Threshold Method Research Articles

Urban Land Use Classification Model Fusing Multimodal Deep Features

Urban land use classification plays a significant role in urban studies and provides key guidance for urban development. However, existing methods predominantly rely on either raster structure deep features through convolutional neural networks (CNNs) or topological structure deep features through graph neural networks (GNNs), making it challenging to comprehensively capture the rich semantic information in remote sensing images. To address this limitation, we propose a novel urban land use classification model by integrating both raster and topological structure deep features to enhance the accuracy and robustness of the classification model. First, we divide the urban area into block units based on road network data and further subdivide these units using the fractal network evolution algorithm (FNEA). Next, the K-nearest neighbors (KNN) graph construction method with adaptive fusion coefficients is employed to generate both global and local graphs of the blocks and sub-units. The spectral features and subgraph features are then constructed, and a graph convolutional network (GCN) is utilized to extract the node relational features from both the global and local graphs, forming the topological structure deep features while aggregating local features into global ones. Subsequently, VGG-16 (Visual Geometry Group 16) is used to extract the image convolutional features of the block units, obtaining the raster structure deep features. Finally, the transformer is used to fuse both topological and raster structure deep features, and land use classification is completed using the softmax function. Experiments were conducted using high-resolution Google images and Open Street Map (OSM) data, with study areas on the third ring road of Shenyang and the fourth ring road of Chengdu. The results demonstrate that the proposed method improves the overall accuracy and Kappa coefficient by 9.32% and 0.17, respectively, compared to single deep learning models. Incorporating subgraph structure features further enhances the overall accuracy and Kappa by 1.13% and 0.1. The adaptive KNN graph construction method achieves accuracy comparable to that of the empirical threshold method. This study enables accurate large-scale urban land use classification with reduced manual intervention, improving urban planning efficiency. The experimental results verify the effectiveness of the proposed method, particularly in terms of classification accuracy and feature representation completeness.

Multi-Level Digital-Twin Models of Pulmonary Mechanics: Correlation Analysis of 3D CT Lung Volume and 2D Chest Motion

Abstract Creating multi-level digital-twin models for mechanical ventilation requires a detailed estimation of regional lung volume. An accurate generic map between 2D chest surface motion and 3D regional lung volume could provide improved regionalisation and clinically acceptable estimates localising lung damage. This work investigates the relationship between CT lung volumes and the forced vital capacity (FVC) a surrogate of tidal volume proven linked to 2D chest motion. 

In particular, a convolutional neural network (CNN) with U-Net architecture is employed to build a lung segmentation model using a benchmark CT scan dataset. An automated thresholding method is proposed for image morphology analysis to improve model performance. Finally, the trained model is applied to an independent CT dataset with FVC measurements for correlation analysis of CT lung volume projection to lung recruitment capacity. 

Model training results show a clear improvement of lung segmentation performance with the proposed automated thresholding method compared to a typically suggested fixed value selection, achieving accuracy greater than 95% for both training and independent validation sets. The correlation analysis for 160 patients shows a good correlation of R squared value of 0.73 between the proposed 2D volume projection and the FVC value, which indicates a larger and denser projection of lung volume relative to a greater FVC value and lung recruitable capacity. 

The overall results thus validate the potential of using non-contact, non-invasive 2D measures to enable regionalising lung mechanics models to equivalent 3D models with a generic map based on the good correlation. The clinical impact of improved lung mechanics digital twins due to regionalising the lung mechanics and volume to specific lung regions could be very high in managing mechanical ventilation and diagnosing or locating lung injury or dysfunction based on regular monitoring instead of intermittent and invasive lung imaging modalities.

CT-perfusion quantitation of cardiac infarct size - a novel technique

Abstract Introduction Cardiac infarct size is associated with cardiac prognosis after AMI. Cardiac CT is able to delineate both coronary anatomy and myocardial pefusion. Thus far, CT identification of infarction has been qualitative. We describe a novel technique for quantitation of myocardial infarct size in CT-perfusion imaging. Methods Patient Population comprised 51 patients that were previously clinically diagnosed with myocardial infarction on the basis of clinical presentation, ECG findings and elevated cardiac enzymes. CTP Imaging All patients had undergone dynamic rest, vasodilator-stress, rest, delayed enhancement CT perfusion imaging performed on a dual-source, third generation scanner (FORCE, Siemens Healthcare). Image Analysis 2 trained investigators independently quantified the infarct volume in 51 patient studies using Siemens SmartSimulator software. Mean ± SD HU were taken from a 1cm² circular ROI of normal myocardium used in a thresholding method. The epicardium and endocardium of infarcted areas were manually contoured from apex to base. Volumetric measurements were obtained of the infarct and total myocardium. Interpolation of contours for segmentation objects was performed. Subtraction of left ventricle cavity from total left ventricle allowed volumetric measurements of total left ventricular myocardium. ROIs of the infarct were estimated using SDs above mean HU of normal myocardium (0.5, 1, 1.5 and 2 SDs) in delayed imaging. Selection of optimal threshold HU was based on visual assessment that best mapped the hyperenhanced infarct area. This allowed volumetric asessment of infarct and total myocardium. Inter-investigator variability was evaluated with Bland-Altman and Intra-Class Correlation Coefficient (ICC). Results Patient characteristics are follow: Age 60.20±11.35 years, 41(89%)male, BMI 25.41±4.17kg/m², Hypertension 23(50%), diabetes 10(22%), hyperlipidemia 40(87%), smoking 7(15%), family history of premature CAD 4(8.7%), previous PCI 45(97.8%). In 51 patients, 23(41%), 24 (46%) & 5(10%) of the infarctions were quantitated as being medium-sized (10%-20%), large (20% -30%) and very large (>30%). Thirty-seven (70%), 6 (11%) & 10(19%) involved the LAD, LCx and RCA territories respectively. 49 (94%) of infarctions were transmural. Identical thresholding was selected by both investigators for each SD above mean (mean 1.42; SD 0.46). 93% of the total cases were within a set threshold of 1 to 2 SDs above the mean HU for both. Interclass correlation coefficient was 0.95, CI range 0.90 – 0.97. Bland-Altman analysis did not demonstrate systemic variations or proportional bias from the plot. Conclusion The study suggests that a method of quantifying cardiac infarct size using a threshold technique and delayed hyperenhancement images with dynamic perfusion imaging is clinically feasible and consistent.Rest-Stress-Delayed Enhancement infarct

Testing a nutrient composition threshold model to classify brands for marketing restrictions.

Food marketing restrictions often apply nutrient profile models (NPM) to distinguish unhealthy products that should not be advertised, however brand-only marketing remains largely unaddressed. We sought to test a threshold method for classifying packaged food, beverage, or fast-food brands as (non)permitted for marketing, based on the nutrient profile of their product-lines. We retrieved nutrient information from the Nutritrack databases for all products sold by the top 51 packaged food, beverage and fast-food brands in New Zealand, selected by market share. All products under each brand were classified as permitted (or not) to be marketed to children, using the NPM for WHO Western Pacific. The 25%, 50%, 75% and 90% threshold of brands' products permitted to market were compared. The 50% and 75% thresholds were compared to the WHO CLICK method, which is based on assessment of the brand's leading product. The 90% threshold permitted 13% of the brands to be marketed to children. The 25% threshold permitted the marketing of 62% of brands. The 50% and 75% thresholds remained highly sensitive in identifying brands that should not be marketed to children. Comparison to the WHO CLICK method identified that a threshold method is more comprehensive and less arbitrary. A threshold model based on product-line nutrient profiling provides a robust and option for brand classification. The 50% and 75% thresholds may be the most politically preferred options for use in regulation, while remaining highly effective. Brand marketing (e.g. sponsorship) remains largely unaddressed in existing restrictions on unhealthy food and beverage marketing to children.An established Nutrient Profile Model can be applied to a brand's entire product line, allowing calculation of the proportion of products that would not be permitted to be advertised to children.Restricting brand marketing for food and beverage brands with less than 50% or 75% of their products classified as 'permitted to be marketed to children' is a robust and evidence-based method that can be applied in regulation, with potential to mitigate industry challenges.

Deciphering the complex interplay: Heterogeneous, threshold, and mediation effects of trade openness on CO2 emissions in Africa.

Despite having barely anything to do with the issue of CO2 emissions, Africa has been experiencing more severe climate change and its adverse effects than most other regions of the globe. However, the issue of CO2 emissions and its adverse effects has received relatively little attention in the African research arena. To this end, the present research assesses the effect of trade openness on the CO2 emissions utilizing panel data from 46 African countries spanning 2000 through 2022. To account for the possible heterogeneity and nonlinearity, the panel quantile regression and threshold methods were employed. Moreover, this study investigates the key mediating effects of the channel. The empirical findings show that greater trade openness is associated with significantly higher CO2 emission, additionally; it demonstrates that the influence is heterogeneous across different CO2 emission quantiles in African countries. Besides the result from the double threshold model reveals a complex, nonlinear relationship between trade openness and CO2 emissions in Africa. Moreover, the findings divulge that openness to trade indirectly reduces CO2 emissions through the substitution and technology channels whereas it indirectly increases carbon dioxide production via the economic track. Therefore, it is vital to promote the use of renewable energy, effectively leverage the knowledge spillover effects of trade to decrease energy intensity and formulate pertinent policies aimed at curbing carbon emissions and addressing the imminent threat of climate change in Africa. Besides, the nonlinear and heterogeneous effects of trade openness on CO2 emissions suggest that policies and interventions related to the impact of trade openness on CO2 emissions should consider the current level of carbon dioxide emissions.

Quantitative characterization, spatiotemporal evolution, and analysis of driving factors of daily dry-wet abrupt alternation: A case study of the Ganjiang River Basin

Study RegionThis study focuses on the Ganjiang River Basin, a major tributary of the Poyang Lake located in southern China. Study FocusWith the growing frequency of extreme weather events driven by climate change, there is increased attention on compound disasters such as Dry-Wet Abrupt Alternation (DWAA). This study aims to quantify and define DWAA in the Ganjiang River Basin by developing and applying a DWAA Index (DWAAI) using a percentile threshold method. The objective is to investigate the spatiotemporal characteristics and patterns of DWAA in the region. Precipitation data from 12 meteorological stations were analyzed to track these events from 1970 to 2019. New Hydrological Insights For the regionThe results of this study provide new insights into DWAA dynamics in the Ganjiang River Basin. Key findings include: (i) The DWAAI effectively captures the extremes of Dry-Wet Abrupt Alternations, especially at the 1st and 99th percentiles; (ii) The basin experienced 37–48 dry-to-wet events (DtWs) during the study period, with higher frequencies observed in the central-eastern, western, and northern mountainous areas, and lower frequencies in the southern regions; (iii) Wet-to-dry events (WtDs) were less common than DtWs and exhibited a distinct spatial and temporal shift from the southern mountains toward the central basin; (iv) Temperature was identified as the dominant factor influencing DWAAI changes, while large-scale atmospheric patterns such as AO, ENSO, PDO, and Sunspot activity showed insignificant correlations. These findings offer critical insights for improving water resource management and climate adaptation efforts in the region.

Comparative Analysis of Water Body Extraction Accuracy Based on Thresholding Method

Abstract. With the continuous development of remote sensing technology, various methods for land water body extraction based on satellite remote sensing have emerged. The thresholding method, as a commonly used image segmentation technique, possesses advantages such as high efficiency and wide applicability, making it widely employed in water body extraction research. In this thesis, utilizing SPOT4 imagery, we conducted experimental comparisons of water body extraction using the Iteration thresholding algorithm, Kittler-Illingworth (KI) thresholding algorithm, and Otsu thresholding algorithm. The experimental results demonstrate that all three thresholding methods exhibit good performance in water body extraction, with the Kittler-Illingworth (KI) thresholding algorithm achieving the highest relative accuracy.

Dynamic Coastal Mapping Using Sentinel-1 and Sentinel-2 Data Through Digital Earth Africa

Abstract. Coastal erosion poses a continuous threat to ecosystems, infrastructure, and property. To address these challenges and mitigate the effects of coastal changes, effective and current monitoring is essential. It is particularly important to monitor coastlines and coastal changes in Africa, where a significant portion of the population resides in coastal regions. While optical satellite imagery has been used for large-scale annual coastlines and change monitoring for Africa, its availability and quality are largely limited by the presence of cloud and cloud shadow. In comparison, using radar satellite observations such as Sentinel-1 data can provide consistent coastal mapping and change detection regardless of cloud presence. This paper outlines a fully automated supervised machine learning workflow using Sentinel-1 data and training samples extracted from Sentinel-2 data. It also explores the performance of the workflow for different coastal morphology types across the African coast. The workflow has proved to perform better and produced results that were visually more consistent with Sentinel-2 data compared to thresholding methods. While challenges exist to distinguish between land and water over smooth sandy beaches and rough near-shore water surfaces, our workflow provides an alternative method for coastal change mapping where optical satellites provide insufficient observations free from clouds. Python code of the proposed methodology has been made publicly available.

Unveiling the lifeblood of cities: Identifying urban ecological networks from the perspective of biodiversity conservation

Urban biodiversity faces threats from habitat loss, landscape fragmentation, and human disturbances. Ecological networks (ENs) can enhance habitat connectivity and bolster population resilience to disruptions. To safeguard the biodiversity of Nanjing's urban area, this study selected understory insectivorous birds as indicator species for biodiversity, employing a comprehensive approach integrating the maximum entropy (MaxEnt) model and the area threshold method to delineate ecological source areas. Key indicators directly linked to the species distribution were extracted based on the habitat suitability assessment results, and an ecological resistance surface was crafted using spatial principal component analysis. Subsequently, the circuit theory model was applied to pinpoint ecological corridors, pinch points, and barrier points. The findings unveiled the following: (1) The normalized difference vegetation index (NDVI), human activities (HA), and canopy height (CH) were critical indicators influencing biodiversity. The response curves of the NDVI and CH were positively correlated with the probability distribution of indicator species, while the response curve of the HA showed an overall negative correlation with the same distribution. (2) The spatial distribution characteristics of the ecological network revealed a ‘one axis, two cores, intersecting’ pattern. Ecological sources were supported by mountainous forests and riverside green spaces, symmetrically distributed on both sides of the Yangtze River. Ecological corridors were forming continuous tree belts along highways and riverways, predominantly concentrated on the eastern side of the Yangtze River. Ecological pinch points and barriers were primarily located at the intersections of fragmented green spaces and developed areas in the northeastern and southeastern regions of the study area. (3) This study finally identified 30 ecological source areas, 65 ecological corridors, 8 pinch points, and 8 barrier points. This study presents a construction paradigm for urban ENs from the vantage point of biodiversity conservation, including both regional specificity and universal applicability, providing vital theoretical underpinnings and pragmatic insights for urban sustainability.

Feasibility of Emergency Flood Traffic Road Damage Assessment by Integrating Remote Sensing Images and Social Media Information

In the context of global climate change, the frequency of sudden natural disasters is increasing. Assessing traffic road damage post-disaster is crucial for emergency decision-making and disaster management. Traditional ground observation methods for evaluating traffic road damage are limited by the timeliness and coverage of data updates. Relying solely on these methods does not adequately support rapid assessment and emergency management during extreme natural disasters. Social media, a major source of big data, can effectively address these limitations by providing more timely and comprehensive disaster information. Motivated by this, we utilized multi-source heterogeneous data to assess the damage to traffic roads under extreme conditions and established a new framework for evaluating traffic roads in cities prone to flood disasters caused by rainstorms. The approach involves several steps: First, the surface area affected by precipitation is extracted using a threshold method constrained by confidence intervals derived from microwave remote sensing images. Second, disaster information is collected from the Sina Weibo platform, where social media information is screened and cleaned. A quantification table for road traffic loss assessment was defined, and a social media disaster information classification model combining text convolutional neural networks and attention mechanisms (TextCNN-Attention disaster information classification) was proposed. Finally, traffic road information on social media is matched with basic geographic data, the classification of traffic road disaster risk levels is visualized, and the assessment of traffic road disaster levels is completed based on multi-source heterogeneous data. Using the “7.20” rainstorm event in Henan Province as an example, this research categorizes the disaster’s impact on traffic roads into five levels—particularly severe, severe, moderate, mild, and minimal—as derived from remote sensing image monitoring and social media information analysis. The evaluation framework for flood disaster traffic roads based on multi-source heterogeneous data provides important data support and methodological support for enhancing disaster management capabilities and systems.

An Improved Adaptive Grid-Based Progressive Triangulated Irregular Network Densification Algorithm for Filtering Airborne LiDAR Data

Ground filtering is crucial for airborne Light Detection and Ranging (LiDAR) data post-processing. The progressive triangulated irregular network densification (PTD) algorithm and its variants outperform others in accuracy, stability, and robustness, using grid-based seed point selection, TIN construction, and iterative rules for ground point identification. However, these methods still face limitations in removing low points and accurately preserving terrain details, primarily due to their sensitivity to grid size. To overcome this issue, a novel PTD filtering algorithm based on an adaptive grid (AGPTD) was proposed. The main contributions of the proposed method include an outlier removal method using a radius outlier removal algorithm and Kd-tree, a method for establishing an adaptive two-level grid based on point cloud density and terrain slope, and an adaptive selection method for angle and distance thresholds in the iterative densification processing. The performance of the AGPTD algorithm was assessed based on widely used benchmark datasets. Results show that the AGPTD algorithm outperforms the classical PTD algorithm in retaining ground feature points, especially in reducing Type I error and average total error significantly. In comparison with other advanced algorithms developed in recent years, the novel algorithm showed the lowest average Type I error, the minimal average total error, and the greatest average Kappa coefficient, which were 1.11%, 2.28%, and 90.86%, respectively. Additionally, the average accuracy, precision, and recall of AGPTD were 97.69%, 97.52%, and 98.98%, respectively.

Simple and efficient step detection algorithm for foot-mounted IMU

Abstract This paper presents a concise, efficient, and adaptive step detection algorithm based on foot-mounted inertial measurement unit sensors. The proposed method maps the temporal values of pedestrian motion and gait diversity into two variables: the distance between peaks and valleys, and the slope. Compared to traditional sliding window methods, this approach amplifies the differences between normal and abnormal steps, allowing it to adapt to various indoor activities such as fast walking, slow walking, running, jogging, standing still, and turning. By incorporating adaptive factors, it addresses the challenge of detecting steps while going up and down stairs. The proposed algorithm overcomes the limitations of traditional adaptive threshold methods that require different temporal and peak thresholds for various gait conditions. By utilizing the significant differences in distance and slope, it effectively resolves the issue of detecting steps during stationary periods. Unlike neural network-based gait classifiers, this algorithm does not need to account for multiple gait conditions, thereby simplifying the training process. Experimental results demonstrate that the algorithm achieves an average accuracy of over 99% under mixed indoor walking conditions and over 98% accuracy in long-term outdoor walking conditions.

Comprehensive Preview Decision Method for Direction and Speed of Intelligent Vehicle Based on Rules and Learning

Decision-making is a key part of autonomous driving systems. Human-like decision-making in complex scenarios is important for enhancing drivers’ trust in and acceptance of autonomous driving systems. In order to improve their human-like features and their adaptability to complex scenarios, this paper proposes a comprehensive preview decision method for direction and speed based on rules and learning. First, a decision-making structure including maneuvering ability judgment, motion trajectory prediction, safety judgment, legitimacy judgment, comprehensive performance evaluation, and parameters learning is presented. Second, a learning method for the longitudinal safety distance threshold based on a BP neural network is introduced. Third, inverse reinforcement learning (IRL) is used to learn the comprehensive performance evaluation weight coefficient for different driving styles. Finally, the DJI AD4CHE dataset is processed and used to train the parameters. Car-following and lane-changing scenarios are simulated to verify the effectiveness of decision-making. The simulation results show that the proposed method can reflect human-like decision-making in multiple scenarios.

Overtaking risk assessment based on extreme value theory and intelligent network information

In order to evaluate the overtaking risk level of intelligent connected vehicles when providing different connected information, and to make up for the neglect of driver factors in traditional risk assessment and the inadequate evaluation of complex traffic scenarios by a single traffic conflict indicator, this paper introduces the Block maxima (BM) and Peak over threshold (POT) methods to fit the extreme value distribution for two conflict scenarios involved in overtaking events (following vehicle conflict and frontal vehicle conflict), so as to evaluate the risk of following vehicle accidents and frontal collision accidents during overtaking. In each conflict scenario, a non-stationary extreme value model considering driver factors and a binary extreme value model considering different traffic conflict indicators are constructed, and the model is verified by the overtaking test data of intelligent connected vehicles in a two-way two-lane vehicle. Overtaking events were extracted from the original test data and conflict indicators were calculated: including the collision time GAP with the front vehicle at the beginning of the overtaking event, the collision time TTC_t1 with the oncoming vehicle, the deceleration DRAC, and the collision time TTC with the oncoming vehicle and the headway time THW with the front vehicle at the end of the overtaking event. The probability of the event with a negative time conflict indicator or DRAC greater than MADR was used to characterize the degree of collision risk. The results show that in the following vehicle conflict scenario, the binary extreme value model constructed with different conflict indicators has different error results, among which the binary extreme value model constructed with THW&DRAC has the most accurate evaluation result (standard error MAE = 0.00028); in the front vehicle conflict scenario, the binary extreme value model constructed with TTC&DRAC has the most accurate evaluation result ( MAE = 0.006 ). In different conflict scenarios, the non- stationary extreme value model considering the driver factor significantly improves the risk assessment accuracy compared with the model without considering the driver factor (small AIC and BIC values). In addition, different intelligent network information (real-time distance, overtaking advice, speed advice) brings different overtaking risks, and when the intelligent network information is speed advice, the vehicle's overtaking risk is the lowest. Therefore, the non- stationary extreme value model and binary extreme value model considering driver factors proposed in this paper can effectively evaluate driving risks through traffic conflict indicators. Secondly, the experimental data of intelligent networked vehicles show that the extreme value theory model proposed in this paper can accurately evaluate the overtaking risk level of intelligent networked vehicles when providing different network information.

Prevalence and assessment of sleep-disordered breathing in head and neck cancer patients: a systematic review.

Sleep-disordered breathing (SDB) is a very common and underdiagnosed condition in head and neck cancers (HNC) patients. If untreated, SDB can lead to negative health consequences. The identification of SDB in HNC patients is crucial to ensure appropriate treatment and to improve outcomes. The purpose of the study was to investigate the incidence of coexisting SDB in HNC patients and to evaluate methods of assessing SDB in the population. A systematic search of PubMed, Embase, CINAHL, Cochrane Database, the Web of Science, and Scopus was performed for studies related to SDB in HNC patients. In total, 1713 articles were identified. 19 articles were selected for qualitative synthesis. The studies involved 584 subjects. The prevalence of SDB ranged from 57 to 90% before cancer treatment and from 12 to 96% after. When using an apnea-hypopnea index (AHI) cut-off ≥ 5/h to diagnosis SDB, the prevalence of SDB was 57-90% before cancer treatment and 12-94% after treatment. Sleep studies using polysomnography are the most commonly used assessment tools, but thresholds for diagnosis have been inconsistent. There is a high prevalence of SDB in HNC patients. However, the diagnostic and thresholds methods used for detecting SDB vary widely. To determine the accurate prevalence of SDB, prospective, systematic studies of SDB in unselected cohorts of HNC participants are required.

Compound and cascading droughts and heatwaves decrease maize yields by nearly half in Sinaloa, Mexico

The impact of droughts and heatwaves on agriculture losses has been exacerbated by the occurrence of compound and cascading events. Here we present a study that evaluates the impact of these events both as singly and as compound and cascading on maize yield in Sinaloa Mexico from 1990 to 2022, using the WOFOST crop model. Drought and heatwave events were identified using the Standardized Precipitation Index and threshold method, respectively. Results show that yield reduction (25%) is found during extreme drought events, emphasizing the vulnerability of maize farming to unfavorable drought conditions. While heatwaves alone did not show a significant impact on maize yields, the compound and cascading droughts and heatwaves amplified the loss of maize yields by up to 44% compared to normal conditions. This study highlights the need for adaptive strategies in agriculture to sustain food security during extreme events, especially in the context of multi hazard framework.

Image segmentation on void regional formation in the flip-chip underfilling process by comparing YOLO and mask RCNN

Purpose This paper aims to identify a suitable convolutional neural network (CNN) model to analyse where void(s) are formed in asymmetrical flip-chips with large amounts of the ball-grid array (BGA) during underfilling. Design/methodology/approach A set of void(s)-filled through-scan acoustic microscope (TSAM) images of BGA underfill is collected, labelled and used to train two CNN models (You Look Only Once version 5 (YOLOv5) and Mask RCNN). Otsu's thresholding method is used to calculate the void percentage, and the model's performance in generating the results with its accuracy relative to real-scale images is evaluated. Findings All discoveries were authenticated concerning previous studies on CNN model development to encapsulate the shape of the void detected combined with calculating the percentage. The Mask RCNN is the most suitable model to perform the image segmentation analysis, and it closely matches the void presence in the TSAM image samples up to an accuracy of 94.25% of the entire void region. The model's overall accuracy of RCNN is 96.40%, and it can display the void percentage by 2.65 s on average, faster than the manual checking process by 96.50%. Practical implications The study enabled manufacturers to produce a feasible, automated means to improve their flip-chip underfilling production quality control. Leveraging an optimised CNN model enables an expedited manufacturing process that will reduce lead costs. Originality/value BGA void formation in a flip-chip underfilling process can be captured quantitatively with advanced image segmentation.

Comparative Analysis of Grass Pollen Dynamics in Urban and Rural Ireland: Identifying Key Sources and Optimizing Prediction Models

The Poaceae family, one of the most diverse and widespread angiosperms, is prevalent in various natural and urban environments and is a major cause of allergies, affecting over 20% of the population in Europe, specifically in Ireland. With extensive grasslands, Ireland supports numerous grass species, though pollen release varies due to the family’s complexity. The Hirst spore-trap is commonly used to sample airborne pollen, but the area of influence is debated and may differ by pollen type. This study compares grass pollen seasons between rural Carlow and urban Dublin, aiming to create forecast models for airborne pollen and identify key grass areas influencing the main pollen season (MPS). Two Hirst samplers were analyzed, using data up to 2020, and two threshold models (based on Swedish and Danish studies) were tested to find the best fit for Ireland. Airmass footprints were calculated using Hysplit and combined with grassland data to pinpoint major pollen sources. The results showed that Carlow had higher pollen concentrations but shorter seasons than Dublin. The Swedish threshold method was the most accurate for Ireland, with the Wicklow Mountains identified as a significant pollen source. These findings improve the understanding of pollen dynamics and support better public health and allergy management.

An integrated method for detecting lung cancer via CT scanning via optimization, deep learning, and IoT data transmission.

With its increasing global prevalence, lung cancer remains a critical health concern. Despite the advancement of screening programs, patient selection and risk stratification pose significant challenges. This study addresses the pressing need for early detection through a novel diagnostic approach that leverages innovative image processing techniques. The urgency of early lung cancer detection is emphasized by its alarming growth worldwide. While computed tomography (CT) surpasses traditional X-ray methods, a comprehensive diagnosis requires a combination of imaging techniques. This research introduces an advanced diagnostic tool implemented through image processing methodologies. The methodology commences with histogram equalization, a crucial step in artifact removal from CT images sourced from a medical database. Accurate lung CT image segmentation, which is vital for cancer diagnosis, follows. The Otsu thresholding method and optimization, employing Colliding Bodies Optimization (CBO), enhance the precision of the segmentation process. A local binary pattern (LBP) is deployed for feature extraction, enabling the identification of nodule sizes and precise locations. The resulting image underwent classification using the densely connected CNN (DenseNet) deep learning algorithm, which effectively distinguished between benign and malignant tumors. The proposed CBO+DenseNet CNN exhibits remarkable performance improvements over traditional methods. Notable enhancements in accuracy (98.17%), specificity (97.32%), precision (97.46%), and recall (97.89%) are observed, as evidenced by the results from the fractional randomized voting model (FRVM). These findings highlight the potential of the proposed model as an advanced diagnostic tool. Its improved metrics promise heightened accuracy in tumor classification and localization. The proposed model uniquely combines Colliding Bodies Optimization (CBO) with DenseNet CNN, enhancing segmentation and classification accuracy for lung cancer detection, setting it apart from traditional methods with superior performance metrics.

A Study on the Coarse-to-Fine Error Decomposition and Compensation Method of Free-Form Surface Machining

To improve the machining accuracy of free-form surface parts, a coarse-to-fine free-form surface machining error decomposition and compensation method is proposed in this paper. First, the machining error was coarsely decomposed using variational mode decomposition (VMD), and the correlation coefficients between the intrinsic mode function (IMF) and the machining error were obtained to filter out the IMF components that were larger than the thresholding value of the correlation coefficients, which was the coarse systematic error. Second, the coarse systematic errors were finely decomposed using empirical mode decomposition (EMD), which still filters out the IMF components that are larger than the thresholding value of the set correlation coefficient based on the correlation coefficient. Then, the wavelet thresholding method was utilized to finely decompose all the IMF components whose correlation coefficients in the first two decomposition processes were smaller than the threshold value of the correlation coefficient set. The decomposed residual systematic errors were reconstructed with the IMF components screened in the EMD fine decomposition, which gave the fine systematic error. Finally, the machining surface was reconstructed according to the fine systematic error, and its corresponding toolpath was generated to compensate for the machining error without moving the part. The simulation and analysis results of the design show that the method has a more ideal processing error decomposition ability and can decompose the systematic error contained in the processing error in a more complete way. The results of actual machining experiments show that, after using the method proposed in this paper to compensate for the machining error, the maximum absolute machining error decreased from 0.0580 mm to 0.0159 mm, which was a 72.5% reduction, and the average absolute machining error decreased from 0.0472 mm to 0.0059 mm, which was an 87.5% reduction. It was shown that the method was effective and feasible for free-form surface part machining error compensation.