Unsupervised Learning Algorithm Research Articles

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.

Predicting UPDRS in Parkinson’s disease using ensembles of self-organizing map and neuro-fuzzy

Parkinson's Disease (PD) is a complex, degenerative disease that affects nerve cells that are responsible for body movement. Artificial Intelligence (AI) algorithms are widely used to diagnose and track the progression of this disease, which causes symptoms of Parkinson's disease in its early stages, by predicting the results of the Unified Parkinson's Disease Rating Scale (UPDRS). In this study, we aim to develop a method based on the integration of two methods, one complementary to the other, Ensembles of Self-Organizing Map and Neuro-Fuzzy, and an unsupervised learning algorithm. The proposed method relied on the higher effect of the variables resulting from the analysis of the initial readings to obtain a correct and accurate preliminary prediction. We evaluate the developed approach on a PD dataset including speech cues. The process was evaluated with root mean square error (RMSE) and modified R square (modified R2). Our findings reveal that the proposed method is effective in predicting UPDRS outcomes by a combination of speech signals (measures of hoarseness). As the preliminary results during the evaluation showed numbers that proved the worth of the proposed method, such as UPDRS = 0.955 and RMSE approximately 0.2769 during the prediction process.

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.

Optimal heterogeneous domain adaptation for text classification in transfer learning

The prime challenge of unsupervised symmetric heterogeneous cross-domain adaptation is to train the source domain and apply the trained knowledge to the target domain. Most of the existing algorithms for unsupervised transfer learning create the subspace of the source domain features and target domain features for training purposes. It is an extensive computational process as most of the techniques require labeled source data. Many techniques also suffer from the loss of originality of features in both domains. This paper aims to consider the feature vectors of both the source and target domain for training the data based on the similarity of exemplar (feature) vectors of different instances, known as Instance Similarity Feature (ISF). The use of vectorization method for the similarity of features is proposed in this paper. The exemplar vectors are chosen randomly for the target datasets. Hence, to acquire relevant factual data in the knowledge base for training in our research, we worked to increase the domain separation error between source and target instances. To avoid the instability caused due to poor exemplar vector selection, the K-means clustering approach is followed after feature similarity, known as K-means Instance Similarity Feature (KISF). Many existing transfer learning techniques are based on the original feature set, which can cause degeneracy, hence affecting Accuracy. In order to vanquish the limitations of existing approaches, we have introduced novel optimal models with KISF and Ant Lion Optimizer (KISFA), KISF with Particle Swarm Optimization (KISFP) and KISF with Biogeography Based Optimization (KISFB). High-dimensionality can impact efficacy of the model, hence, feature selection with nature-based optimizer namely: Ant Lion Optimizer, Particle Swarm Optimization and Biogeography-Based Optimization are applied. We measure the performance of the proposed models by using Support Vector Machine, Logistic Regression, Random Forest, Naive Baye’s, K-Nearest Neighbor and Decision Tree as classifiers, and Accuracy and F1-score as fitness functions. Extensive experiments are performed on four datasets with 50 iterations. The proposed model is compared with eleven other techniques and our technique outperforms all other techniques in average Accuracy. The validation is performed on the dataset using 10-fold cross-validation. The statistical test was performed using ANOVA, proving that our technique is significantly better than other techniques.

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


 
 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.
 

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.

Planning, Design, and Execution of a Quantum Incremental Clustering Algorithm System for the Examination of Unsupervised Data

The exponential growth of data in various domains has underscored the need for efficient unsupervised learning algorithms to discover hidden patterns and structures within large datasets. Traditional clustering algorithms often face challenges in handling dynamic datasets and require periodic retraining, making them less suitable for real-time applications. In response to these challenges, this research introduces a Quantum Incremental Clustering Algorithm System (QICAS) designed to adapt to evolving datasets and provide timely insights into the underlying structures. The proposed QICAS is based on quantum computing principles, leveraging the unique properties of qubits and quantum superposition to perform clustering tasks more efficiently than classical counterparts. The research focuses on the planning, design, and execution of the QICAS, ensuring a comprehensive understanding of the algorithm's capabilities and performance.

Resource efficiency awareness of companies

Aim: This paper aims to identify the characteristic variables that influence firms’ resource efficiency awareness and subsequently group countries based on the similarities of these influencing factors. Design / Research methods: We utilize data from the GESIS Data Archive and Flash Eurobarometer, which conducted a survey in 2017 across 36 European countries and the United States of America. Machine learning tools are applicable to the analysis. Specifically, the Chi-squared independence test is applied to determine the impact of characteristic variables on resource efficiency awareness. Following this, unsupervised learning (clustering) algorithms are used to identify countries that exhibit similar patterns. Conclusions/findings: The findings reveal that turnover performance over the past two years and last year's turnover significantly influence firms’ resource efficiency awareness, while factors such as employee number of the company, one-person company or not (sole proprietorship), and the establishment year of the company do not seem to have a notable effect. The impact of the customer profile of the firm on resource efficiency awareness remains uncertain. Based on these dependency results, the study identifies ten potential clusters of countries with similar characteristics in terms of resource efficiency awareness and related factors. Originality/value of the article: Machine learning methods are relatively novel approaches that have gained prominence with the rise of extensive datasets. As a result, the paper exhibits originality in terms of research methodology. Furthermore, when considering resource efficiency as a significant topic, the article holds considerable importance. Implications of the research (if applicable): Utilizing the findings of the paper, it becomes possible to develop an application suitable for an Erasmus project. Given that resource efficiency is one of Erasmus’ critical focal points in 2023, the likelihood of approval is considerably elevated. Keywords: Energy, Resource Efficiency, Machine Learning. JEL: F64, C55

Attention non-negative spectral clustering

Deep spectral clustering is an advanced unsupervised deep learning method with widespread applications. However, when applied to large-scale datasets, it may confront problems such as an unstable training process, limited scalability, and diminished interpretability. To mitigate these limitations, a novel unsupervised deep learning algorithm named Attention Non-negative Spectral Clustering (ANSC) is proposed. Specifically, a network architecture called the Spectral Attention Network (SAN) is designed to serve as the backbone network for ANSC. This design aims to improve the stability of the training process and the model’s scalability. This attention-based network architecture includes a feature extraction network, an eigenvector mapping network, and an orthogonalization module. Furthermore, to enhance the interpretability of ANSC, the objective function incorporates a cluster indicator matrix by introducing non-negative constraints. Additionally, the ℓ2,1-norm is employed as regularization to approximate the solution of the objective function. An analysis of a lower bound for the network size of ANSC is conducted based on the VC dimension. Extensive experiments validate that ANSC outperforms state-of-the-art clustering methods in terms of clustering accuracy, normalized mutual information, and adjusted rand index.

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.

Research on automotive scrap metal classification method using laser-induced breakdown spectroscopy and two-step clustering algorithm

In the recycling of scrap metal, the establishment of the classification database of recyclables has the advantages of fast classification speed and high analysis accuracy. However, the classification and recycling of unknown samples become highly significant due to the extensive variety of standard metal samples and the challenges in obtaining them. In this study, a method for multi-element classification of automotive scrap metals in general environmental conditions was achieved by utilizing laser-induced breakdown spectroscopy (LIBS) and two-step clustering algorithm (K-means, hierarchical clustering). The two unsupervised learning algorithms were employed to cluster the LIBS spectral data of 60 automotive scrap metal samples rapidly and hierarchically. Three rare metal elements and three elements for distinguishing metal categories were selected to meet the recycling requirements. After applying the multiplicative scatter correction to the spectral data for calibration, the initial clustering clusters were determined using the Davies–Bouldin index, Calinski–Harabasz index, and silhouette coefficient. Then, the Kruskal–Wallis test was conducted on each cluster to check the significance. The clusters that failed the test were split and reclustered until all clusters met the significance criterion (α=0.05). The accuracy of the proposed method for classifying the collected automotive scrap metals reached 97.6%. This indicates the great potential of this method in the field of automotive scrap metal classification.

Continual Learning in an Open and Dynamic World

Building autonomous agents that can process massive amounts of real-time sensor-captured data is essential for many real-world applications including autonomous vehicles, robotics and AI in medicine. As the agent often needs to explore in a dynamic environment, it is thus a desirable as well as challenging goal to enable the agent to learn over time without performance degradation. Continual learning aims to build a continual learner which can learn new concepts over the data stream while preserving previously learnt concepts. In the talk, I will survey three pieces of my recent research on continual learning (i) supervised continual learning, (ii) unsupervised continual learning, and (iii) multi-modal continual learning. In the first work, I will discuss a supervised continual learning algorithm called MEGA which dynamically balances the old tasks and the new task. In the second work, I will discuss unsupervised continual learning algorithms which learn representation continually without access to the labels. In the third work, I will elaborate an efficient continual learning algorithm that can learn multiple modalities continually without forgetting.

Multi-step modeling of well logging data combining unsupervised and deep learning algorithms for enhanced characterization of the Quaternary aquifer system in Debrecen area, Hungary

In this research, a multi-step modeling approach is followed using unsupervised and deep learning algorithms to interpret the geophysical well-logging data for improved characterization of the Quaternary aquifer system in the Debrecen area, Hungary. The Most Frequent Value-Assisted Cluster Analysis (MFV-CA) is used to map lithological variations within the aquifer system. Additionally, the Csókás method is used to discern both vertical and horizontal fluctuations in hydraulic conductivity. MFV-CA is introduced to cope with the limitation of the conventional Euclidean distance-based k-means clustering known for its low resistance to outlying values, resulting in deformed cluster formation. However, the computational time and demands of MFV-CA are evident, making them costly and time-consuming. As a result, Deep Learning (DL) methods are suggested to provide fast characterization of the groundwater aquifers. These methods include Multi-Layer Perceptron Neural Networks (MLPNN), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM), which are implemented for classification and regression. The classification categorized the inputs into three distinct lithologies trained initially by the results of MFV-CA. At the same time, the regression model offered a continuous estimations of hydraulic conductivity trained by the results of the Csókás model. The results demonstrated significant compatibility between the outcomes derived from the clustering and Csókás approaches and DL algorithms. Accordingly, the lithofacies and hydraulic conductivity variations across the main hydrostratigraphical units are mapped. This integration enhanced the understanding of the groundwater system, offering promising inputs for groundwater and development and management.

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 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.

Computational thematics: comparing algorithms for clustering the genres of literary fiction

What are the best methods of capturing thematic similarity between literary texts? Knowing the answer to this question would be useful for automatic clustering of book genres, or any other thematic grouping. This paper compares a variety of algorithms for unsupervised learning of thematic similarities between texts, which we call “computational thematics”. These algorithms belong to three steps of analysis: text pre-processing, extraction of text features, and measuring distances between the lists of features. Each of these steps includes a variety of options. We test all the possible combinations of these options. Every combination of algorithms is given a task to cluster a corpus of books belonging to four pre-tagged genres of fiction. This clustering is then validated against the “ground truth” genre labels. Such comparison of algorithms allows us to learn the best and the worst combinations for computational thematic analysis. To illustrate the difference between the best and the worst methods, we then cluster 5000 random novels from the HathiTrust corpus of fiction.

Anomaly detection in multivariate time series of drilling data

Different clusters of abnormal activities often arise within same temporal domain of drilling operations. This contrasts with employing simplified scenarios, such as anomaly detection models for specific issues like stuck pipe or loss circulation. The dynamic nature of drilling environments demands a holistic framework that can adapt to evolving conditions and detect anomalies beyond predefined categories. There exists a need to evaluate the performance of various data-driven models and achieve a broader applicability of anomaly detection instead of focusing on a single abnormal activity type. This study presents a generalized framework designed to detect anomalous events in drilling operations. Three different unsupervised learning algorithms, principal component analysis (PCA), isolation forest (IF) and lstm-autoencoder (LSTM-AE), are used to determine abnormal patterns and irregularities in the drilling data. PCA is chosen for its interpretability and efficiency in handling high-dimensional data by reducing the dimensionality. IF is selected for its effectiveness in isolating anomalies, making it robust for scenarios where anomalies exhibit distinct patterns. LSTM-AE is employed due to its capability to capture temporal dependencies and nonlinear patterns in time series data. A multivariate time series of drilling data from an offshore well is collected to use in this work. The dataset comprises approximately six months of drilling operations, including drilling and non-drilling periods. The input variables are chosen from the common controllable parameters continuously monitored by the drilling crew. The pre-processed drilling data with input features is organized into groups based on each drilling section. These unlabeled data is split into train, validation and test sets. Cross-validation (CV) is applied into train and validation sets to prevent overfitting and tune the hyperparameters. The test data is used to evaluate the generalizability and robustness of each model. Evaluation metrics such as precision, recall, F1 score, and receiver operating characteristic (ROC) curve are used to select the best-performing model. The thresholds for anomaly identification are determined by analyzing the reconstruction errors from PCA and LSTM-AE models, as well as anomaly scores from the IF algorithm. Subsequently, evaluation metrics are calculated using these thresholds, assigning true and false predictions to each data point. These predictions are then compared with the ground truth data labels obtained from the daily reports. Experimental results show that the proposed approach can effectively predict anomalous events in drilling operations. It is observed that there is a causal link between irregularities in time series drilling data and the occurrence of anomalous events in drilling operations. Implementing the proposed approach in real-time monitoring systems may improve overall efficiency and minimize risks in drilling operations. The presented methodology can be tested with diverse drilling datasets to enhance the generalizability and reduce bias, leading to a more comprehensive and reliable assessment across various scenarios.