Local Monitoring System Research Articles

Implementation of home OSAHS screening device based on sleep sounds

Obstructive Sleep Apnea-Hypopnea Syndrome (OSAHS) is a common chronic sleeping respiratory condition. Screening for OSAHS approaches based on sleep breathing sounds has received much attention since it can provide fully noncontact monitoring at home. Deploying a diagnostic sound-based OSAHS system on a smartphone not only interferes with regular phone use but may also pose privacy problems, as well as suffer from decreasing accuracy owing to device variances. This work describes a local OSAHS monitoring system implementation designed for a dedicated device to estimate the apnea-hypopnea index and screening for OSAHS while doing away with concerns about the abovementioned issue. The OSAHS screening system is deployed on a Kendryte K510 (Canaan Inc.), a low-power RISC-V 64-bit CPU that has 2.5 TFLOPS, to analyze sleep breath sounds in a 9-s window. The design results are relatively low-cost and efficient for screening severe OSAHS. The equipment can be further used as a platform to evaluate the performance of the OSAHS diagnosis model.

Local Government Monitoring System’s Design and Implementation in Ghana from the Lens of the Project Life Cycle

Monitoring at the subnational level has connotations for the effectiveness of local governance in the developing world. Using a cross-sectional survey underpinned by the project life cycle model, the paper contributes to understanding essential considerations in developing and implementing subnational monitoring in Africa. About 74 of the targeted 275 District Development Officers responded to the online Google form questionnaire. The study employed descriptive statistics to analyze data. Results demonstrate that the monitoring system is excellent in design, but its implementation and reflection stages are weak. It highlights planning for subnational monitoring systems encompassing setting clear objectives, utilizing robust indicators, involving stakeholders, and an elaborate plan for data collection, analysis, communication, and reporting as vital ingredients of a monitoring system. Sufficient resources and capacity-building initiatives, including providing on-the-job training, hiring experienced staff, committing financial resources and logistics, and backstopping support, are necessary to implement monitoring activities effectively. An appropriate policy environment, including manuals and legislation, is critical to anchoring and sustaining subnational monitoring systems. Local government’s monitoring systems should prioritize learning, knowledge sharing, and documentation of lessons learned to facilitate programmatic improvements and replication and devote at least 2.5% of the District Assembly Common Fund to finance monitoring and evaluation actions.

Design and Installation of a Local Monitoring System to Validate Debris Flow Methodology for Risk Mitigation

Landslides pose significant threats to communities and infrastructure worldwide, necessitating the development of effective hazard and exposure reduction strategies to mitigate the potential risks. In particular, debris flows can be highly destructive landslides. The paper deals with an integrated monitoring system designed both to further validate an existing debris flow inception and propagation methodology developed by the authors and to fine-tune the landslide inception and warning model to be used in an early warning system. The design of the integrated monitoring system, the definition of the acquisition time of instruments, and the processing of the measured data were based on studies performed in the study area of Favazzina (Italy), which is affected by debris flows that are very difficult to monitor. The proposed approach used to design the integrated monitoring system may serve as a useful methodological tool to be adopted in similar geological and geotechnical contexts within the framework of risk mitigation strategies.

Cytogenetic monitoring of spontaneous mutagenesis

Due to the challenging environmental situation in Ukraine, there is a need for cytogenetic monitoring, establishing cause-and-effect relationships, and assessing the toxic-mutagenic activity of environmental components. The results of such monitoring can serve as a basis for developing rehabilitation measures aimed at improving the environmental condition. Cytogenetic bioassay methods allow the evaluation of ecological and genetic risks to biota, considering the overall impact of pollutants, predicting changes in ecosystems, and making timely management decisions to improve environmental quality and preserve the nation’s gene pool. The article provides cytogenetic monitoring of apical meristems of the roots of Raphanus sativus subsp. radicula (Pers.) DC. and Allium cepa L. seedlings., grown on soils of residential areas, and the effect of ions of some elements on the cytological parameters of Pisum sativum L. was studied. It was noted that the spectrum of mitosis abnormalities and chromosome aberrations was expanded due to lagging chromosomes and micronuclei. Residential areas with a consistently high level of spontaneous cytogenetic disorders require the development of a local monitoring system to identify genetic hazards. The research on the proliferative activity of apical meristem cells confirms the hypothesis of aluminum toxicity to plants. Cytotoxic effects are assessed at the micro- and macroscopic levels. Macroscopically, reduced root growth of bioindicator plants was observed, which may result from several possible mechanisms: cell death, inhibition of division, cell elongation, or nutrient absorption. It was found that the duration of the prophase is directly influenced by the mobile forms of Zn and Pb, while Cu has a reverse effect. According to the results of multiple regression analysis, the most significant influence on these processes is exerted by the mobile forms of Zn, Cu, and Pb in the surface layers of the soils of the studied residential areas. Under the influence of AlCl3, the proportion of cells in the anaphase stage increases; CdCl2 affects the prophase stage; Na2SeO3 affects the meta- and anaphase stages; X-ray irradiation affects the telophase stage. Regarding the ability to induce the frequency of aberrant anaphases, a ranking can be constructed: Na2SeO3 (3.75·10–6 M) > AlCl3 (3.86·10–5 M) > CdCl2 (8.44·10–5 M). A radiation dose of 9.03·10–3 C/kg leads to the frequency of chromosomal aberrations, similar to the effects of AlCl3 (3.86·10–4 M) and Na2SeO3 (8.34·10–6 M). High concentrations of aluminum are associated with an increase in anaphases with fragments and two to three bridges.

A novel Q-learning-based secure routing scheme with a robust defensive system against wormhole attacks in flying ad hoc networks

Nowadays, unmanned aerial vehicles (UAVs) organized in a flying ad hoc network (FANET) can successfully carry out complex missions. Due to the limitations of these networks, including the lack of infrastructure, wireless communication channels, dynamic topology, and unreliable communication between UAVs, cyberattacks, especially wormholes, weaken the performance of routing schemes. Therefore, maintaining communication security and guaranteeing the quality of service (QoS) are very challenging. In this paper, a novel Q-learning-based secure routing scheme (QSR) is presented for FANETs. QSR seeks to provide a robust defensive system against wormhole attacks, especially wormhole through encapsulation and wormhole through packet relay. QSR includes a secure neighbor discovery process and a Q-learning-based secure routing process. Firstly, each UAV gets information about its neighboring UAVs securely. To secure communication in this process, a local monitoring system is designed to counteract the wormhole attack through packet relay. This system checks data packets exchanged between neighboring UAVs and defines three rules according to the behavior of wormholes. In the second process, UAVs perform a distributed Q-learning-based routing process to counteract the wormhole attack through encapsulation. To reward the safest paths, a reward function is introduced based on five factors, the average one-hop delay, hop count, data loss ratio, packet transmission frequency (PTF), and packet reception frequency (PRF). Finally, the NS2 simulator is applied for implementing QSR and executing different scenarios. The evaluation results show that QSR works better than TOPCM, MNRiRIP, and MNDA in terms of accuracy, malicious node detection rate, data delivery ratio, and data loss ratio. However, it has more delay than TOPCM.

The model of choosing a microcontroller for the environmental monitoring system module

Problem. The development and application of modern digital technologies for environmental monitoring is an extremely relevant issue. Such environmental monitoring systems allow for dynamic monitoring of the current state of the studied territories in order to further analyze changes and make decisions on their conservation and development. To improve the environmental situation, it is necessary to constantly improve environmental monitoring systems by creating local environmental monitoring systems operating in real time. Goal. The aim of the study is to develop a model for selecting a microcontroller for an environmental monitoring module based on many functional and cost criteria, which will reduce the time of information collection for a regional environmental monitoring system. Methodology. To achieve this goal, we analyzed the characteristics of microcontrollers. A model for selecting a microcontroller for an environmental monitoring module has been developed based on many functional and cost criteria. An example of using the microcontroller selection model for the environmental monitoring module is given. The method of multicriteria optimization allows the selection of a microcontroller for the module of the environmental monitoring system by calculating the utility function. Results. The paper considers the main tasks of the environmental monitoring system. A mathematical model for selecting a microcontroller for the module of an environmental monitoring system has been developed. It belongs to the class of multicriteria discrete programming models and, unlike the known ones, takes into account the system requirements for the module of the environmental monitoring system as a whole. Originality. The developed model allows us to make a microcontroller according to many functional and cost criteria under conditions of fuzzy input information. Practical value. The use of the proposed model for selecting a microcontroller for the module of the environmental monitoring system will reduce the time of collecting information for the regional environmental monitoring system.

PERFORMANCE EVALUATION OF TEMPORAL MODEL AND SPATIAL CORRELATION METHODS FOR PERSISTENT SCATTERER DETERMINATION IN LANDSLIDE PRONE AREAS

Abstract. The Philippines is no stranger to natural hazards. Aside from flooding, landslides emerge as a primary contributor to damage dealt by natural hazards. Traditional methods for landslide monitoring require on-site field measurements, which makes them resource-intensive and time-consuming. Moreover, the frequency of updating of existing landslide hazard maps is limited by resources and manpower. This research introduces the application of remote sensing technology, specifically Persistent Scatter Interferometry (PSI), as a complementary tool for updating hazard maps. PSI enables the identification of stable ground points, eliminating the need for labor-intensive fieldwork and facilitating assessments of potential slope instability. Two distinct PSI processing methods are evaluated in the study; the Temporal Model approach and the Spatial Correlation model approach. Findings reveal that the Temporal Model approach successfully detected 11,647 Persistent Scatterers (PS) points, while the Spatial Correlation approach identified 272,614 PS points. Furthermore, the Spatial Correlation approach demonstrated its capability to detect PS points within high landslide susceptibility areas. Consequently, the results highlight the suitability of the Spatial Correlation approach for detecting PS points, particularly in landslide-prone regions, offering support to local landslide hazard monitoring systems. This research supports the initiative to a more efficient and cost-effective approach to maintaining up-to-date landslide susceptibility maps in the Philippines in enhancing disaster preparedness and mitigation efforts.

Local Level Monitoring Systems in Community Forestry: Challenges, Opportunities and Directions for Future

A recent study has demonstrated that local level monitoring systems, that could encourage learning and adaptiveness in forest management, are poorly developed, and that this presents a constraint to equitable and active management of forests. This paper reviews the contextual factors and emerging concepts of monitoring, and identifies gaps and prospects. Based on lessons gained thus far, strategies for facilitating local level monitoring are also explored.

Sick building syndrome: do outdoor pollutants and pollen affect it?

Sick building syndrome (SBS) refers to non-specific complaints, including upper-respiratory irritative symptoms, headaches, fatigue, and rash, which are usually associated with a particular building by their temporal pattern of occurrence and clustering among inhabitants or colleagues. The aim of the study was to determine the association between the clinical manifestations of sick building syndrome with outdoor pollutants and airborne pollen. It was a descriptive and prospective observational study conducted from November 2021 to April 2022. It included subjects over 18 years old who completed an online survey on sick building syndrome (general symptoms, nasal, ocular, oropharyngeal, and skin symptoms) presented at home, housing information and personal history. The APS-330 from Pollen Sense ® was used to obtain data on pollen in the air and the local pollution monitoring system (SIMA) to obtain information regarding pollutants. For statistical analysis, SPSS version 16 was used. A total of 402 surveys were included; 91% of the subjects reported having at least 1 symptom. Females presented more general symptoms (fatigue and headache) than males. Subjects with a personal history of atopy showed a higher prevalence of practically all symptoms. Airborne pollen exposure was positively associated with mucosal symptoms in eyes and nose. Outdoor fungi spore exposure was positively associated with oculo-nasal and cutaneous symptoms in the scalp. This study found significant associations with female gender and a history of atopy, which suggests a higher risk for these subjects. Despite the limitations of the study, we can conclude that there is an association between the clinical manifestations of sick building syndrome with indoor and outdoor pollution.

Auditable and Verifiable Federated Learning Based on Blockchain-Enabled Decentralization.

Auditability and verifiability are critical elements in establishing trustworthiness in federated learning (FL). These principles promote transparency, accountability, and independent validation of FL processes. Incorporating auditability and verifiability is imperative for building trust and ensuring the robustness of FL methodologies. Typical FL architectures rely on a trustworthy central authority to manage the FL process. However, reliance on a central authority could become a single point of failure, making it an attractive target for cyber-attacks and insider frauds. Moreover, the central entity lacks auditability and verifiability, which undermines the privacy and security that FL aims to ensure. This article proposes an auditable and verifiable decentralized FL (DFL) framework. We first develop a smart-contract-based monitoring system for DFL participants. This monitoring system is then deployed to each DFL participant and executed when the local model training is initiated. The monitoring system records necessary information during the local training process for auditing purposes. Afterward, each DFL participant sends the local model and monitoring system to the respective blockchain node. The blockchain nodes representing each DFL participant exchange the local models and use the monitoring system to validate each local model. To ensure an auditable and verifiable decentralized aggregation procedure, we record the aggregation steps taken by each blockchain node in the aggregation contract. Following the aggregation phase, each blockchain node applies a multisignature scheme to the aggregated model, producing a globally verifiable model. Based on the signed global model and the aggregation contract, each blockchain node implements a consensus protocol to store the validated global model in tamper-proof storage. To evaluate the performance of our proposed model, we conducted a series of experiments with different machine learning architectures and datasets, including CIFAR-10, F-MNIST, and MedMNIST. The experimental results indicate a slight increase in time consumption compared with the state-of-the-art, serving as a tradeoff to ensure auditability and verifiability. The proposed blockchain-enabled DFL also saves up to 95% communication costs for the participant side.

Interdependence in Coastal Tourist Territories between Marine Litter and Immediate Tourist Zoning Density: Methodological Approach for Urban Sustainable Development

The coastal strip, characterized by the urbanization of coastal tourist territories (CTTs), has expanded over decades through civil engineering, altering the shoreline dynamics and creating artificial beaches crucial for tourism. To examine the relationship between extensive land use in CTTs for tourism and residences and the presence of marine litter, a specific parametric study was conducted along the coast of Tenerife, the largest island in the Canary Islands. Due to Tenerife’s geographical location and exposure to the descending Gulf Stream flow, the coastal waters in the selected zone experience waste impact at both local and global scales. However, the presence of marine litter deposited by ocean currents is at a micro level and falls outside the scope of this report. This study parameterised urban reality in study areas, and the presence of macro waste has been parameterised using standardised units of measurement. This enables the establishment of source measurements that will contribute to preventative measures against this type of coastal pollution. The interdependence between tourist zoning, civil seafront engineering works along the seafront, and marine litter presence in inaccessible and visible areas for tourists requires a methodology to better understand waste origin and loading areas. This knowledge is crucial for an effective local monitoring system. A quantitative overlay reading methodology has been designed in the urban setting through calculations of urban densities, while examining the waste in these areas’ immediate infralittoral flooring through the use of visual underwater extraction. Anticipating the type and quantity of waste in each area will allow for the implementation of effective awareness, promoting action for preventative and corrective measures at the urban level. The results show a direct dependence between urban density and the presence of waste, as well as an equation that makes it possible to anticipate the amount of waste according to urban density and its relational vector. There is no discontinuity between them, as each area is affected by others to the extent that they establish the parametric continuity conditions determining each field. Therefore, it is possible to relate them beyond a one-on-one relationship. This approach fosters sustainable tourism development, reducing pressure on the sea and enhancing the utilisation of tourism revenues in measures to address waste-related challenges and promotes sustainable tourism development in Europe’s coastal regions.

Lung cancer cases attributable to PM2.5 in northeastern Italy

Abstract Background According to the International Agency for Cancer Research (IARC), outdoor pollution is a well established cause of lung cancer, with a prominent carcinogenic role attributed to particulate matter (PM) pollution. 2001 WHO guidelines on outdoor pollution includes a recommendation to reach a PM2.5 annual average of 5ug/m3. The WHO recommendation is in sharp contrast with EU limits: thus, in the present study we estimated the number of incident lung cancer cases due to PM2.5 according to three different scenarios. Methods The number of newly incident lung cancer cases diagnosed in northeastern Italy from 2015 to 2020 was from the population-based cancer registry of the Friuli Venezia Giulia region. We considered three scenarios of average annual concentration of PM2.5: 25ug/m3 according to EU legislation; 10ug/m3 or 5ug/m3 according to 2005 and 2021 WHO guidelines. An 8% increase in the risk of lung cancer for every 10ug/m3 increase in PM2.5 was assumed. Data from outdoor average annual concentration of PM2.5 in northeastern Italy were from local air monitoring systems. Results 5131 lung cancer cases were registered in 2015-2020 in Friuli Venezia Giulia, (i.e., 855 cases/year). In the same period, an average annual concentration of PM2.5 of 18ug/m3 was documented. According to EU legislation, there will not be an excess of future lung cancer cases attributable to PM2.5. Conversely, the projection of the excess cases ranged from 6.4%/year (WHO 2005) or 10.4% (WHO 2021). In absolute terms, we estimated that there will be an excess of future yearly lung cancer cases ranging from 55 cases to 89 cases due to PM2.5.air pollution exceeding WHO recommendations. Conclusions According to WHO recommendations, PM2.5 air pollution will cause an excess of up to 89 yearly cases of lung cancer in Friuli Venezia Giulia, northeastern Italy, a projection in sharp contrast with EU limits. Key messages • An excess of up to 89 yearly cases of lung cancer are projected for the future years due to PM2.5 concentration exceeding WHO guidelines. • EU limits of PM2.5 average yearly concentration underestimate the risk of lung cancer in humans.

Automated service monitoring in the deployment of ARCHER2

SummaryThe ARCHER2 service, a CPU based HPE Cray EX system with 750,080 cores (5860 nodes), has been deployed throughout 2020 and 2021, going into full service in December of 2021. A key part of the work during this deployment was the integration of ARCHER2 into our local monitoring systems. As ARCHER2 was one of the very first large‐scale EX deployments, this involved close collaboration and development work with the HPE team through a global pandemic situation where collaboration and co‐working was significantly more challenging than usual. The deployment included the creation of automated checks and visual representations of system status which needed to be made available to external parties for diagnosis and interpretation. We will describe how these checks have been deployed and how data gathered played a key role in the deployment of ARCHER2, the commissioning of the plant infrastructure, the conduct of HPL runs for submission to the Top500 and contractual monitoring of the availability of the ARCHER2 service during its commissioning and early life.

A Protocol for a Local Community Monitoring and Feedback System for Physical Activity in Organized Group Settings for Children.

Communities are wellness landscapes of geospatially and temporally bound settings where children spend their time. Improving population physical activity (PA) requires investigating available community settings for children, such as classrooms and sport teams, and the dynamic social interactions producing PA. This protocol describes a multiscale community wellness landscape monitoring and feedback system of adult-led organized group settings and PA outcomes for children. The data system assessed organized groups for third- through sixth-grade children in 2 rural communities within seasons (fall 2018-2019). Within each season, groups were identified, sampled, and recruited. Sampled group meetings were assessed for children's PA (accelerometry) and meeting routines (video observation). A data processing protocol time-segmented data into meetings and meeting routines into smaller units (sessions). A purpose code was assigned to each meeting (eg,classroom, sport) and session (eg,academic, PA). Group accelerometer data were paired with the coded segments. Multiscale metrics (season, meeting, and session) were generated and provided to the communities in tailored reports. A total of 94 groups were recruited, and 73 groups with 1302 participants were included in the data system. Data were collected from 213 meetings and 844 sessions. Most participants (83.1%) consented to link their accelerometer data with demographic data from school enrollment records. The community data system identified available organized group settings for children and collected video and PA data from these settings. Incorporating setting data into local data systems provides detailed accounts of whole-of-community PA social systems to inform population health improvement efforts.

Local structural health monitoring system in aircraft based on fiber Bragg grating array

In this study, a structural health monitoring system for aircraft wings based on a fiber-optic grating sensing network was designed, and a three-dimensional position correction algorithm based on fiber Bragg grating (FBG) array test data was developed. Solving the deformation parameters using mathematical models of strain-position offset introduces errors, leading to inaccurate measurements and affecting the preciseness of three-dimensional-reconstructed surfaces. Two fitting algorithms (bitone and spline with linear interpolations) are proposed to improve this method in analyzing errors at the measured points of the wing structure. The relative error of each measurement point of the reconstructed wing structure using the bitone and spline interpolation methods was lower than 4.96%. Furthermore, the absolute error was within 0.014 mm, the average relative error was lower than 3.47%, and the root-mean-square error was lower than 0.01 mm. Compared to linear interpolation, the average relative error decreased by up to 5.84%. The experimental results show that the measurement accuracy of bitone and spline interpolation was significantly higher than that of linear interpolation. FBG array measurements using bitone and spline interpolations for the local structural health monitoring system of aircraft improve the fitting reconstruction effect for the wing structure and stabilize the compensation effect.

Monitoring of Indonesian volcanoes with the IS06 infrasound array

Detecting and notifying ongoing volcanic explosive eruptions is crucial in supporting the Volcanic Ash Advisory Centre (VAAC). However, local monitoring systems are missing at many active volcanoes, but long range infrasound monitoring might provide useful information if able to detect and notify volcanic explosive events. Indeed, many studies have already highlighted the utility and the potential of long-range infrasound monitoring for this aim, but still open questions remain concerning its actual efficiency and reliability. In this study we investigate the potential of the IS06 array (Cocos Island, Australia) of the International Monitoring System (IMS) of the Comprehensive Nuclear-Test-Ban Treaty Organization (CTBTO) to remotely detect volcanic explosive eruptions in the Indonesian Arc between 2012 and 2019, when 11 volcanoes, positioned at a distance between 1000 and 2000 km from the array, erupted with an energy spanning from mild explosions to VEI (Volcanic Explosivity Index) 4 eruptions. For each volcano, using infrasonic data recorded at a single array and accounting for realistic infrasound propagation conditions, we calculate a range corrected Infrasound Parameter (IP) and propose two additional empirical thresholds on signal strength and persistency. The IP is used eventually to define an alert whenever an established threshold is exceeded and the corresponding reliability estimated. Results show that the range corrected IP is highly reliable for events VEI = 3 or greater under favorable propagation conditions, but smaller scale short-lasting explosive eruptions still remain usually undetected. Unresolved ambiguity remains due to short spacing among volcanoes with respect to the array. For regional scale monitoring purposes, this can be solved only considering volcanic sectors rather than single volcanic edifices that, despite preventing unambiguous notification of a given volcano, might allow to increase the attention of the VAAC over a specific area.

IoT-Powered UPS Battery Monitoring: Ensuring High availability and reliability for Critical Systems

An Uninterrupted Power Supply (UPS) is a critical component in any high availability system. However, the effectiveness of a UPS depends largely on its battery backup, which must be continuously monitored to ensure that it is working properly. In the past, this monitoring has been done manually or through local monitoring systems, but advances in IoT technology now make it possible to remotely monitor the status of UPS batteries and receive real-time alerts if any issues arise. The proposed system will have several benefits over existing battery monitoring systems. First, it will be fully automated, reducing the need for manual monitoring and minimizing the risk of human error. Second, it will be accessible remotely, allowing system administrators to monitor the status of the battery backup system from anywhere in the world. Finally, the system will be scalable, allowing additional sensors to be added to the network as needed. Nevertheless, physically checking the UPS battery is highly challenging since it requires more money and time. Data center operators, at the centre of the digital economy, are under pressure from several directions. sustaining the highest level of availability at the most affordable level. A leading provider of battery management solutions.

ADS-B data usage for aircraft noise and air quality modelling and measurement during specific stages of LTO cycle

The paper is targeted at the analysis of the importance of Automatic Dependent Surveillance-Broadcast (ADS-B) data in the terms of overcoming gaps between aircraft noise and local air quality modelling results and their short or long-term measurements. Presented results based on noise and air pollution measurement campaign at Ukrainian airports describe general peculiarities of the pre-processing and usage of ADS-B data during specific stages of aircraft landing and taking-off (LTO) cycle in the airport. The outcomes could be used for more accurate noise and air pollution exposure assessment and the development of recommendations for noise and local air quality monitoring systems in airports under consideration.

SICK BUILDING SYNDROME: HOW IS IT AFFECTED BY AIRBORNE POLLEN, INDOOR AND OUTDOOR POLLUTANTS?

<h3>Introduction</h3> The Sick Building Syndrome (SBS) is defined as symptoms experienced by occupants of specific indoor environments. Other factors may influence this syndrome such as indoor and outdoor pollutants. The aim of the study was to determine the association of the clinical manifestations of the SBS with pollen, indoor and outdoor pollutants in the home environment. <h3>Methods</h3> It was an observational, transversal and descriptive study that was performed from November 2021 to April 2022. It included subjects >18 years old who completed an online survey regarding SBS (general symptoms, nasal, eye, oropharyngeal and skin symptoms) presented at home, housing information and personal history. Pollen Sense SensorÒ was used for airborne pollen data and the local pollution monitoring system for pollutant information. Ethics committee approval: AL21-00015. SPSS version 24 was used for statistical analysis. <h3>Results</h3> A total of 402 surveys were included; 91% of subjects reported having at least 1 symptom, fatigue (74.6%) was the most frequent. Humidity at home was associated to nasal, eye and cutaneous symptoms (p<0.001). Presence of cats was associated to nasal and eye symptoms (p=0.028). Smoking (p=0.045), allergy history (p<0.001) and living in an apartment (p=0.006) were related to nasal symptoms. Headache was associated with exposure to high levels of <i>Fraxinus</i> pollen (p=0.019). Nitrogen oxides (NOx) presented a p=0.05 with eye and nasal symptoms. PM10 were related to cutaneous symptoms and itchy scalp at levels of 67.5 µg/m3. <h3>Conclusion</h3> SBS was associated with airborne pollen, indoor and outdoor pollutants. Humidity represents a risk factor for the development of SBS symptoms.

Vehicle Make Detection Using the Transfer Learning Approach

Vehicle detection and classification is an important part of an intelligent transportation surveillance system. Although car detection is a trivial task for deep learning models, studies have shown that when vehicles are visible from different angles, more research is relevant for brand classification. Furthermore, each year, more than 30 new car models are released to the United States market alone, implying that the model needs to be updated with new classes, and the task becomes more complex over time. As a result, a transfer learning approach has been investigated that allows the retraining of a model with a small amount of data. This study proposes an efficient solution to develop an updatable local vehicle brand monitoring system. The proposed framework includes the dataset preparation, object detection, and a view-independent make classification model that has been tested using two efficient deep learning architectures, EfficientNetV2 and MobileNetV2. The model was trained on the dominant car brands in Lithuania and achieved 81.39 % accuracy in classifying 19 classes, using 400 to 500 images per class.