITAR model to estimate age at PHV. Ages at PHV of boys and girls active in sport and peers not active in sports were compared with sex-specific ANOVAs. RESULTS: Ages at PHV of boys participating in athletics and soccer were similar to age at PHV of boys not active in sport, while ages at PHV of boys in other team sports (basketball, volleyball, handball) and individual sports (skiing, gymnastics, acrobatics) were, respectively, slightly earlier and later. Among girls, age at PHV of participants in team sports (basketball, netball) was earlier, while ages at PHV among participants in athletics and other individual sports (equestrian, acrobatics, shooting) were slightly later compared to non-athlete peers. CONCLUSION: Ages at PHV varied among participants in different sports and were consistent with estimates in other longitudinal samples of Polish youth athletes.

Fast EM-driven nature-inspired optimization of antenna input characteristics using response features and variable-resolution simulation models.

Utilization of optimization technique is a must in the design of contemporary antenna systems. Often, global search methods are necessary, which are associated with high computational costs when conducted at the level of full-wave electromagnetic (EM) models. In this study, we introduce an innovative method for globally optimizing reflection responses of multi-band antennas. Our approach uses surrogates constructed based on response features, smoothing the objective function landscape processed by the algorithm. We begin with initial parameter space screening and surrogate model construction using coarse-discretization EM analysis. Subsequently, the surrogate evolves iteratively into a co-kriging model, refining itself using accumulated high-fidelity EM simulation results, with the infill criterion focusing on minimizing the predicted objective function. Employing a particle swarm optimizer (PSO) as the underlying search routine, extensive verification case studies showcase the efficiency and superiority of our procedure over benchmarks. The average optimization cost translates to just around ninety high-fidelity EM antenna analyses, showcasing excellent solution repeatability. Leveraging variable-resolution simulations achieves up to a seventy percent speedup compared to the single-fidelity algorithm.

Highly integrable planar-structured printed circularly polarized antenna for emerging wideband internet of things applications in the millimeter-wave band.

This paper proposes a numerically and experimentally validated printed wideband antenna with a planar geometry for Internet of Things (IoT) applications. This design tackles the challenges associated with deploying IoT sensors in remote areas or across extensive geographical regions. The proposed design exploits a coplanar-waveguide-fed modified microstrip line monopole for excitation of circularly polarized waves radiating in the broadside direction. The primary design is based on perturbations of the microstrip line protracted from a grounded coplanar waveguide. The capacitively coupled short rectangular stubs are periodically inserted alternately and excited asymmetrically on each side of the microstrip line parallel to the direction of the electric field vector. The sequential phase excitation of the periodic stubs generates a rectangular-cascaded electric field, which suppresses the stop band at the open end. As a result, the antenna radiates in the broadside direction. The impedance bandwidth of the antenna exceeds 8 GHz in the 28 GHz mm-wave band, i.e., it ranged from 25 to 33.5 GHz. Additionally, an axial ratio below 3 dB is achieved within the operating band from 26 to 33.5 GHz with the alterations of the surface current using straightforward topological adjustments of the physical parameters. The average in-band realized gain of the antenna is 10 dBic when measured in the broadside direction. These results indicate that the proposed design has the potential to improve the connectivity between IoT devices and the constantly varying orientation of satellites by mitigating the polarization mismatch.

Expedited re-design of multi-band passive microwave circuits using orthogonal scaling directions and gradient-based tuning.

Geometry scaling of microwave circuits is an essential but challenging task. In particular, the employment of a given passive structure in a different application area often requires re-adjustment of the operating frequencies/bands while maintaining top performance. Achieving this necessitates the utilization of numerical optimization methods. Nonetheless, if the intended frequencies are distant from the ones at the starting point, local search procedures tend to fail, whereas global search algorithms are computationally expensive. As recently demonstrated, a combination of large-scale concurrent geometry parameter scaling with intermittent local tuning allows for dependable re-design of high-frequency circuits at low CPU costs. Unfortunately, the procedure is only applicable to single-band structures due to synchronized modifications of all operating bands under scaling. This article discusses a novel procedure that leverages a similar overall concept, but allows for independent control of all center frequencies. To achieve this goal, an automated decision-making procedure is developed in which a set of orthogonal scaling directions are determined based on their effect on individual circuit bands, and using auxiliary optimization sub-problems. The scaling range is then automatically computed by solving an appropriately-defined least-square design relocation problem. The methodology introduced in the work is illustrated using two planar passive devices. In both cases, wide-range operating frequency re-design has been demonstrated and favorably compared to conventional gradient-based tuning. Furthermore, the presented procedure has been shown to be computationally efficient. It is also easy to implement and integrate with a variety of gradient-based optimization procedures of a descent type.

The change in handgrip strength, after physical exercise, is moderated by digit ratio (2D:4D): A study among the young adults in Poland.

BACKGROUND: The digit ratio (2D:4D), the ratio of the lengths of second (2D) to the fourth (4D) fingers, is a proxy indicator of prenatal androgen exposure. On average, males display lower 2D:4D than females. Previous studies have shown that lower 2D:4D ratios were associated with better sports and physical abilities. AIM: To assess whether a challenge condition, imposed by intense exercise, could increase handgrip strength (HGS) associated with 2D:4D. METHODS: This cross-sectional experimental study included 90 healthy young Polish adults (40 males, 50 females). They underwent intense physical exercise, before (7 days) and after which they were measured for HGS and 2D:4D. Height and weight were also measured. Analyses of Covariance were employed to delineate associations. RESULTS: 2D:4D had significant predictive effects on the differences in HGS (DHGS) measured in two occasions, without and after, physical exercises. The lower was the 2D:4D, the higher the DHGS, particularly, for the left hand. CONCLUSION: The results reconfirmed that the link between prenatal testosterone exposure (indicated by 2D:4D) and physical strength depends on the context, such as a challenged condition.

Age at peak height velocity in Polish adolescents: Effect of socioeconomic factors.

Age at peak height velocity (APHV) is an indicator of maturity timing which is applicable to both sexes, and which is influenced by environmental factors. The objective of this study was to assess variation in APHV associated with several indicators of socioeconomic status (SES) in a longitudinal sample of Polish adolescents. The sample included 739 boys born in 1983 and followed annually from 12 to 16 years, and 597 girls born in 1985 and followed annually from 9 to 13 years. The height records were fitted with the SITAR model to estimate APHV. SES was estimated using principal component analysis of indicators of familial status based on parental education, family size, living conditions and household possessions. Statistical analyses included analysis of variance (one-way for general SES and three-way for parental education and family size) and Tukey post-hoc tests for unequal samples. General SES (p <.001) and family size (p < .05) significantly influenced APHV among boys, while only maternal education (p < .05) significantly influenced APHV among girls. Among youth from families of higher SES, as defined by the respective indicators, APHV was attained significantly earlier, on average, than in peers from families of lower SES. Overall, the results showed a sex-dependent effect of SES on APHV, and highlighted the influence of favorable socioeconomic conditions for optimal growth and maturation during adolescence.

An improvement of body surface area formulas using the 3D scanning technique.

OBJECTIVES: Body surface area (BSA) is one of the major parameters used in several medical fields. However, there are concerns raised about its usefulness, mostly due to the ambiguity of its estimation. MATERIAL AND METHODS: Authors have conducted a voluntary study to investigate BSA distribution and estimation in a group of 179 adult people of various sex, age, and physique. Here, there is provided an extended analysis of the majority of known BSA formulas. Furthermore, it was supplement with a comparison with the authors' propositions of enhanced formulas coefficients for known formulas models as well as with new power models based on an increased number of anthropometric data. RESULTS: Introduction of the enhanced formulas coefficients cause a reduction of at least 30.5% in mean absolute error and 21.1% in maximum error in comparison with their known counterparts. CONCLUSIONS: In the context of the analysis presented it can be stated that the development of a single universal body surface area formula, based on a small number of state variables, is not possible. Therefore, it is necessary and justified to search for new estimation models that allow for quick and accurate calculation of body surface area for the entire population, regardless of individual body variations. The new formulas presented are such an alternative, which achieves better results than the previously known methods. Int J Occup Med Environ Health. 2024;37(2):205-19.

Statistical data pre-processing and time series incorporation for high-efficacy calibration of low-cost NO2 sensor using machine learning.

Air pollution stands as a significant modern-day challenge impacting life quality, the environment, and the economy. It comprises various pollutants like gases, particulate matter, biological molecules, and more, stemming from sources such as vehicle emissions, industrial operations, agriculture, and natural events. Nitrogen dioxide (NO2), among these harmful gases, is notably prevalent in densely populated urban regions. Given its adverse effects on health and the environment, accurate monitoring of NO2 levels becomes imperative for devising effective risk mitigation strategies. However, the precise measurement of NO2 poses challenges as it traditionally relies on costly and bulky equipment. This has prompted the development of more affordable alternatives, although their reliability is often questionable. The aim of this article is to introduce a groundbreaking method for precisely calibrating cost-effective NO2 sensors. This technique involves statistical preprocessing of low-cost sensor readings, aligning their distribution with reference data. Central to this calibration is an artificial neural network (ANN) surrogate designed to predict sensor correction coefficients. It utilizes environmental variables (temperature, humidity, atmospheric pressure), cross-references auxiliary NO2 sensors, and incorporates short time series of previous readings from the primary sensor. These methods are complemented by global data scaling. Demonstrated using a custom-designed cost-effective monitoring platform and high-precision public reference station data collected over 5 months, every component of our calibration framework proves crucial, contributing to its exceptional accuracy (with a correlation coefficient near 0.95 concerning the reference data and an RMSE below 2.4 µg/m3). This level of performance positions the calibrated sensor as a viable, cost-effective alternative to traditional monitoring approaches.