Unsupervised Machine Learning Algorithms Research Articles

Self-Adaptive Incremental PCA-Based DBSCAN of Acoustic Features for Anomalous Sound Detection

In modern industry, maintaining continuous machine operations is important for improving production efficiency and reducing costs. Therefore, the smart technology of acoustic monitoring to detect anomalous machine conditions earlier before breakdowns works as part of predictive maintenance and is applied not only in industry fault detection but also in safety monitoring and surveillance systems. This paper proposes a self-adaptive unsupervised machine learning algorithm with dimension-reduction technology to detect anomalous sounds after extracting acoustic machine features. Technically, the automatic EPS calculation algorithm-based genetic algorithm optimizes the automatic clustering algorithm’s configuration for incremental principal component analysis and density-based spatial clustering algorithms with noise. IPCA is enhanced by the sequential Karhunen–Loeve (SKL) algorithm, and the condensation algorithm works as the second layer of the algorithm to reduce the number of effective components. This architecture could select an optimized set of parameters based on different test environments and keeps performance quality with fewer computational requirements. In the experiments, 228 sets of normal sounds and 100 sets of anomaly sounds are used. The sound files are collected from the same machine type (stepper motors) at a real plant site. We compare the proposed algorithm with K-means++, one-class SVM, agglomerative clustering, DCGAN and DCNN-Autoencoder, and this new algorithm performs best, with an AUC of 0.84 and the shortest execution time. The algorithm is generic and can be applied to detect anomalies in machines to provide early warning to people to avoid serious accidents or disasters.

Using machine learning to discover traumatic brain injury patient phenotypes: national concussion surveillance system Pilot

ABSTRACT Objective The objective is to determine whether unsupervised machine learning identifies traumatic brain injury (TBI) phenotypes with unique clinical profiles. Methods Pilot self-reported survey data of over 10,000 adults were collected from the Centers for Disease Control and Prevention (CDC)’s National Concussion Surveillance System (NCSS). Respondents who self-reported a head injury in the past 12 months (n = 1,364) were retained and queried for injury, outcome, and clinical characteristics. An unsupervised machine learning algorithm, partitioning around medoids (PAM), that employed Gower’s dissimilarity matrix, was used to conduct a cluster analysis. Results PAM grouped respondents into five TBI clusters (phenotypes A-E). Phenotype C represented more clinically severe TBIs with a higher prevalence of symptoms and association with worse outcomes. When compared to individuals in Phenotype A, a group with few TBI-related symptoms, individuals in Phenotype C were more likely to undergo medical evaluation (odds ratio [OR] = 9.8, 95% confidence interval[CI] = 5.8–16.6), have symptoms that were not currently resolved or resolved in 8+ days (OR = 10.6, 95%CI = 6.2–18.1), and more likely to report at least moderate impact on social (OR = 54.7, 95%CI = 22.4–133.4) and work (OR = 25.4, 95%CI = 11.2–57.2) functioning. Conclusion Machine learning can be used to classify patients into unique TBI phenotypes. Further research might examine the utility of such classifications in supporting clinical diagnosis and patient recovery for this complex health condition.

Identification of sleep phenotypes in COPD using machine learning-based cluster analysis

BackgroundDisturbed sleep in patients with COPD impact quality of life and predict adverse outcomes. Research questionTo identify distinct phenotypic clusters of patients with COPD using objective sleep parameters and evaluate the associations between clusters and all-cause mortality to inform risk stratification. Study design and methodsA longitudinal observational cohort study using nationwide Veterans Health Administration data of patients with COPD investigated for sleep disorders. Sleep parameters were extracted from polysomnography physician interpretation using a validated natural language processing algorithm. We performed cluster analysis using an unsupervised machine learning algorithm (K-means) and examined the association between clusters and mortality using Cox regression analysis, adjusted for potential confounders, and visualized with Kaplan-Meier estimates. ResultsAmong 9992 patients with COPD and a clinically indicated baseline polysomnogram, we identified five distinct clusters based on age, comorbidity burden and sleep parameters. Overall mortality increased from 9.4 % to 42 % and short-term mortality (<5.3 years) ranged from 3.4 % to 24.3 % in Cluster 1 to 5. In Cluster 1 younger age, in 5 high comorbidity burden and in the other three clusters, total sleep time and sleep efficiency had significant associations with mortality. InterpretationWe identified five distinct clinical clusters and highlighted the significant association between total sleep time and sleep efficiency on mortality. The identified clusters highlight the importance of objective sleep parameters in determining mortality risk and phenotypic characterization in this population.

Identification of spatial clusters of potentially toxic elements in different soil types using unsupervised machine learning and compositional data analysis

Soil health is an important concept and the generation of soil chemical composition data, including potentially toxic elements (PTEs) is one of its conceptual components. This study aims to reveal the spatial distribution patterns of soil PTEs contents, identify their potential sources, and unveil their geochemical associations in Aragatsotn region (Armenia). For that purpose, the contents of Cr, V, Ti, As, Zn, Cu, Co, Fe, Mn, Ba, and Pb were determined using the X-ray fluorescence spectrometer (Innov X-5000). The results showed that mean contents of Cr and As exceeded their upper continental crust by 1.50 and 3.12 times and their maximum acceptable values by1.53, 1.50 times, respectively. The detailed analysis of the spatial distribution pattern of PTEs demonstrated the presence of sites where all these elements displayed comparatively higher values. The combined application of compositional data analysis and geospatial mapping allowed to reveal multivariate outliers which were located in structural-metallogenic zones with an active exploitation of ore deposits. The application of unsupervised machine learning algorithm unveiled three groups within the main dataset and the clr-biplot identified the source-specific elements. Particularly, Group I included Cu and displayed the highest mean value among the identified groups. The soil samples included in Group I were found in areas where Calcisols were developed and comparatively high Cu contents were attributed to agricultural activities (vineyards) and vehicle emissions. The Group II is represented by the geochemical association of Fe, Co, Cr, Mn, Zn, and As. The formation of this group is conditioned by volcanic rocks of the local geological origin. However, no spatial pattern was identified in Group II distribution aligned with the soil types. The Group III included Ti, V, Pb, and Ba. This group may have a mixed origin as it is spatially distributed in areas where regional highways pass through and where Group II elements also exhibit their higher values.

Walleye (Sander vitreus, Mitchill 1818) age and sex classification using innovative supervised and unsupervised machine learning and soft computing methodologies

Walleye (Sander vitreus) is a freshwater perciform native to Northern America and Canada with high commercial value. Stocking programs for the species are unable to supply the significant demand, creating stock management problems and an ecosystemic decline. For sustainable fisheries, the age and sex estimation are fundamental to marine stock management. Biological methods for age determination and sex estimation were used in the past, conventional observations and techniques are substituted with machine learning methods, currently underused. The aim of this study is to evaluate the performance of an ensemble of Machine Learning (ML) methods for age and sex classification of walleye. Based on the performance of the ensemble models, appropriate evaluation decides on the age criterion with near optimal performance using supervised and unsupervised ML algorithms on the given fish datasets. The innovation of this work lies in the fact that the species age or sex estimation is based on a paramount involvement of models that diminish the proprietary idiosyncrasies of individual methods on specific datasets. For the same models two approaches were used: applied model algorithms developed both in R and Python (Orange Rapid Application Development environment) programming language provided high accuracy percentages. Among all methodologies, the Decision Tree method provided the best classification, for age estimation with 96% and 98% accuracy using the R and Orange models respectively. For the sex classification, Random Forest performed the best using the R-model with 94% accuracy, outperformed by the AdaBoost model in Orange with 97.6% accuracy. When compared, the models which were developed in Python generally performed better than the corresponding R-models both in age and sex classification. Overall, the proposed ML approach is emphasized as a rapid economic solution to standard fish classification with high accuracy, and thus could be integrated in stock assessment for a more sustainable aquaculture management.

Machine Learning to Enhance the Detection of Terrorist Financing and Suspicious Transactions in Migrant Remittances

Migrant remittances have become significant in poverty alleviation and microeconomic development in low-income countries. However, the ease of conducting global migrant remittance transfers has also introduced the risk of misuse by terrorist organizations to quickly move and conceal operational funds, facilitating terrorism financing. This study aims to develop an unsupervised machine learning algorithm capable of detecting suspicious financial transactions associated with terrorist financing in migrant remittances. To achieve this goal, a structural equation model (SEM) and an outlier detection algorithm were developed to analyze and identify suspicious transactions among the financial activities of migrants residing in Belgium. The results show that the SEM model classifies a significantly high number of transactions as suspicious, making it prone to detecting false positives. Finally, the study developed an ensemble outlier detection algorithm that comprises an isolation forest (IF) and a local outlier factor (LOF) to detect suspicious transactions in the same dataset. The model performed exceptionally well, being able to detect over 90% of suspicious transactions.

Empirically derived symptom profiles in adults with attention-Deficit/hyperactivity disorder: An unsupervised machine learning approach

Background Attention-deficit/hyperactivity disorder (ADHD) is associated with various cognitive, behavioral, and mood symptoms that complicate diagnosis and treatment. The heterogeneity of these symptoms may also vary depending on certain sociodemographic factors. It is therefore important to establish more homogenous symptom profiles in patients with ADHD and determine their association with the patient’s sociodemographic makeup. The current study used unsupervised machine learning to identify symptom profiles across various cognitive, behavioral, and mood symptoms in adults with ADHD. It was then examined whether symptom profiles differed based on relevant sociodemographic factors. Methods Participants were 382 adult outpatients (62% female; 51% non-Hispanic White) referred for neuropsychological evaluation for ADHD. Results Employing Gaussian Mixture Modeling, we identified two distinct symptom profiles in adults with ADHD: “ADHD-Plus Symptom Profile” and “ADHD-Predominate Symptom Profile.” These profiles were primarily differentiated by internalizing psychopathology (Cohen’s d = 1.94-2.05), rather than by subjective behavioral and cognitive symptoms of ADHD or neurocognitive test performance. In a subset of 126 adults without ADHD who were referred for the same evaluation, the unsupervised machine learning algorithm only identified one symptom profile. Group comparison analyses indicated that female patients were most likely to present with an ADHD-Plus Symptom Profile (χ2 = 5.43, p < .001). Conclusion The machine learning technique used in this study appears to be an effective way to elucidate symptom profiles emerging from comprehensive ADHD evaluations. These findings further underscore the importance of considering internalizing symptoms and patients’ sex when contextualizing adult ADHD diagnosis and treatment.

Towards Enhanced Security: An improved approach to Phishing Email Detection

Email phishing assaults remain a widespread catastrophe to individuals and businesses, using human weaknesses to obtain unauthorised access to sensitive information. This research study presents an upgraded email phishing detection system that uses machine learning approaches. To construct a robust and adaptable model, the system includes a complete feature set such as email content analysis, sender reputation, and behavioural patterns. The one that has been proposed uses a new combination of supervised and unsupervised machine learning algorithms to analyse email properties and user behaviour, allowing for the detection of subtle phishing signs. The term of body content analysis, URL analysis, and QR code information are among the features retrieved and analysed utilising advanced natural language processing and pattern recognition algorithms. Novelty lies in the integration of supervised and unsupervised machine learning algorithms to identify subtle phishing indicators, along with advanced natural language processing and pattern recognition algorithms for analyzing email properties. A benchmark dataset is used for the proposed system's validation, and a comparison with other phishing detection techniques shows improved, lower false-positive rates. The results indicate the system's ability to effectively discern phishing emails while minimizing the impact on legitimate communication. The system demonstrates a notable improvement by including a diverse range of features and state-of-the-art machine learning algorithms, which makes it a valuable asset to the cybersecurity toolkit for safeguarding email correspondence.

Unveiling the hub genes in the SIGLECs family in colon adenocarcinoma with machine learning.

Despite the recognized roles of Sialic acid-binding Ig-like lectins (SIGLECs) in endocytosis and immune regulation across cancers, their molecular intricacies in colon adenocarcinoma (COAD) are underexplored. Meanwhile, the complicated interactions between different SIGLECs are also crucial but open questions. We investigate the correlation between SIGLECs and various properties, including cancer status, prognosis, clinical features, functional enrichment, immune cell abundances, immune checkpoints, pathways, etc. To fully understand the behavior of multiple SIGLECs' co-evolution and subtract its leading effect, we additionally apply three unsupervised machine learning algorithms, namely, Principal Component Analysis (PCA), Self-Organizing Maps (SOM), K-means, and two supervised learning algorithms, Least Absolute Shrinkage and Selection Operator (LASSO) and neural network (NN). We find significantly lower expression levels in COAD samples, together with a systematic enhancement in the correlations between distinct SIGLECs. We demonstrate SIGLEC14 significantly affects the Overall Survival (OS) according to the Hazzard ratio, while using PCA further enhances the sensitivity to both OS and Disease Free Interval (DFI). We find any single SIGLEC is uncorrelated to the cancer stages, which can be significantly improved by using PCA. We further identify SIGLEC-1,15 and CD22 as hub genes in COAD through Differentially Expressed Genes (DEGs), which is consistent with our PCA-identified key components PC-1,2,5 considering both the correlation with cancer status and immune cell abundance. As an extension, we use SOM for the visualization of the SIGLECs and show the similarities and differences between COAD patients. SOM can also help us define subsamples according to the SIGLECs status, with corresponding changes in both immune cells and cancer T-stage, for instance. We conclude SIGLEC-1,15 and CD22 as the most promising hub genes in the SIGLECs family in treating COAD. PCA offers significant enhancement in the prognosis and clinical analyses, while using SOM further unveils the transition phases or potential subtypes of COAD.

Experimental study and acoustic emission monitoring on damage mechanism of stud shear connectors

Stud shear connectors are popular connectors used in steel-concrete composite structures. Assessing the condition and damage process of studs embedded in concrete is difficult. This paper proposes to assess the condition and damage process of stud shear connectors using an acoustic emission (AE) technique. Nine steel-concrete push-out specimens with stud shear connectors were tested, and AE sensors were used to monitor the damage process and explore the damage mechanism. The test results showed that the specimens failed due to stud fracture, accompanied by concrete cracks. The damage process included three primary stages featuring different characteristics of AE energy. An unsupervised machine learning algorithm called fuzzy C-means clustering was used to analyze the AE signals, and AE events were classified into three clusters, and various damage modes (i.e., concrete cracks and steel-concrete interface debonding, stud fracture, and concrete crushing) were identified based on the parameter characteristics and positions of AE events.

Characterizing multimorbidity in ALIVE: Comparing single and ensemble clustering methods.

Multimorbidity, defined as having 2 or more chronic conditions, is a growing public health concern, but research in this area is complicated by the fact that multimorbidity is a highly heterogenous outcome. Individuals in a sample may have a differing number and varied combinations of conditions. Clustering methods, such as unsupervised machine learning algorithms, may allow us to tease out the unique multimorbidity phenotypes. However, many clustering methods exist and choosing which to use is challenging because we do not know the true underlying clusters. Here, we demonstrate the use of 3 individual algorithms (partition around medoids, hierarchical clustering, and probabilistic clustering) and a clustering ensemble approach (which pools different clustering approaches) to identify multimorbidity clusters in the AIDS Linked to the Intravenous Experience cohort study. We show how the clusters can be compared based on cluster quality, interpretability, and predictive ability. In practice, it is critical to compare the clustering results from multiple algorithms and to choose the approach that performs best in the domain(s) that aligns with plans to use the clusters in future analyses.

Decoding Student Success in Higher Education: A Comparative Study on Learning Strategies of Undergraduate and Graduate Students

&#x0D; &#x0D; Learning management systems (LMS) provide a rich source of data about the engagement of students with courses and their materials that tends to be underutilized in practice. In this paper, we use data collected from the LMS to uncover learning strategies adopted by students and compare their effectiveness. Starting from a sample of over 11,000 enrollments at a Portuguese information management school, we extracted features indicative of self-regulated learning (SRL) behavior from the associated interactions. Then, we employed an unsupervised machine learning algorithm (k-means) to group students according to the similarity of their patterns of interaction. This process was conducted separately for undergraduate and graduate students. Our analysis uncovered five distinct learning strategy profiles at both the undergraduate and graduate levels: 1) active, prolonged and frequent engagement; 2) mildly frequent and task-focused engagement; 3) mildly frequent, mild activity in short sessions engagement; 4) likely procrastinators; and 5) inactive. Mapping strategies with the students' final grades, we found that students at both levels who accessed the LMS early and frequently had better outcomes. Conversely, students who exhibited procrastinating behavior had worse end-of-course grades. Interestingly, the relative effectiveness of the various learning strategies was consistent across instruction levels. Despite the LMS offering an incomplete and partial view of the learning processes students employ, these findings suggest potentially generalizable relationships between online student behaviors and learning outcomes. While further validation with new data is necessary, these connections between online behaviors and performance could guide the development of personalized, adaptive learning experiences.&#x0D; &#x0D;

Takotsubo syndrome outcomes predicted by thyroid hormone signature: insights from cluster analysis of a multicentre registry

Recently, abnormal thyroid function was shown to be common in patients with Takotsubo syndrome (TTS), being classified into "endocrine-type" and "stress-type" responses. The aim of this study was to investigate the association between thyroid homeostasis and TTS in a larger international registry. In total 288 patients with TTS were enrolled through the GEIST multicentre registry from Germany, Italy and Spain. Thyrotropin (TSH), free T4 (FT4) and free T3 (FT3) concentrations were analysed at admission. Data were collected both retrospectively and prospectively from 2017 onwards. Primary endpoints included in-hospital and all-cause fatality, determined by cluster analysis using an unsupervised machine learning algorithm (k-medoids). Three clusters were identified, classifying TTS with low (TSLT), high (TSHT) and normal (TSNT) thyroid output, based on TSH and FT4 levels in relation to the median thyroid's secretory capacity (SPINA-GT). Although TSH and FT4 concentrations were similar among survivors and non-survivors, these clusters were significantly associated with patient outcomes. In the longitudinal Kaplan-Meier analysis including in- and out-of-hospital survival, the prognosis related to concentrations of TSH, FT4, and FT3 as well as SPINA-GT, deiodinase activity (SPINA-GD) and clusters. Patients in the TSHT cluster and with cardiogenic shock had a lower initial left ventricular ejection fraction (LVEF). This study suggests that thyroid hormones may impact the evolution and prognosis of TTS. The findings indicate that thyroid-derived biomarkers may help identify high-risk patients and pave the way for novel personalized and preventive therapeutic options. This research was not funded by any public, commercial, or not-for-profit agencies.

A Data-driven Approach for Planning Stock Keeping Unit (SKU) in a Steel Supply Chain

In response to the growing complexities in supply chain management, there is an imperative need for a data-driven methodology aimed at optimizing inventory allocation strategies. The purpose of this research is to enhance the efficiency of allocation and operational scheduling, particularly concerning the stock keeping units (SKUs). To achieve this, one year's operational data from a specific organization's SKUs is taken and machine learning tools are employed on the data collected. These tools are instrumental in identifying clusters of SKUs that exhibit similar behaviour. Consequently, this research offers recommendations for rational inventory allocation strategies that are finely attuned to the unique characteristics of each SKU cluster. Results obtained reveals substantial disparities between the recommended strategies for the organization's SKUs and those typically found in the literature such as same strategy cannot be used for all different types for products. This underscores the critical importance of adopting a tailored approach to supply chain management. Furthermore, the research demonstrates the remarkable efficiency of unsupervised machine learning algorithms in determining the optimal number of segments within the SKUs. The current research differentiates from others in a way that in most of the research, the holistic data-driven approach is underutilized, right from the selection of the clustering algorithm to the validation of segments.

Intrusion Detection using Network Traffic Profiling and Machine Learning for IoT

The proliferation of the Internet of Things (IoT) in various sectors, including healthcare, smart cities, and industrial automation, has significantly enhanced operational efficiency and service delivery. However, this widespread adoption has introduced new vulnerabilities, making IoT networks a prime target for cyberattacks. Traditional security mechanisms often fall short in protecting IoT devices due to their limited computational resources and the unique nature of IoT network traffic. This paper introduces a novel intrusion detection system (IDS) that leverages network traffic profiling and machine learning techniques tailored for the IoT ecosystem. By analyzing the behavioral patterns of network traffic, the proposed system can accurately identify malicious activities and potential threats in real-time, ensuring the integrity and confidentiality of IoT networks. The methodology encompasses data collection, feature extraction, model training, and evaluation stages, employing a combination of supervised and unsupervised machine learning algorithms to optimize detection accuracy. Experimental results, conducted on real-world IoT network datasets, demonstrate the effectiveness of our approach in detecting a wide range of cyber threats with high precision and recall rates. This research contributes to the cybersecurity domain by providing a scalable, efficient, and adaptive IDS framework that can be integrated into various IoT infrastructures to mitigate the risk of cyber intrusions.

Systems and Computational Screening identifies SRC and NKIRAS2 as Baseline Correlates of Risk (CoR) for Live Attenuated Oral Typhoid Vaccine (TY21a) associated Protection

AimWe investigated the molecular underpinnings of variation in immune responses to the live attenuated typhoid vaccine (Ty21a) by analyzing the baseline immunological profile. We utilized gene expression datasets obtained from the Gene Expression Omnibus (GEO) database (accession number: GSE100665) before and after immunization. We then employed two distinct computational approaches to identify potential baseline biomarkers associated with responsiveness to the Ty21a vaccine. Main methodsThe first pipeline (knowledge-based) involved the retrieval of differentially expressed genes (DEGs), functional enrichment analysis, protein-protein interaction network construction, and topological network analysis of post-immunization datasets before gauging their pre-vaccination expression levels. The second pipeline utilized an unsupervised machine learning algorithm for data-driven feature selection on pre-immunization datasets. Supervised machine-learning classifiers were employed to computationally validate the identified biomarkers. Key findingsBaseline activation of NKIRAS2 (a negative regulator of NF-kB signalling) and SRC (an adaptor for immune receptor activation) was negatively associated with Ty21a vaccine responsiveness, whereas LOC100134365 exhibited a positive association. The Stochastic Gradient Descent (SGD) algorithm accurately distinguished vaccine responders and non-responders, with 88.8%, 70.3%, and 85.1% accuracy for the three identified genes, respectively. SignificanceThis dual-pronged novel analytical approach provides a comprehensive comparison between knowledge-based and data-driven methods for the prediction of baseline biomarkers associated with Ty21a vaccine responsiveness. The identified genes shed light on the intricate molecular mechanisms that influence vaccine efficacy from the host perspective while pushing the needle further towards the need for development of precise enteric vaccines and on the importance of pre-immunization screening.

Investigation of ground movements induced by underground gas storages via unsupervised ML methodology applied to InSAR data

The research explores the definition, formalization, and validation of a sound and rigorous methodology for analyzing a vast amount of satellite-based measures to geo-localize and quantify the ground movements induced by the storage of natural gas in underground formations. Time series decomposition analysis and unsupervised machine learning algorithms (partitive and hierarchical clustering) are adopted for processing, categorizing, and interpreting ground vertical movements from InSAR acquisitions. At the surface level, storage operations induce characteristic seasonal and cyclical movements, showing uplift during the injection period and subsidence during the withdrawal one. Consequently, the analysis of the solely sinusoidal component of the vertical movements (obtained via the time-series decomposition) turns out to be the key aspect of the proposed approach for handling the superposition of different ground movement sources, and consequently for clearly and reliably identifying the effects of underground gas storage (UGS) only.The proposed methodology was validated using two independent case studies in the Po Plain (northern Italy), a highly urbanized area affected by ground movements induced by several natural and anthropogenic causes, including underground gas storage facilities. For each case study, the methodology localizes one well-defined and confined area as the most affected by storage operations: this area corresponds to a cluster characterized by a high cohesion and by a seasonality phase coherent with the storage injection/withdrawal periods. The other clusters group areally wide-spread measurement points; the phase of their sinusoidal curves shows no time-coherency (or even phase opposition) with the seasonal storage operations. The results were verified via available independent information about the storage locations and were compared with the findings of previous research.

Application of machine learning for identification of heterotic groups in sunflower through combined approach of phenotyping, genotyping and protein profiling

Application of machine learning in plant breeding is a recent concept, that has to be optimized for precise utilization in the breeding program of high yielding crop plants. Identification and efficient utilization of heterotic grouping pattern aided with machine learning approaches is of utmost importance in hybrid cultivar breeding as it can save time and resources required to breed a new plant hybrid/variety. In the present study, 109 genotypes of sunflower were investigated at morphological, biochemical (SDS-PAGE) and molecular levels (through micro-satellites (SSR) markers) for heterotic grouping. All the three datasets were combined, scaled, and subjected to unsupervised machine learning algorithms, i.e., Hierarchical clustering, K-means clustering and hybrid clustering algorithm (hierarchical + K-means) for assessment of efficiency and resolution power of these algorithms in practical plant breeding for heterotic grouping identification. Following the application of machine learning unsupervised clustering approach, two major groups were identified in the studied sunflower germplasm, and further classification revealed six smaller classes in each major group through hierarchical and hybrid clustering approach. Due to high resolution, obtained in hierarchical clustering, classification achieved through this algorithm was further used for selection of potential parents. One genotype from each smaller group was selected based on the maximum seed yield potential and hybridized in a line  ×  tester mating design producing 36 F1 cross combinations. These F1s along with their parents were studied in open field conditions for validating the efficacy of identified heterotic groups in sunflowers genetic material under study. Data for 11 agronomic and qualitative traits were recorded. These 36 F1 combinations were tested for their combining ability (General/Specific), heterosis, genotypic and phenotypic correlation and path analysis. Results suggested that F1 hybrids performed better for all the traits under investigation than their respective parents. Findings of the study validated the use of machine learning approaches in practical plant breeding; however, more accurate and robust clustering algorithms need to be developed to handle the data noisiness of open field experiments.

Searching for local features in primordial power spectrum using genetic algorithms

Abstract We present a novel methodology for exploring local features directly in the primordial power spectrum using a genetic algorithm (GA) pipeline coupled with a Boltzmann solver and Cosmic Microwave Background data (CMB). After testing the robustness of our pipeline using mock data, we apply it to the latest CMB data, including Planck 2018 and CamSpec PR4. Our model-independent approach provides an analytical reconstruction of the power spectra that best fits the data , with the unsupervised machine learning algorithm exploring a functional space built off simple ‘grammar’ functions. We find significant improvements upon the simple power-law behaviour, by Δχ2 ≲ −21, consistently with more traditional model-based approaches. These best-fits always address both the low-ℓ anomaly in the TT spectrum and the residual high-ℓ oscillations in the TT, TE and EE spectra. The proposed pipeline provides an adaptable tool for exploring features in the primordial power spectrum in a model-independent way, providing valuable hints to theorists for constructing viable inflationary models that are consistent with the current and upcoming CMB surveys.

Spectroscopic Confirmation of Obscured AGN Populations from Unsupervised Machine Learning

We present the result of a spectroscopic campaign targeting active galactic nucleus (AGN) candidates selected using a novel unsupervised machine-learning (ML) algorithm trained on optical and mid-infrared photometry. AGN candidates are chosen without incorporating prior AGN selection criteria and are fainter, redder, and more numerous, ∼340 AGN deg−2, than comparable photometric and spectroscopic samples. In this work, we obtain 178 rest-optical spectra from two candidate ML-identified AGN classes with the Hectospec spectrograph on the MMT Observatory. We find that our first ML-identified group is dominated by Type I AGNs (85%) with a <3% contamination rate from non-AGNs. Our second ML-identified group is mostly comprised of Type II AGNs (65%), with a moderate contamination rate of 15% primarily from star-forming galaxies. Our spectroscopic analyses suggest that the classes recover more obscured AGNs, confirming that ML techniques are effective at recovering large populations of AGNs at high levels of extinction. We demonstrate the efficacy of pairing existing WISE data with large-area and deep optical/near-infrared photometric surveys to select large populations of AGNs and recover obscured growth of supermassive black holes. This approach is well suited to upcoming photometric surveys, such as Euclid, Rubin, and Roman.