Machine Learning-based Approach Research Articles

Active learning strategies for the design of sustainable alloys.

Active learning comprises machine learning-based approaches that integrate surrogate model inference, exploitation and exploration strategies with active experimental feedback into a closed-loop framework. This approach aims at describing and predicting specific material properties, without requiring lengthy, expensive or repetitive experiments. Recently, active learning has shown potential as an approach for the design of sustainable materials, such as scrap-compatible alloys, and for enhancing the longevity of metallic materials. However, in-depth investigations into suited best-practice strategies of active learning for sustainable materials science are still scarce. This study aims to present and discuss active learning strategies for developing and improving sustainable alloys, addressing single-objective and multi-objective learning and modelling scenarios. As model cases, we discuss active learning strategies for optimizing Invar and magnetic alloys, representing single-objective scenarios, and more general steel design approaches, exemplifying multi-objective optimization. We discuss the significance of finding the right balance between exploitation and exploration strategies in active learning and suggest strategies to reduce the number of iterations across diverse scenarios. This kind of research aims to find metrics for a more effective application of active learning and is used here to advance the field of sustainable alloy design.This article is part of the discussion meeting issue 'Sustainable metals: science and systems'.

An efficient leakage power optimization framework based on reinforcement learning with graph neural network

Threshold voltage (Vth\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$V_{th}$$\\end{document}) assignment is convenient for leakage optimization due to the exponential relation between leakage power and Vth\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$V_{th}$$\\end{document} by swapping logic cells without routing effort. However, it poses great challenge in large scale circuit design as an NP-hard problem. Machine learning-based approaches have been proposed to solve this problem, aiming to achieve well tradeoff between leakage power reduction and runtime speed up without new induced timing violation. In this paper, a leakage power optimization framework based on reinforcement learning (RL) with graph neural network (GNN) is first-ever proposed to formulate Vth\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$V_{th}$$\\end{document} assignment as a RL process by learning timing and physical characteristics of each circuit instance with GNN. Multiple instances are selected in a non-overlapped manner for each RL action iteration to speed up convergence and decouple timing interdependence along circuit path, where the corresponding reward is carefully defined to tradeoff between leakage reduction and potential timing violation. The proposed framework was validated by the Opencores and IWLS 2005 benchmark circuits with TSMC 28 nm technology. Experimental results demonstrate that our work outperforms prior non-analytical and GNN-based methods with better leakage power optimization by additional 5% to 17% reduction, which is highly consistent with the commercial tool. When transferring the trained RL-based framework to unseen circuits, it achieves the roughly identical leakage optimization results as seen circuit and speed up the runtime by 5.7×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes$$\\end{document} to 8.5×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes$$\\end{document} compared with commercial tool.

Predicting food adulterants in milk using Support Vector Machine (SVM)

Milk adulteration is a significant global issue, particularly in emerging nations, where inadequate monitoring and unhygienic conditions prevail. The adulteration of milk with various chemicals, such as urea, water, skimmed milk powder, sugar, and detergent, poses serious health risks, including heart problems, diarrhea, CNS disorders, irritation, and gastrointestinal disorders. Traditional detection methods are labor-intensive and require sophisticated equipment, which limits their practical application. This study aims to develop a machine learning-based approach to detect milk adulteration using attributes like Solids- Not-Fat (SNF), fat, Corrected Lactometer Reading (CLR), Total Solids (TS), temperature, and protein content. Various machine learning models were employed and evaluated for their performance, including Logistic Regression, Decision Trees, SVM, and Random Forests. The findings demonstrate that machine learning can effectively identify adulteration types, providing a foundation for the dairy industry’s practical and automated detection systems. This research comprehensively reviews common milk adulterants and highlights advanced detection methods to ensure milk quality and safety.

Construction of an inflammatory, nutritional, and metabolic prognostic risk score in patients with heart failure with preserved ejection fraction: a machine learning-based approach

Abstract Background Chronic inflammation, malnutrition, and metabolic syndrome contribute to the underlying mechanisms of heart failure with preserved ejection fraction (HFpEF). Inflammatory, nutritional, and metabolic biomarkers often interact with each other and affect the prognosis of patients. Purpose We aimed to identify the most predictive indicators from a pool of 21 biomarkers encompassing inflammation, nutritional status, as well as lipid, glucose, thyroid, and uric acid metabolism. Subsequently, predictive biomarkers were used to develop a risk score to enhance risk prediction for patients with HFpEF. Methods We included patients diagnosed with HFpEF and without infective or systemic disease. The primary outcome was all-cause mortality. We employed the Least Absolute Shrinkage and Selection Operator (LASSO) regression to screen the biomarkers. A machine learning-based approach was utilized to fine-tune the optimal model parameters. Additionally, we generated 1000 bootstrapping datasets to identify biomarkers recurring above a 95% frequency in repetitions, which were then employed to formulate the biomarker risk score. The discrimination of incorporating the risk score into the basic model was evaluated using 100 iterations of 5-fold cross-validation to assess the predictive efficacy. Results Among the 1311 included patients (with a median age of 64 years and 42.6% female), 363 patients (27.7%) experienced mortality over a median follow-up period of 2.7 years. The final risk score model was derived from 5 biomarkers—albumin (ALB), red blood cell distribution width-standard deviation (RDW-SD), lymphocytes, triiodothyronine (T3), and uric acid—each selected in over 95% of 1000 bootstrapping iterations. Integration of this risk score into the basic model notably enhanced discrimination (∆C-index=0.015, 95% CI 0.005-0.023) and reclassification (IDI: 3.3%, 95% CI 1.7%-5.8%; NRI: 15.2%, 95% CI 6.5%-22.5%) for risk stratification. In time-dependent receiver operating characteristic (ROC) analysis, the mean area under the curve (AUC) of the risk score was 0.688, 0.710, and 0.738 at 1, 3, and 5 years post-discharge, respectively, in the cross-validation sets. Incorporating the risk score into the basic model significantly improved the AUC at 1, 3, and 5 years (DeLong test P-value<0.05). Furthermore, in multivariable Cox regression, the risk score demonstrated an independent association with all-cause mortality (HR: 1.81, 95% CI 1.51-2.16, P<0.001 per 1 score increase). Conclusions A risk score derived from 5 commonly used inflammatory, nutritional, thyroid and uric acid metabolic biomarkers can effectively identify high-risk patients with HFpEF. This approach supports the development of potential individualized management strategies for patients with HFpEF.Study population and model constructionPredictive performance of the risk score

Machine Learning-Based Local Knowledge Approach to Mapping Urban Slums in Bandung City, Indonesia

Rapid urban population growth in Bandung City has led to the development of slums due to inadequate housing facilities and urban planning. However, it remains unclear how these slums are distributed and evolve spatially and temporally. Therefore, it is necessary to map their distribution and trends effectively. This study aimed to classify slum areas in Bandung City using a machine learning-based local knowledge approach; this classification exercise contributes towards Sustainable Development Goal 11 related to sustainable cities and communities. The methods included settlement and commercial/industrial classification from 2021 SPOT-6 satellite data by the Random Forest classifier. A knowledge-based classifier was used to derive slum and non-slum settlements from the settlement and commercial/industrial classification, as well as railway, river, and road buffering. Our findings indicate that these methods achieved an overall accuracy of 82%. The producer’s accuracy for slum areas was 70%, while the associated user’s accuracy was 92%. Meanwhile, the Kappa coefficient was 0.63. These findings suggest that local knowledge could be a potent option in the machine learning algorithm.

Optimisation of artefact detection in photoplethysmography heart rate data: influence of different classifiers in machine learning models

Abstract Background Heart rate (HR) tracking by wrist-worn devices using photoplethysmography (PPG) could assist in continuously following up physical activity. However, the accuracy can be impacted by (motion) artefacts. Machine learning models could help to recognise artefacts in PPG-based HR data. The choice of classifier in these machine learning models is a determing factor for task performance of the model. Purpose This study evaluates and determines the optimal classifier for a new machine learning-based approach to enhance the reliability of artefact detection in PPG-based HR data. Methods A total of 62 participants (27 cardiac rehabilitation patients, 35 healthy athletes) wore both a test device and a reference device measuring HR continuously for 24 hours. A training dataset was prepared, assigning two independent labels (i.e. anomaly and activity) to each HR episode based on the reference device data. Fitbit data were processed using our in-house designed artefact removal procedure, which involves the application of two classification models: one for anomaly detection and another for activity detection. Four distinct classifiers were employed for both models: Balanced Bagging, Balanced Bagging with Random Forest, Balanced Random Forest, and Logistic Regression. Each classifier was evaluated using area under the receiver operating characteristic curve (ROC-AUC), accuracy, sensitivity and specificity. Results Of the 1,647,328 HR data points collected, 103,095 (6.26%) were identified as artefacts. Figure 1 and Figure 2 summarise the performance of the distinct classifiers for the anomaly model and the activity model, respectively. Balanced Bagging and Balanced Bagging with Random Forest consistently demonstrate the highest AUC values and accuracies across both anomaly and activity detection models (anomaly detection: AUC = 0.95, accuracy = 89-85%; activity detection: AUC = 0.98, accuracy = 95%). Comparing these two, Balanced Bagging with Random Forest emerges as the preferred option, given the highest sensitivity in both anomaly detection (93%>86%) and activity detection models (99%>96%). In contrast, Balanced Random Forest and Logistic Regression exhibit inferior performance. In the anomaly detection model, Balanced Random Forest exhibits a lower sensitivity of 75%, while Logistic Regression performs even worse with a sensitivity of 25%. Similarly, in the activity detection model, both Balanced Random Forest and Logistic Regression demonstrate diminished performance. Conclusions Balanced Bagging with Random Forest emerges as the optimal classifier to detect anomalies and activities in continuous PPG-based HR data, thus contributing to the optimisation of our in-house designed procedure for removing artefacts. This processing aims to provide a reliable and automatic way for continuous HR monitoring, which can help monitor and guide physical activities.

Data driven cost-sensitive boosted tree for interpretable banking systemic risk prediction

Systemic risk (SR) in the banking sector poses a significant threat to both the financial system and the real economy. Its inherent characteristics of nonlinearity, non-equilibrium, and interconnectedness make it challenging to analyze using conventional statistical methods. In this paper, a cost-sensitive gradient boosting tree algorithm, FLXGBoost, is proposed for predicting SR. FLXGBoost considers the boosted tree, XGBoost as the base framework, boosting trees as the fundamental framework, guaranteeing the robustness of SR prediction. Additionally, to tackle the challenge of extreme data imbalance prevalent in SR prediction tasks, a cost-aware loss function, focal loss, is embedded into the boosted tree to enable FLXGBoost a risk-aware fashion. Moreover, a tree-derived interpretable algorithm SHAP is incorporated into this cost-sensitive solution, making FLXGBoost an accurate and interpretable risk-aware model. Experimental results on a financial risk prediction dataset pertaining to banking SR evince the capacity of FLXGBoost to significantly reduce the misclassification rate of risk banks, thereby mitigating substantial losses attributed to erroneous predictions of risky scenarios. Moreover, compared with classical imbalanced machine learning-based SR prediction approaches, the diverse evaluation metrics of FLXGBoost show that it is a competitive solution for accurate SR prediction. Besides, the explanatory analysis further demonstrates that FLXGBoost is a promising solution to address the issue of biased predictions in imbalanced banking SR in the interpretation perspective.

Metasurface-enabled multifunctional single-frequency sensors without external power

IoT sensors are crucial for visualizing multidimensional and multimodal information and enabling future IT applications/services such as cyber-physical spaces, digital twins, autonomous driving, smart cities and virtual/augmented reality (VR or AR). However, IoT sensors need to be battery-free to realistically manage and maintain the growing number of available sensing devices. Here, we provide a novel sensor design approach that employs metasurfaces to enable multifunctional sensing without requiring an external power source. Importantly, unlike existing metasurface-based sensors, our metasurfaces can sense multiple physical parameters even at a fixed frequency by breaking classic harmonic oscillations in the time domain, making the proposed sensors viable for usage with limited frequency resources. Moreover, we provide a method for predicting physical parameters via the machine learning-based approach of random forest regression. The sensing performance was confirmed by estimating the temperature and light intensity, and excellent determination coefficients larger than 0.96 were achieved. Our study affords new opportunities for sensing multiple physical properties without relying on an external power source or requiring multiple frequencies, which markedly simplifies and facilitates the design of next-generation wireless communication systems.

Hypertension Detection Through Speech Analysis Using Machine Learning-Based Approaches with the Identification of BP Sensitive Phonemes and Features

There are certain difficulties and unpleasant issues related to conventional diagnostic tools. These factors tilted the researchers toward finding an alternative non-invasive way of diagnosis. This alternate approach usually involves physiological and lifestyle-related data. The non-invasive tools are more convenient for common people as they are user-friendly and have no side effects. At the same time, they are cost-effective as well. The non-invasive diagnosis is also preferred by the people who live in places where medical facilities are not abundant. This study concentrates on detecting a person as hypertensive by analyzing certain parameters in speech using machine learning approaches. We identify some phonemes and features of speech that are more sensitive to capture the distortions in speech due to hypertension. Four different machine learning methods involving both classical and state-of-the-art methods in our study show the effectiveness of both types of machine learning methods in different dimensions. The study shows inspiring results in terms of prediction accuracy ([Formula: see text]95%) as well as identifying a minimal set of hypertension-sensitive features. It is also found that when we combine the predictions of both classical and state-of-the-art methods, the result gives more reliable predictions.

Convergent reductive evolution in bee-associated lactic acid bacteria.

Distantly related organisms may evolve similar traits when exposed to similar environments or engaging in certain lifestyles. Several members of the Lactobacillaceae [lactic acid bacteria (LAB)] family are frequently isolated from the floral niche, mostly from bees and flowers. In some floral LAB species (henceforth referred to as bee-associated LAB), distinctive genomic (e.g., genome reduction) and phenotypic (e.g., preference for fructose over glucose or fructophily) features were recently documented. These features are found across distantly related species, raising the hypothesis that specific genomic and phenotypic traits evolved convergently during adaptation to the floral environment. To test this hypothesis, we examined representative genomes of 369 species of bee-associated and non-bee-associated LAB. Phylogenomic analysis unveiled seven independent ecological shifts toward the bee environment in LAB. In these species, we observed significant reductions of genome size, gene repertoire, and GC content. Using machine leaning, we could distinguish bee-associated from non-bee-associated species with 94% accuracy, based on the absence of genes involved in metabolism, osmotic stress, or DNA repair. Moreover, we found that the most important genes for the machine learning classifier were seemingly lost, independently, in multiple bee-associated lineages. One of these genes, acetaldehyde-alcohol dehydrogenase (adhE), encodes a bifunctional aldehyde-alcohol dehydrogenase which has been associated with the evolution of fructophily, a rare phenotypic trait that is pervasive across bee-associated LAB species. These results suggest that the independent evolution of distinctive phenotypes in bee-associated LAB has been largely driven by independent losses of the same sets of genes.IMPORTANCESeveral LAB species are intimately associated with bees and exhibit unique biochemical properties with potential for food applications and honeybee health. Using a machine learning-based approach, our study shows that adaptation of LAB to the bee environment was accompanied by a distinctive genomic trajectory deeply shaped by gene loss. Several of these gene losses occurred independently in distantly related species and are linked to some of their unique biotechnologically relevant traits, such as the preference for fructose over glucose (fructophily). This study underscores the potential of machine learning in identifying fingerprints of adaptation and detecting instances of convergent evolution. Furthermore, it sheds light onto the genomic and phenotypic particularities of bee-associated bacteria, thereby deepening the understanding of their positive impact on honeybee health.

METASPACE-ML: Context-specific metabolite annotation for imaging mass spectrometry using machine learning

Imaging mass spectrometry is a powerful technology enabling spatial metabolomics, yet metabolites can be assigned only to a fraction of the data generated. METASPACE-ML is a machine learning-based approach addressing this challenge which incorporates new scores and computationally-efficient False Discovery Rate estimation. For training and evaluation, we use a comprehensive set of 1710 datasets from 159 researchers from 47 labs encompassing both animal and plant-based datasets representing multiple spatial metabolomics contexts derived from the METASPACE knowledge base. Here we show that, METASPACE-ML outperforms its rule-based predecessor, exhibiting higher precision, increased throughput, and enhanced capability in identifying low-intensity and biologically-relevant metabolites.

Advance industrial monitoring of physio-chemical processes using novel integrated machine learning approach

With the rapid transition of Industry 4.0 to 5.0, modern industrial physio-chemical processes are characterized by two critical challenges: process safety and the quality of the final product. Traditional industrial monitoring methods have low reliability in accuracy and robustness, and they are inefficiently providing satisfactory results. This paper introduces a novel integration technique that employs machine learning (ML) to tackle the challenges associated with real industrial monitoring in physical and industrial processes. The proposed framework integrates distributed canonical correlation analysis - R-vine copula (DCCA-RVC), global local preserving projection (GLPP), and 2-Dimensional Deng information entropy (2-DDE). The framework's ability and productivity are assessed utilizing existing approaches such as wavelet-PCA, MRSAE, and DALSTM-AE and the new proposed novel integrated machine learning-based (DCCA-RVC) approach as benchmarks for model performance. The proposed novel approach has been validated by testing it on the ethanol-water system distillation column (DC) and Tennessee Eastman Process (TEP), utilizing it as actual industrial benchmarks. The results demonstrate that the novel integration ML-technique (DCCA-RVC) T22 – GLP monitoring graphs for the fault class type 1 in the distillation column showed a (FAR) of 0 %, a (FDR) of 100 %, a precision of 100 %, F1-score of 100 % and an accuracy of 100 %. However, for the TEP process failure event 13, the (FAR) was 0 %, the (FDR) was 99 %, the accuracy was 100 %, the F1-score was 99.5 %, and the accuracy was 99.5 %.

LSTM-based framework for predicting point defect percentage in semiconductor materials using simulated XRD patterns

In this paper, we present a machine learning-based approach that leverages Long Short-Term Memory (LSTM) networks combined with a sliding window technique for feature extraction, aimed at accurately predicting point defect percentages in semiconductor materials based on simulated X-ray Diffraction (XRD) data. The model was initially trained on silicon-simulated XRD data with defect percentages ranging from 1 to 5%, enabling it to predict defect percentages from 0 to 10% in silicon and other semiconductor materials, including AlAs, CdS, GaAs, Ge, and ZnS. Through extensive experimentation, we explored different sequence lengths and LSTM units, identifying the optimal configuration as a sequence length of 3501 and 4500 units, which yielded the best results. The model’s mean absolute error at 4500 units was 0.021, the lowest among the LSTM configurations tested. The sliding window technique plays a crucial role in capturing temporal dependencies within the XRD data, allowing the model to generalize to other semiconductor materials. Additionally, we observed that increasing defect percentages consistently led to a rise in background intensity. We further examined the relationship between crystal structure and defect precentage predictions, uncovering consistent trends for materials with Diamond Cubic and Zinc Blende structures. This LSTM-based method offers a novel approach to predicting defect percentages using simulated XRD patterns of materials.

Sustainable Spatial Features of Settlements along the Miao Frontier Wall and Miao Frontier Corridor Analyzed through Machine Learning Clustering

This study employed unsupervised machine learning clustering algorithms to systematically analyze the spatial layout characteristics of residential buildings in villages along the Miao Frontier Wall and Miao Frontier Corridor in Western Hunan. The results indicated significant differences between the two regions in terms of the number of building clusters, distribution patterns, and compactness. A comparative analysis of the K-means and DBSCAN algorithms revealed that K-means is more effective in uncovering the internal spatial layout characteristics of settlements. Further analysis showed that villages along the Miao Frontier Wall exhibited greater diversity and complexity, whereas those along the Miao Frontier Corridor demonstrated higher clustering efficiency and denser internal building distribution. These differences can be attributed to variations in historical functions, geographical environments, planning concepts, and social structures. This research uncovers the spatial layout patterns of traditional settlements and proposes a machine learning-based approach to cultural heritage preservation, providing a theoretical foundation for future heritage conservation and spatial optimization, thereby promoting the sustainable development and protection of traditional cultural heritage.

Machine Learning-Based Approach towards Identification of Pharmaceutical Suspensions Exploiting Speckle Pattern Images

Parenteral artificial nutrition (PAN) is a lifesaving medical treatment for many patients worldwide. Administration of the wrong PAN drug can lead to severe consequences on patients’ health, including death in the worst cases. Thus, their correct identification, just before injection, is of crucial importance. Since most of these drugs appear as turbid liquids, they cannot be easily discriminated simply by means of basic optical analyses. To overcome this limitation, in this work, we demonstrate that the combination of speckle pattern (SP) imaging and artificial intelligence can provide precise classifications of commercial pharmaceutical suspensions for PAN. Towards this aim, we acquired SP images of each sample and extracted several statistical parameters from them. By training two machine learning algorithms (a Random Forest and a Multi-Layer Perceptron Network), we were able to identify the drugs with accurate performances. The novelty of this work lies in the smart combination of SP imaging and machine learning for realizing an optical sensing platform. For the first time, to our knowledge, this approach is exploited to identify PAN drugs.

Experimentation, Taguchi and machine learning-based optimisation of parameters concerning heat losses from the trapezoidal box-type solar cooker

ABSTRACT The optimal design parameter combinations for a trapezoidal solar cooker that yield the lowest heat loss coefficient have been determined using a thorough Taguchi and Machine learning-based optimization approach that has been established for this study. Data for the previously described optimization have been generated through the use of an experimental approach in a laboratory environment. Numerous influencing factors are taken into account, including the temperature of the bottom plate, the depth of the cavity, the emissivity of the bottom cover, and the wind-induced heat transfer coefficient on the top glass cover. For the current investigation, the ideal factor combination is found to be a parametric combination plate temperature of 350K with 0.4 plate emissivity, 15W/m2 convective heat transfer coefficient, and 0.25 m height. To determine the percentage contribution of each control element to the heat loss coefficient, analysis of variance (ANOVA) has been used for the collected data and signal-to-noise ratios. Plate temperature at 74.72% and emissivity at 23.84% are the primary contributing variables found. Likewise, the least contributing factors like height (0.57%) and convective heat transfer coefficient (0.32%) are discovered. A regression equation is used to represent the connection between the response and the control factor. This formula is suggested as a forecast formula for calculating the heat loss coefficient.

Machine learning-based outlier detection for pipeline in-line inspection data

Pipeline companies are facing challenges in maintaining the integrity and reliability of their pipelines. They are working towards predictive maintenance using machine learning-based approaches to predicting anomalies. Training machine learning models requires sufficient data. Data quality is therefore becoming important because inaccurate data will lead to an inaccurate or wrong decision on pipeline condition assessment and the following management. This research paper intends to address the data quality issues of pipeline inspection data such as in-line inspection (ILI) data using machine learning models. Different machine learning models developed by random forest regression, linear regression, and nearest neighbors’ methods were tested to detect outliers in the ILI data. In this paper, the ILI data collected from an oil pipeline over a period of 22 years was applied to testing and analysis. To verify the outlier detection results of machine learning models, we used statistical analysis including Z-score method to check and find if there are any gaps in the analysis. It verifies that all these methods show almost the same or very similar results for the detection of the outliers. Hence, this study presents a robust method for the field applications in the pipeline industry.

Challenges and Advances in Analyzing TLS 1.3-Encrypted Traffic: A Comprehensive Survey

The widespread adoption of encrypted communication protocols has significantly enhanced network security and user privacy, simultaneously elevating the importance of encrypted traffic analysis across various domains, including network anomaly detection. The Transport Layer Security (TLS) 1.3 protocol, introduced in 2018, has gained rapid popularity due to its enhanced security features and improved performance. However, TLS 1.3’s security enhancements, such as encrypting more of the handshake process, present unprecedented challenges for encrypted traffic analysis, rendering traditional methods designed for TLS 1.2 and earlier versions ineffective and necessitating the development of novel analytical techniques. This comprehensive survey provides a thorough review of the latest advancements in TLS 1.3 traffic analysis. First, we examine the impact of TLS 1.3’s new features, including Encrypted ClientHello (ECH), 0-RTT session resumption, and Perfect Forward Secrecy (PFS), on existing traffic analysis techniques. We then present a systematic overview of state-of-the-art methods for analyzing TLS 1.3 traffic, encompassing middlebox-based interception, searchable encryption, and machine learning-based approaches. For each method, we provide a critical analysis of its advantages, limitations, and applicable scenarios. Furthermore, we compile and review key datasets utilized in machine learning-based TLS 1.3 traffic analysis research. Finally, we discuss the main challenges and potential future research directions for TLS 1.3 traffic analysis. Given that TLS 1.3 is still in the early stages of widespread deployment, research in this field remains nascent. This survey aims to provide researchers and practitioners with a comprehensive reference, facilitating the development of more effective TLS 1.3 traffic analysis techniques that balance network security requirements with user privacy protection.

Automated Classification of Coronary Plaque on Intravascular Ultrasound by Deep Classifier Cascades.

Intravascular ultrasound (IVUS) is the gold standard modality for in vivo visualization of coronary arteries and atherosclerotic plaques. Classification of coronary plaques helps to characterize heterogeneous components and evaluate the risk of plaque rupture. Manual classification is time-consuming and labor-intensive. Several machine learning-based classification approaches have been proposed and evaluated in recent years. In the current study, we develop a novel pipeline composed of serial classifiers for distinguishing IVUS images into five categories: normal, calcified plaque, attenuated plaque, fibrous plaque, and echolucent plaque. The cascades comprise densely connected classification models and machine learning classifiers at different stages. Over 100,000 IVUS frames of five different lesion types were collected and labeled from 471 patients for model training and evaluation. The overall accuracy of the proposed classifier is 0.877, indicating that the proposed framework has the capacity to identify the nature and category of coronary plaques in IVUS images. Further, it may provide real-time assistance on plaque identification and facilitate clinical decision-making in routine practice.

Predictive modeling for coiled tubing fatigue using advanced machine learning techniques

Coiled tubing CT plays Pivotal role in oil and gas well intervention operations due to its advantages such as flexibility, fast mobilization, safe, low cost and wide range of applications, including: well intervention, cleaning, stimulation, fluid displacement, cementing, and drilling. However, CT is subject of fatigue and mechanical damage caused by repeated bending cycles, internal pressure and environmental factors which can lead to a premature failure, high operational cost and production downtime. With the development of CT proprieties and application traditional fatigue life prediction methods based on analytical models integrated in tracking process showed in some cases an underestimate or overestimate of the actual fatigue life of CT particularly when complex factor like welding type, corrosive environment, and high-pressure variation are involved. This study addresses this limitation by introducing a comprehensive machine learning-based approach to improve the accuracy of CT fatigue life prediction, using a data set derived from over 350 tests both lab scale and full-scale fatigue test. The study has incorporated the impact of different parameters such as CT, grades, wall, thickness, CT diameter, internal pressure and welding types. By using advanced machine learning techniques such as artificial network (ANN), Gradient boosting regressor we got a more precise estimation of the number of cycles to failure than traditional models. The results of this study shown the importance of integration of machine learning for CT fatigue life analysis and demonstrating its capacity to enhance the prediction accuracy and reduce the uncertainty. A detailed machine Learning models is presented, emphasizing their capability to handle complex data and improve prediction under diverse operational conditions. This study contributes to more reliable, CT management and safer more cost-efficient well intervention operations.