Assessing the effects of sampling frequency on behavioural classification of accelerometer data

The detection and identification of Distributed Denial-of-Service (DDoS) attacks remains a challenge in cloud/edge/fog computing environments. It usually requires network middleboxes, such as deep packet inspectors (DPI), for detection task mostly. But clouds and fogs have native powerful telemetry systems that are not yet fully exploited for DDoS detection; and provide so much information that could aid attack identification tasks as well. Machine Learning (ML) algorithms can help one diving into the richness of cloud’s native data collection services, which have a multitude of metrics from both physical and virtual hosts. This paper evaluates the use of ML algorithms over datasets collected from a experimental testbed based on OpenStack. Controlled attack scenarios were used to investigate the ability of ML for tasks such as detecting and identifying SYN_Flood and GET_Flood DDoS attacks mixed, in different proportions, with legitimate clients. kNN and Random Forest ML algorithms were trained and tested, and for evaluation the metrics accuracy, recall, precision, and F1-score were used. Our experiments presented about 87% of accuracy in the detection of SYN_Flood and GET_Flood DDoS attacks, whereas Snort IDS mostly fails to detect the latter attack by processing the corresponding packet traces. Also, the detection of PING_Flood DDoS attack was tested without training as an initial evaluation towards the generalization of the proposal.

Machine learning approach in non-intrusive monitoring of tool wear evolution in massive CFRP automatic drilling processes in the aircraft industry

Background: Current approaches to predicting intervention needs and mortality have reached 65–85% accuracy, which falls below clinical decision-making requirements in patients with acute pancreatitis (AP). We aimed to accurately predict therapeutic intervention needs and mortality on admission, in AP patients, using machine learning (ML). Methods: Data were obtained from three databases of patients admitted with AP: one retrospective (Chengdu) and two prospective (Liverpool and Chengdu) databases. Intervention and mortality differences, as well as potential predictors, were investigated. Univariate analysis was conducted, followed by a random forest ML algorithm used in multivariate analysis, to identify predictors. The ML performance matrix was applied to evaluate the model’s performance. Results: Three datasets of 2846 patients included 25 potential clinical predictors in the univariate analysis. The top ten identified predictors were obtained by ML models, for predicting interventions and mortality, from the training dataset. The prediction of interventions includes death in non-intervention patients, validated with high accuracy (96%/98%), the area under the receiver-operating-characteristic curve (0.90/0.98), and positive likelihood ratios (22.3/69.8), respectively. The post-test probabilities in the test set were 55.4% and 71.6%, respectively, which were considerably superior to existing prognostic scores. The ML model, for predicting mortality in intervention patients, performed better or equally with prognostic scores. Conclusions: ML, using admission clinical predictors, can accurately predict therapeutic interventions and mortality in patients with AP.

The durability and long-term survival of medical implants are major concerns for patients and surgeons. The laser shock peening (LSP) process can enhance the implant’s in-vivo lifespan through the compressive residual stress introduced on the implant’s surface. In the current research, a novel hybrid machine learning (ML) prediction tool was developed to calculate LSP induced residual stresses. Laser energies of 3 J, 5 J, 7 J with three overlapping levels of 33%, 50% and 67% with a constant laser spot diameter were introduced to a Ti-6Al-7Nb titanium hip implant material. A three-dimensional finite element model was developed incorporating an explicit dynamic analysis to capture the dynamic material response during the LSP process. Furthermore, The random forest ML algorithm was adapted so that the laser energy and overlapping were set as input parameters, while the associated residual stresses were set as output parameters. The mean squared error (MSE), root MSE and coefficient of determination for testing data sets concerning residual stress were 112.9%, 10.6% and 97%, respectively. The FEM and ML results both show a good agreement with the experimental data. The new proposed approach allows development of ML models even with a limited experimental data. The accuracy and performance of each model are discussed and the limitations are addressed. The approach carried out in this paper enables subsequent predictions of surface treatment techniques of implants through residual stress fields and can be applied to a wide range of applications.

يعد طرد الموظفين من المنظمات مشكلة خطيرة. يجب حل مشكلة تدوير الموظفين أو اطردهم من داخل المنظمة نظرًا لأن لها تأثيرًا سلبيًا على المنظمة. يعد الاكتشاف اليدوي لتسرب الموظفين أمرًا صعبًا للغاية، لذلك تم استخدام خوارزميات التعلم الآلي ML بشكل متكرر لاكتشاف تسرب الموظفين بالإضافة إلى تصنيف الموظفين وفقًا للاستبدالهم. باستخدام التعلم الآلي، بحثت دراسة واحدة فقط في تصنيف الموظفين حتى الآن. تم اقتراح نهج جديد لاتخاذ القرار متعدد المعايير MCDM إلى جانب مبدأ DE-PARETO لتصنيف الموظفين. يشار إلى هذا باسم مخطط SNEC . تم تصميم نموذج AHP-TOPSIS DE-PARETO PRINCIPLE (AHPTOPDE) الذي يستخدم نظام MCDM على مرحلتين لتصنيف الموظفين. في المرحلة الأولى، تم استخدام عملية التسلسل الهرمي التحليلي AHP لتعيين الأوزان النسبية لعوامل إنجاز الموظف. في المرحلة الثانية، تم استخدام TOPSIS للتعبير عن أهمية الموظفين في إجراء تصنيف الموظفين. تم تطبيق قاعدة 20-30-50 البسيطة في مبدأ DE PARETO لتصنيف الموظفين إلى ثلاث مجموعات رئيسية وهي الموظفون المتحمسون والسلوكيون والمضطربون. يتم بعد ذلك تطبيق خوارزمية الغابة العشوائية كخوارزمية أساسية لإطار عمل الموظفين المقترح للتنبؤ بخسارة الموظفين على أساس الفصل والذي يتم اختباره على مجموعة بيانات قياسية لنظام معلومات الموارد البشرية HRIS، ويتم تقييم النتائج التي تم الحصول عليها باستخدام طرق تعلم الآلة الأخرى. تتمتع خوارزمية Random Forest ML في مخطط SNEC بدقة إجمالية مماثلة أو أفضل قليلاً وMCC مع تعقيد زمني أقل مقارنةً بمخطط ECPR باستخدام خوارزمية CATBOOST

Os dados de sensoriamento remoto (SR) são uma fonte essencial de informação para o mapeamento da dinâmica da paisagem em áreas urbanas. Algoritmos de inteligência artificial (IA), incluindo aprendizado de máquina (AM), fornecem métodos robustos para o processamento de dados de SR. Este estudo utilizou métodos de AM do software GRASS GIS para processar imagens de satélite e analisar as mudanças na paisagem da região central da China. O objetivo foi analisar a dinâmica da paisagem por meio das mudanças na cobertura do solo detectadas ao longo de 10 anos, com intervalos de 2 anos entre as imagens. O fluxo de trabalho incluiu o algoritmo Random Forest de classificação de imagens. Os dados incluíram seis imagens Landsat 8-9 OLI/TIRS, capturadas no outono de 2013, 2015, 2017, 2019, 2021 e 2023. Os resultados indicaram a expansão da área da cidade de Wuhan, o que evidencia os processos de urbanização e desenvolvimento intensivo do solo. Este artigo demonstra a aplicação de uma abordagem aprimorada por IA em cartografia para análise de imagens, visando a análise da dinâmica da paisagem na região central da China.

Accurate and reliable lithological mapping through satellite-borne remote sensing data and image classification approaches has a critical role since it can automatically and promptly identify lithological units over large areas. Most available Pixel-Object Based comparative classification studies have been applied to land use land cover (LULC) studies; however, this research aims to evaluate and compare the performance of these digital classification methods in the field of geological mapping in semi-arid areas, by integrating spectral bands and neo-bands, particularly the Minimum noise fraction (MNF) and the principal component analysis (PCA), of Sentinel-2A satellite imagery, to map the southern of Skhour Rehamna which is located at the western Moroccan Meseta. The analysis results from two different methods, namely, pixel-based image analysis (PBIA) with k-nearest neighbour (K-NN) and Random Forest (RF) machine learning algorithms (MLAs), and Geographic Object-Based Image Analysis (GEOBIA) were assessed and compared. PBIA method involved selection of training areas whether it was k-NN or RF MLAs, and produced lithological maps that exhibit “salt and pepper” effects as well as problems associated to delineating accurate lithological boundaries, while GEOBIA approach involved multi-resolution segmentation step where scale, shape and compactness parameters should be adjusted as accurate as possible, in order to segment the image into homogeneous and meaningful regions so that the resulted samples were classified using Standard Nearest Neighbour algorithm. Therefore, the resulting lithological maps were assessed by comparing both techniques using confusion matrix, overall accuracy (OA) and Kappa coefficient (K). The results show that the GEOBIA approach had higher overall agreement (83.46% OA and 0.76 K) than RF (81.92% OA and 0.72 K) and k-NN (80.79% OA and 0.70 K) PBIA approaches. Overall, the results clearly indicate the potential of GEOBIA technique for lithological mapping applications to produce more realistic maps.

Several machine learning (ML) techniques were tested for the feasibility of performing automated pattern and waveform recognitions of terahertz time-domain spectroscopy datasets. Out of all the ML techniques under test, it was observed that random forest statistical algorithm works well with the THz datasets in both the frequency and time domains. With such ML algorithm, a classifier can be created with less than 1% out-of-bag error for segmentation of rusted and non-rusted sample regions of the image datasets in frequency domain. The degree of linear correlation between the rusted area percentage and the image spatial resolution with terahertz frequency can be used as an additional cross-validation criteria for the evaluation of classifier quality. However, for different rust staging measured datasets, a standardized procedure of image pre-processing is necessary to create/apply a single classifier and its usage is only limited to 1 ± 0.2 THz. Moreover, random forest is practically the best choice among the several popular ML techniques under test for waveform recognition of time-domain data in terms of classification accuracy and timing. Our results demonstrate the usefulness of random forest and several other machine learning algorithms for terahertz hyperspectral pattern recognition.

PURPOSE: As accelerometer methods advance, researchers may employ different body placements and data processing techniques. This may result in different physical activity (PA) estimates that will make study comparisons challenging. We compared three data processing techniques for hip worn accelerometer data; compared wrist and hip locations; and compared wake-time wrist to a 24-hour wrist protocol. METHODS: 2608 days from 333 women (mean age 55) with matched hip and wrist accelerometer data were compared using generalized estimating equations adjusting for days within individuals. Participants were asked to wear hip accelerometers for waking hours and the wrist accelerometer (on the non-dominant hand) for 24 hours over 7 days. Standard wake wear time criteria (5 days, 600 mins/day) were applied to the hip and wrist. Minute level count (CPM) cut points from the vertical axis were applied to the hip data (1952 cpm (MVPA)). A laboratory developed algorithm (GGIR) for wrist and hip vector magnitude (VM) data was employed to identify MVPA. A free living machine learned (ML) behavioral algorithm was applied to classify walking in the hip and wrist. Meeting guidelines was considered as 30 mins PA per day. RESULTS: Wear time compliance between the hip and wrist only varied by 2%. 25% of days included 30 minutes of PA with the hip cut points, 35% with the GGIR VM at the hip, and 71% with the ML walking algorithm. 54% of days were classified by the wrist GGIR wake time criteria compared to 58% with the 24 hour protocol. The ML algorithm classified 60% of days on the wrist wake time, compared with 61% with the 24 hour protocol. All differences were statistically significant at p<.05. CONCLUSIONS: Different processing methods and body placements appear to significantly affect estimates of PA. These differences could greatly impact population estimates of PA. Differences between methods could have been affected by the validity of the algorithms for this aged population: the CPM and VM algorithms were developed in younger adults in the laboratory, and the ML algorithm was developed in free-living women the same age as this cohort. These findings will inform consensus development for accelerometer wear and data processing protocols in future studies.

India is ranked 120th among 122 countries globally in WaterAid&amp;#8217;s water quality index. Regular water quality monitoring is essential to determine which inland water bodies are experiencing depreciating water quality. Long-term trends have been obtained using satellite remote sensing, necessitating multiple image analysis. The computational burden of processing numerous satellite images can be reduced using Google Earth Engine&amp;#8217;s (GEE) cloud computing capabilities. Thorough research was conducted to determine the global spatio-temporal and biochemical factors impacting surface water quality (WQ). The public availability of geospatial datasets and free access to cloud-based geo-computing platforms such as GEE are widely used for spatio-temporal mapping, global surface water monitoring, water quality parametric variation, and real-time forecasting. Many researchers have recently focused on improving data mining and machine learning algorithms to accurately deal with image classification and predictive problems for crop identification and monitoring. In the present study, we propose to define band spectral ratios, spectral band equations, and empirical models for water quality parameters. A few neural network models will be used to (i) query and pre-process satellite earth observations that coincide with the study area, (ii) extract the spectra, and (iii) use spectral band wavelength charts, time-series charts, spatial-distribution maps, and the development of an online dashboard application to visualize the results graphically upon using integrated Landsat (8,9), Sentinel-2A/B and PlanetScope satellite data for the pre-monsoon and post-monsoon seasons in 2023 in the pan-India region. MODIS-TERRA provides LST spatial-temporal monitoring. In this, we have assessed and compared the performance of CART, SVM, and RF ML algorithms. We found that RF outperforms CART and SVM algorithms in the GEE platform with PlanetScope data (80.71% overall accuracy (OA) with Kappa 0.89) and also with the integration of PlanetScope and Sentinel-2A/B data (OA = 85.53%, Kappa 0.91). But CART outperforms RF and SVM algorithms with Sentiel-2A/B data (OA = 81.59%, Kappa 0.85). The SAM technique, spectral feature fitting, continuum band removal, and other band-spectral ratio techniques are employed for quantitative hyperspectral data analysis. Specifically, the performance metrics of XGBoost and SGD for both Chl-a (R^2 = 0.818) and Turbidity (R^2 = 0.815) models exhibited robust accuracy. We have also developed a Google API-based JavaScript code that can be tested under complex coastal shores, challenging inundation and variable climatic conditions. Our method provides the end-to-end cloud computing workflow shown in this research, considering cost and computational efficiency for timely information delivery.Keywords: Classification and Regression Trees (CART), Chlorophyll-a (conc), Color dissolved organic matter (CDOM), Composite water management index (CWMI), Environmental Mapping and Analysis Program (EnMAP), Land Surface Temperature (LST), Machine Learning (ML), Random Forest (RF), Spectral Angle Mapper (SAM), Stochastic Gradient Descent (SGD), Support Vector Machine (SVM), Total Suspended Solids (TSS), Water Quality (WQ), XGBoost (Extreme Gradient Boosting).

The performance of three popular machine learning algorithms to predict diabetes based upon using three diabetes datasets is presented. Two of the datasets are from the public domain and the third is composed from a research study group. The J48, Random Forest and Naive Bayes machine learning algorithms were evaluated. Machine Learning (ML) is used to both analyse and make predictions from data that is simply too voluminous for humans to process. This is especially true with medical data where the use of machine learning and data analytics is still in its infancy. More specifically this research investigates the application of ML algorithms on the growing data from the healthcare industry on the global diabetes epidemic. The performance of ML algorithms to predict diabetes is lacking. This paper provides an analysis of the challenges of machine learning in this field and covers this gap in the research.

Resistance spot-welded joints are crucial parts in contemporary manufacturing technology due to their ubiquitous use in the automobile industry. The necessity of improving manufacturing efficiency and quality at an affordable cost requires deep knowledge of the resistance spot welding (RSW) process and the development of artificial neural network (ANN)- and machine learning (ML)-based modelling techniques, apt for providing essential tools for design, planning, and incorporation in the welding process. Tensile shear force and nugget diameter are the most crucial outputs for evaluating the quality of a resistance spot-welded specimen. This study uses ML and ANN models to predict shear force and nugget diameter responses to RSW parameters. The RSW analysis was executed on similar and dissimilar AISI 304 and grade 2 titanium alloy joints with equal and unequal thicknesses. The input parameters included welding current, pressure, welding duration, squeezing time, holding time, pulse welding, and sheet thickness. Linear regression, Decision tree, Support vector machine (SVM), Random forest (RF), Gradient-boosting, CatBoost, K-Nearest Neighbour (KNN), Ridge, Lasso, and ElasticNet machine learning algorithms, along with two different structures of Multilayer Perceptron, were utilized for studying the impact of the RSW parameters on the shear force and nugget diameter. Different validation metrics were applied to assess each model's quality. Two equations were developed to determine the shear force and nugget diameter based on the investigation parameters. The current research also presents a prediction of the Relative Importance (RI) of RSW factors. Shear force and nugget diameter predictions were examined using SHapley (SHAP) Additive Explanations for the first time in the RSW field. Trainbr as the training function and Logsig as the transfer function delivered the best ANN model for predicting shear force in a one-output structure. Trainrp with Tansig made the most accurate predictions for nugget diameter in a one-output structure and for shear force and diameter in a two-output structure. Depending on validation metrics, the Random forest model outperformed the other ML algorithms in predicting shear force or nugget diameter in a one-output model, while the Decision tree model gave the best prediction using a two-output structure. Linear regression made the worst ML predictions for shear force, while ElasticNet made the worst nugget diameter forecasts in a one-output model. However, in two-output models, Lasso made the worst predictions.

Cognitive and functional decline are common problems in older adults, especially in those 75+ years old. Currently, there is no specific plasma biomarker able to predict this decline in healthy old-age people. Machine learning (ML) is a subarea of artificial intelligence (AI), which can be used to predict outcomes Aim: This study aimed to evaluate routine laboratory variables able to predict cognitive and functional impairment, using ML algorithms, in a cohort aged 75+ years, in a one-year follow-up study. One hundred and thirty-two older adults aged 75+ years were selected through a community-health public program or from long-term-care institutions. Their functional and cognitive performances were evaluated at baseline and one year later using a functional activities questionnaire, Mini-Mental State Examination, and the Brief Cognitive Screening Battery. Routine laboratory tests were performed at baseline. ML algorithms-random forest, support vector machine (SVM), and XGBoost-were applied in order to describe the best model able to predict cognitive and functional decline using routine tests as features. The random forest model showed better accuracy than other algorithms and included triglycerides, glucose, hematocrit, red cell distribution width (RDW), albumin, hemoglobin, globulin, high-density lipoprotein cholesterol (HDL-c), thyroid-stimulating hormone (TSH), creatinine, lymphocyte, erythrocyte, platelet/leucocyte (PLR), and neutrophil/leucocyte (NLR) ratios, and alanine transaminase (ALT), leukocyte, low-density lipoprotein cholesterol (LDL-c), cortisol, gamma-glutamyl transferase (GGT), and eosinophil as features to predict cognitive decline (accuracy = 0.79). For functional decline, the most important features were platelet, PLR and NLR, hemoglobin, globulin, cortisol, RDW, glucose, basophil, B12 vitamin, creatinine, GGT, ALT, aspartate transferase (AST), eosinophil, hematocrit, erythrocyte, triglycerides, HDL-c, and monocyte (accuracy = 0.92). Routine laboratory variables could be applied to predict cognitive and functional decline in oldest-old populations using ML algorithms.

Background/Objectives: Acute respiratory distress syndrome (ARDS) represents a critical complication in polytrauma patients, characterized by diffuse lung inflammation and bilateral pulmonary infiltrates with mortality rates reaching 45% in intensive care units (ICU). The heterogeneous nature of ARDS and complex clinical presentation in severely injured patients poses substantial diagnostic challenges, necessitating early prediction tools to guide timely interventions. Machine learning (ML) algorithms have emerged as promising approaches for clinical decision support, demonstrating superior performance compared to traditional scoring systems in capturing complex patterns within high-dimensional medical data. Based on the identified research gaps in early ARDS prediction for polytrauma populations, our study aimed to: (i) develop a balanced random forest (BRF) ML model for early ARDS prediction in critically ill polytrauma patients, (ii) identify the most predictive clinical features using ANOVA-based feature selection, and (iii) evaluate model performance using comprehensive metrics addressing class imbalance challenges. Methods: This retrospective cohort study analyzed 407 polytrauma patients admitted to the ICU of the Center of Traumatology and Major Burns of Ben Arous, Tunisia, between 2017 and 2021. We implemented a comprehensive ML pipeline that incorporates Tomek Links undersampling, ANOVA F-test feature selection for the top 10 predictive variables, and SMOTE oversampling with a conservative sampling rate of 0.3. The BRF classifier was trained with class weighting and evaluated using stratified 5-fold cross-validation. Performance metrics included AUROC, PR-AUC, sensitivity, specificity, F1-score, and Matthews correlation coefficient. Results: Among 407 patients, 43 developed ARDS according to the Berlin definition, representing a 10.57% incidence. The BRF model demonstrated exceptional predictive performance with an AUROC of 0.98, a sensitivity of 0.91, a specificity of 0.80, an F1-score of 0.84, and an MCC of 0.70. Precision-recall AUC reached 0.86, demonstrating robust performance despite class imbalance. During stratified cross-validation, AUROC values ranged from 0.93 to 0.99 across folds, indicating consistent model stability. The top 10 selected features included procalcitonin, PaO2 at ICU admission, 24-h pH, massive transfusion, total fluid resuscitation, presence of pneumothorax, alveolar hemorrhage, pulmonary contusion, hemothorax, and flail chest injury. Conclusions: Our BRF model provides a robust, clinically applicable tool for early prediction of ARDS in polytrauma patients using readily available clinical parameters. The comprehensive two-step resampling approach, combined with ANOVA-based feature selection, successfully addressed class imbalance while maintaining high predictive accuracy. These findings support integrating ML approaches into critical care decision-making to improve patient outcomes and resource allocation. External validation in diverse populations remains essential for confirming generalizability and clinical implementation.

The aging and multimorbid population and health personnel shortages pose a substantial burden on primary health care. While predictive machine learning (ML) algorithms have the potential to address these challenges, concerns include transparency and insufficient reporting of model validation and effectiveness of the implementation in the clinical workflow. To systematically identify predictive ML algorithms implemented in primary care from peer-reviewed literature and US Food and Drug Administration (FDA) and Conformité Européene (CE) registration databases and to ascertain the public availability of evidence, including peer-reviewed literature, gray literature, and technical reports across the artificial intelligence (AI) life cycle. PubMed, Embase, Web of Science, Cochrane Library, Emcare, Academic Search Premier, IEEE Xplore, ACM Digital Library, MathSciNet, AAAI.org (Association for the Advancement of Artificial Intelligence), arXiv, Epistemonikos, PsycINFO, and Google Scholar were searched for studies published between January 2000 and July 2023, with search terms that were related to AI, primary care, and implementation. The search extended to CE-marked or FDA-approved predictive ML algorithms obtained from relevant registration databases. Three reviewers gathered subsequent evidence involving strategies such as product searches, exploration of references, manufacturer website visits, and direct inquiries to authors and product owners. The extent to which the evidence for each predictive ML algorithm aligned with the Dutch AI predictive algorithm (AIPA) guideline requirements was assessed per AI life cycle phase, producing evidence availability scores. The systematic search identified 43 predictive ML algorithms, of which 25 were commercially available and CE-marked or FDA-approved. The predictive ML algorithms spanned multiple clinical domains, but most (27 [63%]) focused on cardiovascular diseases and diabetes. Most (35 [81%]) were published within the past 5 years. The availability of evidence varied across different phases of the predictive ML algorithm life cycle, with evidence being reported the least for phase 1 (preparation) and phase 5 (impact assessment) (19% and 30%, respectively). Twelve (28%) predictive ML algorithms achieved approximately half of their maximum individual evidence availability score. Overall, predictive ML algorithms from peer-reviewed literature showed higher evidence availability compared with those from FDA-approved or CE-marked databases (45% vs 29%). The findings indicate an urgent need to improve the availability of evidence regarding the predictive ML algorithms' quality criteria. Adopting the Dutch AIPA guideline could facilitate transparent and consistent reporting of the quality criteria that could foster trust among end users and facilitating large-scale implementation.