Unsupervised Machine Learning Techniques Research Articles

Uncovering emotional and network dynamics in the speech of patients with chronic low back pain

BackgroundComputational linguistics allows an understanding of language structure and different forms of expression of patients’ perceptions. AimsThe aims of this study were (i) to carry out a descriptive analysis of the discourse of people with chronic low back pain using sentiment analysis (SA) and network analysis; (ii) to verify the correlation between patients’ profiles, pain intensity and disability levels with SA and network analysis; and (iii) to identify clusters in our sample according to language and SA using an unsupervised machine learning technique. MethodsWe performed a secondary analysis of a qualitative study including participants with chronic non-specific low back pain. We used the data related to participants’ feelings when they received the diagnosis. The SA and network analysis were performed using the Valence Aware Dictionary and sEntiment Reasoner, and the Speech Graph, respectively. Clustering was performed using the K-means algorithm. ResultsIn the SA, the mean composite score was −0.31 (Sd. = 0.58). Most participants presented a negative discourse (n = 41; 72%). Word Count (WC) and Largest Strongly connected Component (LSC) positively correlated with education. No statistically significant correlations were observed between pain intensity, disability levels, SA, and network analysis. Two clusters were identified in our sample. ConclusionThe SA showed that participants reported their feeling when describing the moment of the diagnosis using sentences with negative discourse. We did not find a statistically significant correlation between pain intensity, disability levels, SA, and network analysis. Education level presented positive correlation with WC and LSC.

Image Denoising Techniques Using Unsupervised Machine Learning and Deep Learning Algorithms: A Review

The continuous evolution of imaging technologies has accentuated the demand for robust and efficient image denoising techniques. Unsupervised machine learning algorithms have emerged as promising tools for addressing this challenge. This review scrutinizes the efficacy, versatility, and limitations of various unsupervised machine learning approaches in the area of image denoising. The paper commences with a clarification of the foundational concepts of image denoising and the pivotal role unsupervised machine learning plays in enhancing its efficacy. Traditional denoising methods, encompassing filters and transforms, are briefly outlined, highlighting their insufficiencies in handling complicated noise patterns prevalent in modern imaging systems. Subsequently, the review delves into an exploration of unsupervised machine learning techniques tailored for image denoising. This includes an in-depth analysis of methodologies such as clustering deep learning. Each technique is surveyed for its architectural variation, adaptability, and performance in denoising diverse image datasets. Additionally, the review encompasses an evaluation of prevalent metrics used for quantifying denoising performance, discussing their relevance and applicability across varying noise types and image characteristics. Furthermore, it delineates the challenges faced by unsupervised techniques in this domain and charts prospective avenues for future research, emphasizing the fusion of unsupervised methods with other learning paradigms for heightened denoising efficacy. This review merges empirical insights, critical analysis, and future perspectives, serving as a roadmap for researchers and practitioners navigating the landscape of image denoising through unsupervised machine learning methodologies.

A statistical and multiwavelength photometric analysis of a young embedded open star cluster: IC 1590

ABSTRACT We present a statistical and multiwavelength photometric studies of young open cluster IC 1590. We identified 91 cluster members using Gaia DR3 astrometry data using ensemble-based unsupervised machine learning techniques. From Gaia EDR3 data, we estimate the best-fitting parameters for IC 1590 using the Automated Stellar Cluster Analysis package (asteca) yielding the distance d ∼ 2.87 ± 0.02 kpc, age ∼ 3.54 ± 0.05 Myr, metallicity z ∼ 0.0212 ± 0.003, binarity value of ∼ 0.558, and extinction Av ∼ 1.252 ± 0.4 mag for an Rv value of ∼ 3.322 ± 0.23. We estimate the initial mass function slope of the cluster to be α = 1.081 ± 0.112 for single stars and α = 1.490 ± 0.051 for a binary fraction of ∼ 0.558 in the mass range 1 M⊙ ≤ m (M⊙) ≤ 100 M⊙. The G-band luminosity function slope is estimated to be ∼ 0.33 ± 0.09. We use (J − H) versus (H − Ks) colour–colour diagram to identify young stellar objects (YSOs). We found that all the identified YSOs have ages ≤ 2 Myr and masses ∼ 0.35 – 5.5 M⊙. We also fit the radial surface density profile. Using the galpy, we performed orbit analysis of the cluster. The extinction map for the cluster region has been generated using the PNICER technique, and it is almost similar to the dust structure obtained from the 500 μm dust continuum emissions map of Herschel SPIRE. We finally at the end discussed the star formation scenario in the cluster region.

Proposed Model for Real-Time Anomaly Detection in Big IoT Sensor Data for Smart City

A smart city represents an advanced urban environment that utilizes digital technologies to improve the well-being of residents, efficiently manage urban operations, and prioritize long-term sustainability. These technologically advanced cities collect significant data through various Internet of Things (IoT) sensors, highlighting the crucial importance of detecting anomalies to ensure both efficient operation and security. However, real-time identification of anomalies presents challenges due to the sheer volume, rapidity, and diversity of the data streams. This manuscript introduces an innovative framework designed for the immediate detection of anomalies within extensive IoT sensor data in the context of a smart city. Our proposed approach integrates a combination of unsupervised machine learning techniques, statistical analysis, and expert feature engineering to achieve real-time anomaly detection. Through an empirical assessment of a practical dataset obtained from a smart city environment, we demonstrate that our model outperforms established techniques for anomaly detection.

Unsupervised machine learning combined with 4D scanning transmission electron microscopy for bimodal nanostructural analysis

Unsupervised machine learning techniques have been combined with scanning transmission electron microscopy (STEM) to enable comprehensive crystal structure analysis with nanometer spatial resolution. In this study, we investigated large-scale data obtained by four-dimensional (4D) STEM using dimensionality reduction techniques such as non-negative matrix factorization (NMF) and hierarchical clustering with various optimization methods. We developed software scripts incorporating knowledge of electron diffraction and STEM imaging for data preprocessing, NMF, and hierarchical clustering. Hierarchical clustering was performed using cross-correlation instead of conventional Euclidean distances, resulting in rotation-corrected diffractions and shift-corrected maps of major components. An experimental analysis was conducted on a high-pressure-annealed metallic glass, Zr-Cu-Al, revealing an amorphous matrix and crystalline precipitates with an average diameter of approximately 7 nm, which were challenging to detect using conventional STEM techniques. Combining 4D-STEM and optimized unsupervised machine learning enables comprehensive bimodal (i.e., spatial and reciprocal) analyses of material nanostructures.

Determining Smart Phone Sensing and K-Means Clustering for Accurate and Timely Railway Track Joint Fault Diagnosis

The railway track joint is an important component that connects two sections of the rail and ensures a smooth and safe operation of trains. However, the joint is also a critical point of failure that can lead to train derailments and accidents. Therefore, accurate and timely detection of joint faults is crucial for ensuring the safety and reliability of railway transportation. In this paper, we propose a novel approach for railway track joint fault diagnosis using smart phone sensing and k-means clustering. Our approach utilizes the accelerometer sensor of a smart phone to measure the vibrations and movements of a specifically developed railway shoe stick that is employed on an actual railway track for the condition monitoring of the railway tracks. More than 60000 data values are collected and are then processed and analysed using k-means clustering, a popular unsupervised machine learning technique that groups similar data points together. The K means clustering in this study forms 3 clusters as a result. The 3 clusters after being validated on the track by virtue of visual inspection are determined to be acceleration values of the healthy track, track with higher joint gap than the standardized value and super-elevated railway track joint fault(s), respectively. In addition to its high accuracy and efficiency, our approach has several advantages over traditional methods, such as low cost, easy deployment, and high scalability. Moreover, the smart phone sensing technology can be easily integrated with existing train monitoring systems, making it a useful tool for real-time joint fault diagnosis and maintenance. Overall, this study demonstrates the potential of smart phone sensing and k-means clustering for railway track joint fault diagnosis and highlights the need for further research in this field.

Therapeutic Peptides Are Preferentially Solubilized in Specific Microenvironments within PEG-PLGA Polymer Nanoparticles.

Polymeric nanoparticles are a highly promising drug delivery formulation. However, a lack of understanding of the molecular mechanisms that underlie their drug solubilization and controlled release capabilities has hindered the efficient clinical translation of such technologies. Polyethylene glycol-poly(lactic-co-glycolic) acid (PEG-PLGA) nanoparticles have been widely studied as cancer drug delivery vehicles. In this letter, we use unbiased coarse-grained molecular dynamics simulations to model the self-assembly of a PEG-PLGA nanoparticle and its solubulization of the anticancer peptide, EEK, with good agreement with previously reported experimental structural data. We applied unsupervised machine learning techniques to quantify the conformations that polymers adopt at various locations within the nanoparticle. We find that the local microenvironments formed by the various polymer conformations promote preferential EEK solubilization within specific regions of the NP. This demonstrates that these microenvironments are key in controlling drug storage locations within nanoparticles, supporting the rational design of nanoparticles for therapeutic applications.

An Unsupervised Learning Approach for Predicting Wind Farm Power and Downstream Wakes Using Weather Patterns

AbstractWind energy resource assessment typically requires numerical modeling at fine resolutions, which is computationally expensive for multi‐year timescales. Increasingly, unsupervised machine learning techniques are used to identify representative weather patterns that can help simulate long‐term behavior. Here we develop a novel wind energy workflow that combines the weather patterns from unsupervised clustering with a numerical weather prediction model (WRF) to obtain efficient long‐term predictions of wind farm power and downstream wakes, which provide a good approximation to full WRF simulations at vastly reduced computational cost. We use ERA5 reanalysis data and compare clustering on low altitude pressure and wind velocity, a more relevant variable for wind resource assessment. We also compare varying domain sizes for the clustering. A WRF simulation is run at each cluster center and the results aggregated into a long‐term prediction using a novel post‐processing technique. We consider two case study regions and show that our long‐term predictions achieve good agreement with a year of WRF simulations in 2% of the computational time. Moreover, clustering over a Europe‐wide domain produces good agreement for predicting wind farm power output, but clustering over smaller domains is required for downstream wake predictions which agree with the year of WRF simulations. Our approach facilitates multi‐year predictions of power output and downstream farm wakes, by providing a fast, reliable, and flexible methodology applicable to any global region. Moreover, this constitutes the first tool to help mitigate effects of wind energy loss downstream of wind farms.

Using Natural Language Processing and Patient Journey Clustering for Temporal Phenotyping of Antimicrobial Therapies for Cat Bite Abscesses

BackgroundTemporal phenotyping of patient journeys, which capture the common sequence patterns of interventions in the treatment of a specific condition, is useful to support understanding of antimicrobial usage in veterinary patients. Identifying and describing these phenotypes can inform antimicrobial stewardship programs designed to fight antimicrobial resistance, a major health crisis affecting both humans and animals, in which veterinarians have an important role to play. ObjectiveThis research proposes a framework for extracting temporal phenotypes of patient journeys from clinical practice data through the application of natural language processing (NLP) and unsupervised machine learning (ML) techniques, using cat bite abscesses as a model condition. By constructing temporal phenotypes from key events, the relationship between antimicrobial administration and surgical interventions can be described, and similar treatment patterns can be grouped together to describe outcomes associated with specific antimicrobial selection. MethodsCases identified as having a cat bite abscess as a diagnosis were extracted from VetCompass Australia, a database of veterinary clinical records. A classifier was trained and used to label the most clinically relevant event features in each record as chosen by a group of veterinarians. The labeled records were processed into coded character strings, where each letter represents a summary of specific types of treatments performed at a given visit. The sequences of letters representing the cases were clustered based on weighted Levenshtein edit distances with KMeans++ to identify the main variations of the patient treatment journeys, including the antimicrobials used and their duration of administration. ResultsA total of 13,744 records that met the selection criteria was extracted and grouped into 8,436 cases. There were 9 clinically distinct event sequence patterns (temporal phenotypes) of patient journeys identified, representing the main sequences in which surgery and antimicrobial interventions are performed. Patients receiving amoxicillin and surgery had the shortest duration of antimicrobial administration (median of 3.4 days) and patients receiving cefovecin with no surgical intervention had the longest antimicrobial treatment duration (median of 27 days). ConclusionOur study demonstrates methods to extract and provide an overview of temporal phenotypes of patient journeys, which can be applied to text-based clinical records for multiple species or clinical conditions. We demonstrate the effectiveness of this approach to derive real-world evidence of treatment impacts using cat bite abscesses as a model condition to describe patterns of antimicrobial therapy prescriptions and their outcomes.

Towards Automated Target Picking in Scalar Magnetic Unexploded Ordnance Surveys: An Unsupervised Machine Learning Approach for Defining Inversion Priors

With advancements in both the quality and collection speed of magnetic data captured by uncrewed aerial vehicle (UAV)-based systems, there is a growing need for robust and efficient systems to automatically interpret such data. Many existing conventional methods require manual inspection of the survey data to pick out candidate areas for further analysis. We automate this initial process by implementing unsupervised machine learning techniques to identify small, well-defined regions. When further analysis is conducted with magnetic inversion algorithms, then our approach also reduces the nonlinear computation and time costs by breaking one huge inversion problem into several smaller ones. We also demonstrate robustness to noise and sidestep the requirement for large quantities of labeled training data: two pitfalls of current automation approaches. We propose first to use hierarchical clustering on filtered magnetic gradient data and then to fit ellipses to the resulting clusters to identify subregions for further analysis. In synthetic data experiments and on real-world datasets, our model successfully captures all true targets while simultaneously proposing fewer computationally costly false positives. With this approach, we take an important step towards fully automating the detection of high-risk subregions, but we wish to emphasize the importance of prudent skepticism until it has been tested and proven on more diverse data.

Using marine mammal necropsy data in animal health surveillance: the case of the harbor porpoise in the Southern North Sea

Rapid changes of marine ecosystems resulting from human activities and climate change, and the subsequent reported rise of infectious diseases in marine mammals, highlight the urgency for timely detection of unusual health events negatively affecting populations. Studies reporting pathological findings in the commonly stranded harbor porpoise (Phocoena phocoena) on North Atlantic coastlines are essential to describe new and emerging causes of mortality. However, such studies often cannot be used as long-term health surveillance tools due to analytical limitations. We tested 31 variables gained from stranding-, necropsy-, dietary- and marine debris data from 405 harbor porpoises using applied supervised and unsupervised machine learning techniques to explore and analyze this large dataset. We classified and cross-correlated the variables and characterized the importance of the different variables for accurately predicting cause-of-death categories, to allow trend assessment for good conservation decision. The variable ‘age class’ seemed most influential in determining cause-of-death categories, and it became apparent that juveniles died more often due to acute causes, including bycatch, grey-seal-predation and other trauma, while adults of infectious diseases. Neonates were found in summer, and mostly without prey in their stomach and more often stranded alive. The variables assigned as part of the external examination of carcasses, such as imprints from nets and lesions induced by predators, as well as nutritional condition were most important for predicting cause-of-death categories, with a model prediction accuracy of 75%. Future porpoise monitoring, and in particular the assessment of temporal trends, should predominantly focus on influential variables as determined in this study. Pathogen- and contaminant assessment data was not available for all cases, but would be an important step to further complete the dataset. This could be vital for drawing population-inferences and thus for long-term harbor porpoise population health monitoring as an early warning tool for population change.

Construction of a predictive model for blood transfusion in patients undergoing total hip arthroplasty and identification of clinical heterogeneity

A precise forecast of the need for blood transfusions (BT) in patients undergoing total hip arthroplasty (THA) is a crucial step toward the implementation of precision medicine. To achieve this goal, we utilized supervised machine learning (SML) techniques to establish a predictive model for BT requirements in THA patients. Additionally, we employed unsupervised machine learning (UML) approaches to identify clinical heterogeneity among these patients. In this study, we recruited 224 patients undergoing THA. To identify factors predictive of BT during the perioperative period of THA, we employed LASSO regression and the random forest (RF) algorithm as part of supervised machine learning (SML). Using logistic regression, we developed a predictive model for BT in THA patients. Furthermore, we utilized unsupervised machine learning (UML) techniques to cluster THA patients who required BT based on similar clinical features. The resulting clusters were subsequently visualized and validated. We constructed a predictive model for THA patients who required BT based on six predictive factors: Age, Body Mass Index (BMI), Hemoglobin (HGB), Platelet (PLT), Bleeding Volume, and Urine Volume. Before surgery, 1 h after surgery, 1 day after surgery, and 1 week after surgery, significant differences were observed in HGB and PLT levels between patients who received BT and those who did not. The predictive model achieved an AUC of 0.899. Employing UML, we identified two distinct clusters with significantly heterogeneous clinical characteristics. Age, BMI, PLT, HGB, bleeding volume, and urine volume were found to be independent predictors of BT requirement in THA patients. The predictive model incorporating these six predictors demonstrated excellent predictive performance. Furthermore, employing UML enabled us to classify a heterogeneous cohort of THA patients who received BT in a meaningful and interpretable manner.

Anomaly Detection of Wire Arc Additively Manufactured Parts via Surface Tension Transfer through Unsupervised Machine Learning Techniques

Wire Arc Additive Manufacturing (WAAM) has recently gained significant attention from the research community as it offers potential for notable time and cost reduction compared to other technologies. To enhance the overall quality of products, the ability to detect defects in real-time is a subject of great interest. Accordingly, this work investigates the effectiveness of diverse semi-supervised anomaly detection algorithms based on machine learning for online defect detection in WAAM. Deposition data in terms of welding voltage and current during a Surface Tension Transfer welding process on mild steel samples are used. Twelve statistical features are extracted in the time and frequency domains to identify defects as anomalies with a sample rate of 1 s with a maximum achieved accuracy of 91.9%. The obtained results provide valuable insights into the efficacy of machine learning for online defect detection in WAAM, which can be leveraged to enhance product quality and reduce costs.

Machine Learning-aided Computational Fragment-based Design of Small Molecules for Hypertension Treatment

With over 1 billion affected adults, hypertension is one of the most critical public health challenges worldwide. If left untreated over time, hypertension increases the likelihood of premature disability or death from cardiovascular diseases. Despite the range of medications available for the treatment of hypertension, many individuals do not respond positively to the treatment. Additionally, a significant percentage of the population does not take the medication as prescribed, which is sometimes attributed to intolerable side effects. Hence, there is still the need to develop new hypertension drugs that provide patients with favourable treatment outcomes. This paper explores the computational method of drug discovery to generate new lead drug molecules for hypertension by targeting the renin-angiotensin-aldosterone system (RAAS). Specifically, we proposed a framework that integrates computational fragment-based methods and an unsupervised machine learning technique to generate new lead Angiotensin-Converting Enzyme Inhibitor (ACEI) and Angiotensin-Receptor Blocker (ARB) molecules. The molecule generation process is initiated using all the approved agents acting on the RAAS that are available in the ChEMBL and DrugBank databases to create a fragment pool. The fragments are used to generate new molecules, which are categorised into ACEI and ARB clusters using unsupervised machine learning techniques. The generated molecules in each category are screened to determine their suitability as oral drug molecules, considering their physicochemical properties. Further screening is performed to determine the molecules’ suitability as ACEIs or ARBs, based on the presence of the appropriate functional groups and their similarities with existing drug molecules. The resultant molecules that passed screening are proposed as new lead antihypertensive agents. A synthesizability test is also performed on the final new lead molecules to determine the ease of making them compared to the original molecules.

Multi-Criteria Decision-Making and Machine Learning Techniques: A Multidisciplinary Analysis of the World Military Scenario

Military development is increasingly related to strategic independence and technological advantages, representing an important factor in countries’ scientific, technological, and economic development. In this context, the present work proposes a methodology for evaluating the world’s military power based on the integration between Multi-Criteria Decision-Making (MCDM) and Machine Learning. To this end, data from the military, economic, and strategic spheres of 140 countries were analyzed and evaluated considering 12 quantitative variables. Considering the large volume of data to be analyzed and establishing a ranking of countries, the Principal Component Analysis (PCA), an unsupervised Machine Learning technique, was used. PCA allowed the analysis of 140 countries, identifying three factors representing the collective behavior of the 12 original variables, providing a world ranking of military power. The results were compared with specialized rankings on the subject and proved robust and reliable. As a contribution to the academy and society, the authors highlighted that this work fills the gap regarding the application of PCA in military problems to classify the observations, emphasized that the proposed methodology can be replicated in the most diverse problems and serve as input in other MCDM and data science techniques. In addition, the multidisciplinary of PCA allows the technique to support the decision-making process in the most diverse areas of knowledge that involve data analysis in tactical, operational, and strategic problems.

Characterization of serpentinization in olivine‐orthopyroxene‐H2O system revealed by thermogravimetric and multivariate statistical analyses

AbstractThermogravimetric (TG) analyses were used to characterize the products and quantify the extent of serpentinization as a stepwise weight loss during heating (TG loss) or its derivative (DTG). Multivariate analyses are powerful tools for extracting information from complicated spectrum data; however, no studies have applied them to characterize serpentinites. In this study, hydrothermal experiments of olivine‐H2O, olivine–orthopyroxene‐H2O and orthopyroxene‐H2O were conducted at 250–400°C and under vapor‐saturated pressure. The product minerals observed were serpentine+brucite+magnetite in the olivine‐H2O experiments and serpentine±talc in the orthoyroxene‐H2O and olivine‐orthopyroxene‐H2O experiments. These results are consistent with those of previous studies; however, the positions and width of DTG peaks for individual minerals were varied depending on the experimental conditions. To extract systematics from the TG spectra, non‐negative matrix factorization (NMF), an unsupervised machine learning technique, was applied to the DTG spectra of the experimental products. NMF revealed that the DTG profiles were explained by a linear combination of six basis spectra, which corresponded to the characteristic products, including three types of serpentine minerals (low‐, medium‐, and high‐T), two types of brucite (low‐and high‐T), two type of talc (talc+serpentine mixture, well‐crystallized talc) with different crystallinity, and noise during the TG measurement. Systematic changes in the factor loading revealed that, in the olivine‐H2O systems, the products changed from medium‐T serpentine+low‐T brucite to high‐T serpentine+high‐T brucite as serpentinization progressed. In the olivine‐orthopyroxene system, low‐T serpentine or poorly crystallized talc+serpentine mixture was initially formed, followed by the formation of well‐crystallized talc, resulting in dehydration. Applying NMF to DTG showed the mineralogical differences between olivine and orthopyroxene systems and increases of the crystallinity during the progress of serpentinization, suggesting its potential for characterizing various serpentinites within oceanic lithospheres that suffer from several stages of alteration and weathering at different temperatures.

Melt pool instability in surface polishing by laser remelting: preliminary analysis and online monitoring with K-means clustering

Surface polishing by laser remelting (SP-LRM) is a novel, versatile, high-speed, and low-cost advanced manufacturing technology for producing high-quality surface finishes. The process utilizes a high-power laser that delivers a large amount of instantaneous energy melting a superficial thin layer of material to a molten state. This allows the melt pool to flow driven by thermocapillary and surface tension forces. The target of the process is to melt, reallocate, and resolidify surface peaks into valleys in order to yield a low surface roughness (Sa). SP-LRM, complexity arises from instabilities occurring during laser-material interactions, resulting from non-linear thermodynamics, initial surface topography, overheating, abrupt changes in laser path trajectories involving acceleration and deceleration, and various other factors. These process instabilities significantly affect the attainment of a desired smooth final surface. Presently, the identification of anomalies resulting from a specific set of laser parameters in laser remelting (LRM) is performed offline by assessing the surface topography of LRM using optical profilometer and correlating it with surface non-uniformities that are indicative of process instabilities. This study streamlines the anomaly detection process and identifies the presence of irregularities using an unsupervised clustering machine learning (ML) technique, specifically K-means clustering. During the laser remelting (LRM) process, a high-speed near-infrared (NIR) camera captures relative thermal emission images, which are then classified into a minimum of three clusters using the K-means algorithm. These clusters correspond to positive and negative axial laser beam positions, indicating shifts in the laser spot on the image, and the stability states of laser-material interactions. Preliminary findings show promising results in the employment of artificial intelligence (AI) to enhance LRM as a conventional industrial technology for polishing and structuring tooling surfaces.

Early detection of critical urban events using mobile phone network data.

Network Signalling Data (NSD) have the potential to provide continuous spatio-temporal information about the presence, mobility, and usage patterns of cell phone services by individuals. Such information is invaluable for monitoring large urban areas and supporting the implementation of decision-making services. When analyzed in real time, NSD can enable the early detection of critical urban events, including fires, large accidents, stampedes, terrorist attacks, and sports and leisure gatherings, especially if these events significantly impact mobile phone network activity in the affected areas. This paper presents empirical evidence that advanced NSD can detect anomalies in mobile traffic service consumption, attributable to critical urban events, with fine spatial (a spatial resolution of a few decameters) and temporal (minutes) resolutions. We introduce two methodologies for real-time anomaly detection from multivariate time series extracted from large-scale NSD, utilizing a range of algorithms adapted from the state-of-the-art in unsupervised machine learning techniques for anomaly detection. Our research includes a comprehensive quantitative evaluation of these algorithms on a large-scale dataset of NSD service consumption for the Paris region. The evaluation uses an original dataset of documented critical or unusual urban events. This dataset has been built as a ground truth basis for assessing the algorithms' performance. The obtained results demonstrate that our framework can detect unusual events almost instantaneously and locate the affected areas with high precision, largely outperforming random classifiers. This efficiency and effectiveness underline the potential of NSD-based anomaly detection in significantly enhancing emergency response strategies and urban planning. By offering a proactive approach to managing urban safety and resilience, our findings highlight the transformative potential of leveraging NSD for anomaly detection in urban environments.

Supervised and unsupervised techniques in textile quality inspections

Quality inspection is a critical step in ensuring the quality and efficiency of textile production processes. With the increasing complexity and scale of modern textile manufacturing systems, the need for accurate and efficient quality inspection and defect detection techniques has become paramount. This paper compares supervised and unsupervised Machine Learning techniques for defect detection in the context of industrial textile production, in terms of their respective advantages and disadvantages, and their implementation and computational costs. We explore the use of an autoencoder for the detection of defects in textiles. The goal of this preliminary work is to find out if unsupervised methods can successfully train models with good performance without the need for defect labelled data.

A case study of petrophysical prediction using machine learning integrated with interval inversion in a tight sand reservoir in Egypt

This study presents a new algorithm for reservoir characterization using borehole logging data, which integrates unsupervised machine learning techniques and interval inversion to automatically determine layers’ boundaries and petrophysical parameters. The research aims to reduce the time and manual input required for borehole inversion to estimate petrophysical parameters. The algorithm was used to predict different layer boundaries of sand-shale intercalations for both synthetic and field wireline log data. Field well logging measurements were obtained from an oil and gas field in Egypt, specifically the Jurassic reservoir. The reservoir is composed of a dense sandstone layer with significant heterogeneity due to diagenesis, which converts kaolinite into illite. The algorithm was used to predict petrophysical parameters, resulting in a decrease in porosity and permeability. The field data from the well reveals that the reservoir is made up of varying-quality sandstone, impacting storage capacity and hydrocarbon saturation. The algorithm demonstrates consistent convergence of the data at 7.5%. Overall, the integration of the new cluster technique and interval inversion can improve the time-intensive and laborious process of borehole data inversion to estimate petrophysical parameters.