Atomic force microscopy works by mounting a probing tip on the free end of a micro mechanical cantilever and then scanning an item with that tip. Cantilever deflection occurs during horizontal scanning of the sample. Several ways exist for sensing the cantilever’s deflection. For example, this approach is commonly employed in optical beam deflection due to its simplicity. It compares the observed deflection to the set point deflection while scanning the sample stage. The next step is to reduce the error signal, which is the set point deflection minus the detected deflection, by advancing the sample stage in the Z-direction. This closed-loop feedback mechanism may sustain the cantilever deflection and, by extension, the force exerted by the contact between the tip and the sample, up to a certain point value. This causes the sample stage to move in three dimensions, which roughly follows the contours of the sample. As a result, the topographic picture is often generated from the Z-direction electrical impulses that drive the sample stage scanner. To create the AFM topographic picture, the authors in this study employed a weight function close to 3 to combine the height image, which is used to drive the Z-scanner, with the deflection image. By means of trial and error, the value of has been ascertained experimentally. A more accurate topographic picture is produced by this technique.
Cardiac tumors present significant challenges in terms of early diagnosis and treatment planning due to their low incidence and complex anatomical location. Precise segmentation of CT scan images plays an essential role in enhancing the efficacy of diagnosis and clinical decision support. This paper introduces a deep learning-oriented automatic segmentation pipeline for identifying and outlining cardiac tumors with high accuracy. The proposed pipeline starts with the preprocessing of the CT scans, such as intensity normalization, denoising, resampling, and cropping, to make the images uniform and receptive to better visualize the tumors. A CNN encoder–decoder architecture motivated from U-Net is adopted to extract multiscale spatial and contextual cues for robust and dense tumor segmentation, and skip connections maintain structural cues during the process of reconstruction. To achieve optimal learning and compensate for class imbalance, a hybrid loss function integrating Binary Cross-Entropy, Soft Dice Loss, and Focal Tversky Loss is utilized. Furthermore, the traditional machine learning classifiers Naïve Bayes and K-Nearest Neighbors are used in addition to the outputs of CNN for complementary classification and generalizability improvement. The pipeline was trained and tested on a CT-based image dataset for 70:10:20 partitioning, and experimental results revealed robust performance, obtaining an accuracy of 97.8%, precision of 95.71%, recall of 93.62%, F1-score of 94.63%, Dice coefficient of 94.52%, IoU of 91.83%, and AUC of 96.45%. Overlay of segmentation revealed precise delimitation of tumoral outlines, and ROC curve analysis further confirmed model robustness, too. These results proved the efficacy of the proposed CNN encoder–decoder pipeline with hybrid loss optimization and complementary classifiers, qualifying it as a reliable and clinically feasible method for automatic segmentation of cardiac tumors in CT scans.
Poverty remains a pressing socio-economic issue in Anambra State, Nigeria, necessitating data-driven strategies for accurate assessment and policy action. This study applies machine learning techniques to model poverty status using socio-economic variables, including age, satisfaction level, perception of poverty trends over the past eight years, choice of health facility, source of fuel, and educational attainment. The analysis utilizes secondary data from the Anambra Bureau of Statistics Poverty Index Survey 2021, comprising approximately 2,500 households across 188 communities. Three classification algorithms: Random Forest (RF), Support Vector Machines (SVM), and Gradient Boosting (GB) were employed to estimate poverty status and compared using key performance metrics: accuracy, precision, recall, F1-score, Area Under the Curve (AUC), Mean Squared Error (MSE), and R-squared. The study’s objectives were to: (1) identify key socio-economic determinants of poverty, (2) apply RF, SVM, and GB models to classify poverty status, and (3) determine the most effective classifier based on predictive performance. Empirical results showed that the Gradient Boosting model had the highest classification accuracy (92.3%), followed by RF (89.7%) and SVM (85.4%). F1-scores ranged from 0.81 to 0.91, with GB outperforming others due to its superior handling of complex, non-linear data patterns. Feature importance analysis revealed that perception of poverty rate and choice of health facility were the most influential predictors, followed by educational qualification and fuel source. These findings demonstrate the value of machine learning in socio-economic research and advocate for its integration into real-time poverty monitoring and targeted policy interventions in Anambra State.
Fibre optic sensors (FOS) have emerged as a robust alternative to conventional vibration sensors due to their immunity to electromagnetic interference (EMI), high sensitivity, and suitability for harsh environments. This study presents a comparative analysis of single-mode (SM) and multi-mode (MM) fibre optic cables for vibration sensing, focusing on their performance in controlled and uncontrolled vehicular traffic scenarios. Distributed fibre optic sensing (DFOS) technology, specifically Phase Optical Time Domain Reflectometry (Φ-OTDR), was employed to measure vibrations. Results indicate that multi-mode fibres exhibit higher sensitivity to localized vibrations due to their larger core diameter and multiple propagation paths, while single-mode fibres offer superior performance over long distances with minimal attenuation. The study also highlights the advantages of multi-mode fibres in short-range applications, such as vehicular traffic monitoring, where high spatial resolution and multiplexing capabilities are critical. These findings provide valuable insights for selecting fibre optic cables based on specific vibration sensing requirements
Brand withholding at retail stores, in which one brand is restricted from consumer availability or purchase, is employed most often to create exclusivity, maintain supplier agreements, or stimulate private-label options. Although the tactic can have an impact on brand image and consumer behavior, it can also lead to accidental revenue loss. This study examines the financial effect of brand locking through a test and control group analysis to provide empirical evidence for their store profitability results. The results show there is a quantifiable decline in total sales performance for locked brand stores, varying according to product category, substitute existence, and customer loyalty. The results mirror brand locking to cause revenue losses of 5-10% in terms of smaller transaction sizes, smaller basket sizes, and customers switching to substitution stores. Various factors including strategic pricing, special promotions, and the availability of substitution products were found to reduce some of these losses. The paper establishes evidence-based strategy recommendations to enhance brand-locking strategy optimization with a view to avoiding economic loss while still securing competitive gain. Retailers ought to utilize customer analytics, A/B testing frameworks, and forecast models to analyze the long-run sustainability of brand limitations. Follow-up research may also explore brand loyalty dynamics, customer churn dynamics, and category-level effects further to optimize revenue-maximizing actions. Results from this study increase the nuance of describing how brand access impacts consumer behavior and store profitability, allowing retailers to make knowledgeable strategic choices amid chaotic markets.
