Balanced Data Research Articles

Sistem Otomatis Penyimpanan Data Pendeteksi Fase Pelanggan Tegangan Rendah

Inaccurate phase detection due to manual data recording often led to errors, impacting load balancing processes in electrical distribution. This research aimed to develop an automated phase detection system for low-voltage customers, utilizing a MicroSD-Card for data storage to reduce human error and enhance data reliability. The device used Power Line Carrier (PLC) communication technology integrated with customer identity (ID PEL) and employed Arduino Uno for phase data processing. The research method involved designing and testing phase detection and data storage functions across various distances to assess system accuracy. Findings indicated the system accurately detected customer phases and stored data efficiently, with minor delays only at longer distances. This automated solution effectively minimized manual errors in phase data entry. Future applications of this system could significantly improve load balancing accuracy and data management in electrical distribution networks

Denoising diffusion probabilistic model enhanced tool condition monitoring method under imbalanced conditions

Abstract In recent years, tool condition monitoring (TCM) based on deep learning has been widely considered and achieved remarkable success. However, these methods typically require relatively large training samples to produce significant results, which are both imbalanced and rather troublesome to obtain in the practical application of TCM. To address this issue, a novel TCM method combined with multiscale permutation entropy (MPE), denoising diffusion probabilistic model (DDPM) and a residual network (ResNet) is proposed under conditions of sample imbalance. First, the one-dimensional sensing signal data is converted to a grayscale recurrence plot (RP) by minimizing the MPE of the signals in each channel. Second, combine and splice these grayscale RPs from different channels in each sample into color RPs. After that, the generated RP images using DDPM are added to the imbalanced dataset to augment the data to achieve a balanced state of the dataset. Finally, the balanced mixed data set of real and fake samples is input into a ResNet for recognition and monitoring tool conditions. TCM experiments are conducted to verify the performance of the proposed method with imbalanced dataset, and the results of experimental investigation demonstrate that the accuracy of the proposed method improved by 2%–18.8% compared to that of the other four sample augmentation methods using ResNet18 when the imbalance rate is 1:200.

Assessing the non-linear impact of fiscal balance on current account balance in major SAARC economies: evidence from method of moments quantile regression

PurposeIn the backdrop of persistent internal and external imbalances, the nexus between fiscal imbalance and current account imbalance remains a subject of debate among economists, policymakers, research scholars and governmental organisations. Nevertheless, there is no definitive consensus, either theoretical or empirical, especially within the SAARC region. This evident lack of unequivocal solid agreement underscores the pressing necessity for further empirical inquiry into the twin deficits hypothesis. In this regard, the present study makes a novel attempt to re-examine the twin deficits hypothesis for major SAARC economies in a non-linear fashion using a balanced data set from 1985 to 2021.Design/methodology/approachIn our empirical analysis, we addressed several methodological challenges in examining the relationship between fiscal balance and current account balance. Initially, we tackled cross-section dependency, heterogeneous slope coefficients and non-stationarity issues. We employed the panel Fourier unit root test by Nazlioglu and Karul to detect smooth breaks and non-linearity. Long-run cointegration was assessed using novel third-generation cointegration tests introduced by Westerlund and Edgerton (2008) and Banerjee and Carrion-i-Silvestre (2017). The non-linear dynamics were examined using the method of moments quantile regression (MMQR). Finally, to investigate the causal relationship between fiscal deficit and current account deficit within a panel framework, we employed the novel JKS test.FindingsThe MMQR analysis reveals that the fiscal balance has a positive and significant impact on the current account balance across all quantiles except the lower quantiles (first to third). The magnitude of the coefficient for fiscal balance increases from lower to higher quantiles, suggesting that countries with lower fiscal deficits manage their current account balances more efficiently. Likewise, a positive and significant impact of the saving-investment balance on the current account balance is observed across all quantiles, with the coefficient decreasing as quantiles increase. This indicates that a wider saving-investment gap leads to a more pronounced deterioration in the current account balance. The exchange rate also significantly influences the relationship, highlighting a strong exchange rate channel in transmitting fiscal policy shocks to the current account balance. These findings are corroborated by robustness checks using fully modified ordinary least squares (FMOLS) and dynamic ordinary least squares (DOLS) estimators. The JKS causality test confirms the bi-directional causality between fiscal and current account balances, further validating the results.Practical implicationsOur study has profound policy implications, suggesting that the “size” of fiscal deficit significantly impacts external balances and broader macroeconomic goals in SAARC economies. Policymakers are urged to implement prudent fiscal policies, enhance revenue generation, and promote fiscal discipline to achieve economic stability and sustainability. Minimising unproductive consumer spending and improving tax collections are also recommended to manage external imbalances effectively. Our research offers valuable insights for policymakers and researchers striving to foster sustainable economic development in the SAARC region.Originality/valueMost macroeconomic variables do not always behave symmetrically and linearly. As a result, it is likely that these variables exhibit asymmetric and non-linear behaviour in response to cyclical and structural changes. Therefore, employing asymmetric and non-linear econometric approaches, rather than the usual symmetrical analysis, to understand the behaviour of the current account and fiscal balance in SAARC economies is rational. Existing empirical studies predominantly focus on the twin deficits hypothesis, neglecting the influence of the saving-investment balance on both fiscal and current account balances. Our research aims to fill this gap by integrating the saving-investment balance into the twin deficits model, thus providing a pioneering analysis that expands our understanding of the relationship between internal and external imbalances. The methodological novelty of our study lies in the fact that this is the first study, at least in the SAARC region, to investigate the non-linear dynamics and causality direction in the twin deficits hypothesis using the MMQR and the JKS causality test.

SGO: An innovative oversampling approach for imbalanced datasets using SVM and genetic algorithms

Imbalanced datasets present a challenging problem in machine learning and artificial intelligence. Since most models typically assume balanced data distributions, imbalanced positive and negative examples can lead to significant bias in prediction or classification tasks. Current over-sampling methods frequently encounter issues like overfitting and boundary bias. A novel imbalanced data augmentation technique called SVM-GA over-sampling (SGO) is proposed in this paper, which integrates Support Vector Machines (SVM) with Genetic Algorithms (GA). Our approach leverages SVM to identify the decision boundary and uses GA to generate new minority samples along this boundary, effectively addressing both over-fitting and boundary biases. It has been experimentally validated that SGO outperforms the traditional methods on most datasets, providing a novel and effective approach to address imbalanced data problems, with potential application prospects and generalization value.

PreMLS: The undersampling technique based on ClusterCentroids to predict multiple lysine sites.

The translated protein undergoes a specific modification process, which involves the formation of covalent bonds on lysine residues and the attachment of small chemical moieties. The protein's fundamental physicochemical properties undergo a significant alteration. The change significantly alters the proteins' 3D structure and activity, enabling them to modulate key physiological processes. The modulation encompasses inhibiting cancer cell growth, delaying ovarian aging, regulating metabolic diseases, and ameliorating depression. Consequently, the identification and comprehension of post-translational lysine modifications hold substantial value in the realms of biological research and drug development. Post-translational modifications (PTMs) at lysine (K) sites are among the most common protein modifications. However, research on K-PTMs has been largely centered on identifying individual modification types, with a relative scarcity of balanced data analysis techniques. In this study, a classification system is developed for the prediction of concurrent multiple modifications at a single lysine residue. Initially, a well-established multi-label position-specific triad amino acid propensity algorithm is utilized for feature encoding. Subsequently, PreMLS: a novel ClusterCentroids undersampling algorithm based on MiniBatchKmeans was introduced to eliminate redundant or similar major class samples, thereby mitigating the issue of class imbalance. A convolutional neural network architecture was specifically constructed for the analysis of biological sequences to predict multiple lysine modification sites. The model, evaluated through five-fold cross-validation and independent testing, was found to significantly outperform existing models such as iMul-kSite and predML-Site. The results presented here aid in prioritizing potential lysine modification sites, facilitating subsequent biological assays and advancing pharmaceutical research. To enhance accessibility, an open-access predictive script has been crafted for the multi-label predictive model developed in this study.

More ESG Practices, Higher Financial Performance? The U‐Shaped Pattern in China's Agricultural and Food Firms

ABSTRACTESG (environmental, social, and governance) practices, an internationally recognized concept of a firm's sustainability, can serve as a bridge to enhance effective communication between firms and various stakeholders. It is also a new tool for measuring firms' value. This study employs a balanced panel data set of 114 publicly traded agricultural and food firms in China from 2016 to 2022. It empirically investigates the relationship between ESG and financial performance based on shareholder primacy theory and stakeholder theory. Employing a two‐way fixed effects (FE) model, our findings reveal a U‐shaped nonlinear pattern in how ESG impacts financial performance. It differs from previous studies that found predominantly positive relationships: Specifically, the average ESG score for firms is 0.396, the median is 0.390, and the inflection point of the U‐shape occurs at 0.53. When firms' ESG investments are less than 0.53, the high initial ESG cost makes it difficult to transform ESG into financial improvement. However, once this threshold is surpassed, good ESG can convey an excellent reputation to the public and increase anti‐risk ability—which, in turn, significantly improves firms' financial performance and facilitates long‐term development. Also, our study demonstrates that firms' ownership and different positions in the supply chain differentially affect the relationship between ESG and financial performance. This paper also offers insights into promoting the sustainable development of Chinese agri‐food firms.

Agricultural trade liberalization, governance quality, and technical efficiency in the agricultural sector of Southeast Asia

International trade has been regarded as an essential factor in enhancing a country's productivity and efficiency. Nevertheless, developing countries squander money and resources as a result of their deficient institutional quality, impeding their ability to profit from specialization and trade. Therefore, this study intends to investigate the impact of agricultural trade liberalization and governance quality on technical efficiency in Southeast Asia's agricultural sector using balanced panel data spanning from 2002 to 2021. The research utilizes translog stochastic frontier analysis (SFA) with a single-stage maximum likelihood estimation (MLE) to simultaneously calculate the time-varying technical efficiency scores and explore the core factors influencing agricultural inefficiency. The findings reveal that the average output-oriented technical efficiency for ASEAN-8 countries was 94 %. This suggests that there is significant potential to enhance technical efficiency in agricultural production by up to 6 % by addressing the adverse impacts of technical inefficiency. The research findings further point out that Malaysia is the most technically efficient country, having a technical efficiency score of 99.82 %, followed by Vietnam (99.75 %), Thailand (99.70 %), Lao PDR (98.90 %), Myanmar (95.42 %), Indonesia (91.64 %), the Philippines (90.65 %), and Cambodia (76.11 %). The results of disaggregated agricultural trade liberalization demonstrate a significant reduction in agricultural inefficiency in Southeast Asia through agricultural exports and imports. The findings also emphasize that improvements in the rule of law positively contribute to agricultural efficiency, whereas enhancements in terms of voice and accountability and regulatory quality appear to reduce it. Based on these findings, the government should consider enlarging open and liberalized trade policies in order to facilitate the exchange of technology and knowledge within the agriculture sector. Additionally, the government should involve farmers, agricultural cooperatives, local communities, and other relevant stakeholders in the decision-making process to ensure that policies address the specific needs and constraints faced by the sector.

Enhanced ADHD classification through deep learning and dynamic resting state fMRI analysis.

Attention Deficit Hyperactivity Disorder (ADHD) is characterized by deficits in attention, hyperactivity, and/or impulsivity. Resting-state functional connectivity analysis has emerged as a promising approach for ADHD classification using resting-state functional magnetic resonance imaging (rs-fMRI), although with limited accuracy. Recent studies have highlighted dynamic changes in functional connectivity patterns among ADHD children. In this study, we introduce Skip-Vote-Net, a novel deep learning-based network designed for classifying ADHD from typically developing children (TDC) by leveraging dynamic connectivity analysis on rs-fMRI data collected from 222 participants included in the NYU dataset within the ADHD-200 database. Initially, for each subject, functional connectivity matrices were constructed from overlapping segments using Pearson's correlation between mean time series of 116 regions of interest defined by the Automated Anatomical Labeling (AAL) 116 atlas. Skip-Vote-Net was then developed, employing a majority voting mechanism to classify ADHD/TDC children, as well as distinguishing between the two main subtypes: the inattentive subtype (ADHDI) and the predominantly combined subtype (ADHDC). The proposed method was evaluated across four classification scenarios: (1) two-class classification of ADHD from TD children using balanced data, (2) two-class classification between ADHD and TD children using unbalanced data, (3) two-class classification between ADHDI and ADHDC, and (4) three-class classification among ADHDI, ADHDC, and TD children. Using Skip-Vote-Net, we achieved mean classification accuracies of 97% ± 1.87 and 97.7% ± 2.2 for the balanced and unbalanced classification cases, respectively. Furthermore, the mean classification accuracy for discriminating between ADHDI and ADHDC reached 99.4% ± 1.21. Finally, the proposed method demonstrated an average accuracy of 98.86% ± 1.03 in classifying ADHDI, ADHDC, and TD children collectively. Our findings highlight the superior performance of Skip-Vote-Net over existing methods in the classification of ADHD, showcasing its potential as an effective diagnostic tool for identifying ADHD subtypes and distinguishing ADHD from typically developing children.

Demand for milk and milk products in the rural household of Bangladesh: A panel data analysis

Milk is considered an essential source of protein for people of all ages. However, Bangladeshi people, particularly those living in rural areas, tend to consume less milk and milk products than necessary. Therefore, this study aims to investigate the demand for milk and milk products among rural consumers and the factors affecting their consumption habits. The study utilizes balanced panel data from three waves of the Bangladesh Integrated Household Survey: 2011–12, 2015, and 2018–19, collected by the International Food Policy Research Institute. Both the Almost Ideal Demand System (AIDS) and Fixed Effects Model were employed. The expenditure elasticity for liquid milk, powdered milk, and condensed milk was found to be 1.013, 1.856, and 1.060, respectively, indicating that these products are considered luxury goods in rural Bangladesh. Additionally, powdered milk is more price-sensitive than liquid or condensed milk in these areas. Milk and milk products exhibit a substitutable relationship based on the Slutsky and Cournot cross-price elasticities matrix. Consumption of liquid milk is significantly influenced, either positively or negatively, by several factors, including age, education, family size, ownership of dairy animals, income, expense of food, and year. Furthermore, while the consumption of powdered milk is increasing over time, factors such as family size and livestock ownership negatively impact its consumption. Similarly, the consumption of condensed milk is negatively affected by education and ownership of dairy animals. Based on our study results, we recommend increasing household income through on and off-farm job creation, promoting educational campaigns on the benefits of milk, and supporting livestock ownership to reduce reliance on processed milk products.

Theoretical framework for the difference of two negative binomial distributions and its application in comparative analysis of sequencing data.

High-throughput sequencing (HTS) technologies have been instrumental in investigating biological questions at the bulk and single-cell levels. Comparative analysis of two HTS data sets often relies on testing the statistical significance for the difference of two negative binomial distributions (DOTNB). Although negative binomial distributions are well studied, the theoretical results for DOTNB remain largely unexplored. Here, we derive basic analytical results for DOTNB and examine its asymptotic properties. As a state-of-the-art application of DOTNB, we introduce DEGage, a computational method for detecting differentially expressed genes (DEGs) in scRNA-seq data. DEGage calculates the mean of the sample-wise differences of gene expression levels as the test statistic and determines significant differential expression by computing the P-value with DOTNB. Extensive validation using simulated and real scRNA-seq data sets demonstrates that DEGage outperforms five popular DEG analysis tools: DEGseq2, DEsingle, edgeR, Monocle3, and scDD. DEGage is robust against high dropout levels and exhibits superior sensitivity when applied to balanced and imbalanced data sets, even with small sample sizes. We utilize DEGage to analyze prostate cancer scRNA-seq data sets and identify marker genes for 17 cell types. Furthermore, we apply DEGage to scRNA-seq data sets of mouse neurons with and without fear memory and reveal eight potential memory-related genes overlooked in previous analyses. The theoretical results and supporting software for DOTNB can be widely applied to comparative analyses of dispersed count data in HTS and broad research questions.

Sustainability Implications of Commodity Price Shocks and Commodity Dependence in Selected Sub-Saharan Countries

Sub-Saharan economies often rely heavily on a narrow range of commodities, making them particularly vulnerable to price fluctuations in global markets. This volatility predisposes these countries to economic instability, threatening short-term growth and long-term development goals. As a result, this study examines the sustainability implications of commodity price volatility and commodity dependence for 31 Sub-Saharan African countries from 2000 to 2023. Eleven agricultural commodity-dependent countries, six energy commodity-dependent countries, and fourteen mineral and metal ore-dependent countries were chosen. This study uses balanced annual panel data from World Development Indicators, World Bank Commodity Price Data, and Federal Reserve Bank Data. The data were analyzed using the VECM, and this study’s findings were threefold and unanimous for all three categories of commodities (agricultural, energy and mineral, and metal ore). First, commodity dependence is positively related to economic growth, suggesting that higher commodity prices benefit the economy in the long run. Second, commodity price volatility is negatively related to economic growth, indicating adverse impacts on economic stability in the long run. Third, commodity dependence is positively related to commodity price volatility in the long run. By analyzing the interconnectedness of these factors, this study underscores the need for diversified economic policies and sustainable practices to reduce vulnerability and promote sustainable development in the region. The findings highlight the critical role of strategic resource management and policy interventions in achieving economic stability and ensuring the well-being of future generations.

Balancing customer and employee orientations: impact on financial distress and firm value

PurposeThis paper investigates the effect of balanced orientation (BO) toward customers and employees on financial distress and firm valuation. Rooted in stakeholder theory and the attention-based theory of firms, the study aims to understand how a balanced synthesis of employee orientation (EO) and customer orientation (CO) influences the long-term market performance and survivability of firms, particularly in the context of emerging markets.Design/methodology/approachA panel dataset of the top 500 firms listed on the National Stock Exchange of India was analyzed using fixed-effect panel models with robust estimators. The Heckman procedure was employed to address selection bias. Financial data were sourced from the CMIE Prowess database and balanced orientation data were extracted from the annual letters to shareholders.FindingsThe study finds that a balanced approach to EO and CO significantly lowers bankruptcy risk and increases firm valuation. Contrary to the traditional dichotomy of EO and CO, BO emerges as a key driver in reducing financial distress and enhancing long-term market performance. Firms embracing multiple strategic orientations outperform those solely focused on customer orientation.Practical implicationsFor emerging market firms facing resource constraints, developing BO is challenging but crucial. This study suggests adopting a sequential or alternating approach to developing EO and CO, which can alleviate bankruptcy risk and improve market valuation even in competitive environments.Originality/valueThis paper contributes to the existing literature by empirically demonstrating the significance of BO in emerging markets. It offers a novel perspective on strategic management, highlighting the importance of balancing customer and employee needs, especially in resource-constrained environments.

Comparative Analysis of Cross-Validation Techniques: LOOCV, K-folds Cross-Validation, and Repeated K-folds Cross-Validation in Machine Learning Models

Effective model evaluation is crucial for robust machine learning, and cross-validation techniques play a significant role. This study compares Repeated k-folds Cross Validation, k-folds Cross Validation, and Leave-One-Out Cross Validation (LOOCV) on imbalanced and balanced datasets across four models: Support Vector Machine (SVM), K-Nearest Neighbors (K-NN), Random Forest (RF), and Bagging, both with and without parameter tuning. On imbalanced data without parameter tuning, Repeated k-folds cross-validation demonstrated strong performance for SVM with a sensitivity of 0.541 and balanced accuracy of 0.764. K-folds Cross Validation showed a higher sensitivity of 0.784 for RF and a balanced accuracy of 0.884. In contrast, LOOCV achieved notable sensitivity for RF and Bagging at 0.787 and 0.784, respectively, but at the cost of lower precision and higher variance, as detailed in Table 1. When parameter tuning was applied to balanced data, the performance metrics improved. Sensitivity for SVM reached 0.893 with LOOCV and balanced accuracy for Bagging increased to 0.895. Stratified k-folds provided enhanced precision and F1-Score for SVM and RF. Notably, processing times varied significantly, with k-folds being the most efficient with SVM taking 21.480 seconds and Repeated k-folds showing higher computational demands where RF took approximately 1986.570 seconds in model processing, as shown in Table 4. This analysis underscores that while k-folds and repeated k-folds are generally efficient, LOOCV and balanced approaches offer enhanced accuracy for specific models but require greater computational resources. The choice of cross-validation technique should thus be tailored to the dataset characteristics and computational constraints to ensure optimal model evaluation.

Can the digital economy contribute to rural revitalization? A case of from China?

This study establishes a multi-dimensional evaluation index system for measuring digital economy and rural revitalization. It explores the impact of digital economy on China's rural revitalization and its mechanism using dynamic balanced panel data of 30 provinces and cities in China from 2012 to 2020 and adopting two-way fixed effect and mediated effect models. The results reveal that digital economy promotes rural revitalization in China; however, differences exist in its impact on industrial prosperity, ecological livability, civilized rural customs, effective governance, and affluent living under rural revitalization. Heterogeneity analysis shows that the impact of digital economy on rural revitalization is more pronounced in eastern China, with high levels of new urbanization and areas for big-data experimentation. In addition, this thesis verifies that technological innovation and human capital are two important transmission paths through which digital economy affects rural revitalization in China. The conclusions provide theoretical guidance and practical support for China and other developing countries to vigorously develop their digital economies and comprehensively revitalize the countryside.

Data augmentation using SMOTE technique: Application for prediction of burst pressure of hydrocarbons pipeline using supervised machine learning models

Accurate burst pressure prediction is critical for ensuring oil and gas pipeline safety, guiding maintenance decisions, and lowering costs and risks. Traditional methods have limitations, including high experimental costs, conservative empirical models, and computationally expensive numerical algorithms. Machine learning (ML) models have supplanted traditional methods in recent years. However, small and imbalanced datasets are the big challenge to build a ML model that can generate more accurate results. Moreover, the lack of generalization in ML models trained on a dataset of pipelines with specific material grids prevents them from producing superior results on other pipeline types. First, FEA was used to make a dataset. Then, a new way to improve machine learning (ML) model generalization for burst pressure prediction is suggested: combine publicly available datasets of different pipeline specifications. In this combined dataset, some pipelines have a higher number of data samples, and some have fewer, which causes a class imbalance issue. The Synthetic Minority Oversampling Technique (SMOTE) technique was applied to address the issue of class imbalance. The performance of various ML models, Extra Trees (ET), Extreme Gradient Boosting (XGBR), Random Forest (RF), Light Gradient Boosting Machine (LGBM), and Decision Tree (DT), was evaluated to validate the model's prediction and generalization on pipelines of various material grids. Results show that all the selected ML models produced high R-squared, i.e., >0.95, on balanced data compared to the imbalance dataset. These results show that SMOTE-based augmentation is a beneficial way to fix dataset imbalance and make ML models better at predicting burst pressure in oil and gas pipelines.

Privacy-Enhancing Technologies (PETs) and Application Security

Abstract: This article explores the critical component in safeguarding personal information in the digital age. This comprehensive exploration delves into the definition, scope, and key characteristics of PETs, examining their crucial role in modern data protection. The article discusses fundamental PET categories, including data encryption and anonymization/pseudonymization techniques, and their implementation in application security. It highlights the importance of Privacy Impact Assessments, Privacy by Design principles, and strong access controls in effectively integrating PETs into security strategies. By addressing the challenges of balancing data utility with privacy protection, PETs offer organizations a pathway to compliance with stringent data protection regulations while building trust with users and gaining a competitive edge in an increasingly privacy-conscious market.

Efficient SpMM Accelerator for Deep Learning: Sparkle and Its Automated Generator

Deep learning (DL) technology has made breakthroughs in a wide range of intelligent tasks, such as vision, language, recommendation systems, and so on. Sparse matrix multiplication (SpMM) is the key computation kernel of most sparse models. Conventional computing platforms, such as CPUs, GPUs, and AI chips with regular processing units, are unable to effectively support sparse computation due to their fixed structure and instruction sets. This work extends Sparkle, an accelerator architecture, which is developed specifically for processing SpMM in DL. During the balanced data loading process, some modifications are implemented to enhance the flexibility of the Sparkle architecture. Additionally, a Sparkle generator is proposed to accommodate diverse resource constraints and facilitate adaptable deployment. Leveraging Sparkle’s structural parameters and template-based design methods, the generator enables automatic Sparkle circuit generation under varying parameters. An instantiated Sparkle accelerator is implemented on the Xilinx xqvu11p FPGA platform with a specific configuration. Compared to the state-of-the-art SpMM accelerator SIGMA, the Sparkle accelerator instance improves the sparse computing efficiency by about 10 to 20 \(\%\) . Furthermore, the Sparkle instance achieved 7.76 \(\times\) higher performance over the Nvidia Orin NX GPU. More instances of accelerators with different parameters were evaluated, demonstrating that the Sparkle architecture can effectively accelerate SpMM.

The Effect of Physiotherapy on Strength, Mobility and Balance in Older Adults Attending an Integrated Care Programme for Older Persons

Abstract Background Physiotherapy has a significant impact on strength, mobility and balance in older adults but does the presence of frailty negate this? This study aimed to determine the benefit of a six-week physiotherapy intervention as part of an Integrated Care Programme for Older Persons (ICPOP) admission in frail older adults. Methods This was a retrospective observational study of frail older adults attending physiotherapy in ICPOP between 2022 and 2024. All patients had a Clinical Frailty Score of 4-6. Each patient referred to physiotherapy had strength assessments including Five Times Sit to Stand (5TSTS) & Grip Strength Test, mobility assessment including Timed Up and Go (TUG) and balance assessment using the Mini BESTest. Patients with pre- and post-admission outcome measures were included in the study. Patients were offered individualised interventions of strength, mobility, and balance rehabilitation once per week for six weeks. Data was collected from a hospital clinical system using Microsoft Excel. Results 82 patients were included in the data for 5TSTS with an average of 22.3 seconds pre physiotherapy intervention and 18.5 seconds post. 163 patients were included in the Grip Strength Test. Initial mean left/right grip strength was 17.0/18.9kg while final left/right grip strength was 18.2/20.2kg. 173 patients were included in TUG testing with an average of 23.1 seconds pre-physiotherapy and 16.9 seconds post. 41 patients were included in the balance data with mean score of 15.7 pre-physiotherapy intervention and 20.0 post. Conclusion Lower limb strength, mobility and balance had on average minimally clinical important differences (MCID) post physiotherapy intervention despite the presence of frailty. The MCID was not achieved for grip strength potentially reinforcing the appropriateness of grip strength as part of the frailty phenotype.

Comparative Analysis of K-Means and Divisive Clustering Techniques on Balanced Mental Health Data

Effective Clustering of mental health data can provide significant insights into patterns and relationships that are critical for understanding mental health conditions. This study investigated various clustering techniques applied to balanced mental health data to avoid biases associated with an imbalanced data. Clustering of the balanced mental health data was done with respect to the area of Residence feature. Firstly, Random undersampling and SMOTE techniques were incorporated to the imbalanced data set as balancing techniques so as to improve model performance. Random Undersampling Technique turned out to be the most ideal balancing technique with its accuracy, recall, precision and F-score values as 1. After balancing the data, two clustering techniques were applied to the Random Undersampled balanced data. The two techniques were namely: K-means and Divisive techniques. In order to select which of the two clustering techniques is ideal, two test statistics namely Internal Validation and Stability Validation were applied. Results showed that K-means clustering technique indicated slightly lower Average Propotion of None-overlap, Average Distance between Means and Figure Of Merit values given as 0.12, 0.41 and 0.9972 as compared to Divisive clustering technique which were 0.14, 0.42 and 0.9999. The conclusion was that K-means clustering has a better performance. This study's findings will help guide future researchers dealing with mental health data analysis on ways to improve model performance for better and more reliable predictions.

An optimized multi-layer ensemble model for airborne networks intrusion detection

In view of the characteristics of airborne networks, such as the traffic data of 1553B data bus and public networks, numerous redundant and irrelevant data, and fewer but more types of attack behaviors, a highly representative balanced data subset is generated by combining K-means with synthetic minority oversampling technique (SMOTE). A feature selection (FS) method of fast correlation-based filter combined with information gain (IG-FCBF) is proposed to filter the key characteristics with 90 % cumulative importance. Aiming at the problem that it is not easy for a single classifier to accurately classify various types of attacks, as well as the difficulty in obtaining the best prediction results by adjusting default and manual parameters, a multi-layer ensemble model based on Bayesian optimization tree-structured Parzen estimator (BO-TPE) is proposed for airborne networks intrusion detection, combining the advantages of supervised learning, stacking ensemble method and hyperparameter optimization (HPO). The experimental results show the superiority and effectiveness of the model, as well as its universality in Integrated Avionics Systems (IAS) and onboard public networks, which provides a new approach for airborne networks intrusion identification and protection.