Anomaly Detection and Machine Learning for Stand-Level Growth and Yield Modeling in Hybrid Eucalypt Plantations

This paper compares three unsupervised machine-learning algorithms – local outlier factor (LOF), Isolation Forest (iForest) and one-class support vector machine (OCSVM) – for anomaly detection in a multivariate geochemical dataset in northeastern Iran. This area contains several Au, Cu and Pb–Zn mineral occurrences. The methodology incorporates single-element geochemistry, multivariate data analysis and application of the three unsupervised machine-learning algorithms. Principal component analysis unveiled diverse elemental associations for the first seven principal components (PCs): PC1 shows a Co–Cr–Ni–V–Sn association indicating a lithological influence; PC2 shows a Au–Bi–Cu–W association suggesting epithermal Au mineralization; PC3 shows variability in Zn–V–Co–Sb–Cu–Cr; PC4 shows a Au–Cu–Ba–Sr–Ag association indicating Au and polymetallic mineralization; PC5 reflects Zn–Ag–Ni–Pb related to hydrothermal mineralization; and PC6 and PC7 show element associations suggesting epithermal and intrusive-related polymetallic mineralization. It was found that OCSVM performed slightly better than LOF and iForest in detecting anomalies associated with known Cu occurrences, and it successfully delineated dispersion from all known Au occurrences. LOF outperformed iForest and OCSVM in identifying all four Pb–Zn occurrences, and the three methods substantially limited the areas of the anomaly class. The analysis showed that LOF produced a less cluttered anomaly map compared to the isolated patterns in the iForest map. LOF was accurate in identifying anomalies associated with Au–Pb mineralization, while iForest detected anomalies associated with Pb–Zn–Cu occurrences and neighbouring Pb–Zn occurrence. OCSVM performed similarly in the northern and western areas but displayed unique discrepancies in the SE and west by detecting anomalies associated with two Cu occurences and a Pb–Cu occurrence. This study examined the influence of contamination fraction on detection of geochemical anomalies, revealing a noteworthy rise in the count of mineral occurrences delineated by anomalies when the contamination fraction increases from 5 to 10%. However, even with a 35% contamination fraction, some Cu occurrences remained outside the anomaly category, indicating potentially overlooked geochemical signals from mineral occurrences due to sampling schemes.

In Indonesia, large earthquakes happen frequently. Due to the location of Indonesia, over three active tectonic plates, fractures and trenches have formed on both the land and ocean floor. Over 1,250 large earthquake occurrences have occurred in Indonesia during the past 120 years, beginning in 1900. Based on data from the BMKG (Indonesian non-departmental government organization for meteorology, climatology, and geophysics) official website, up to 12,351 earthquakes occurred in Indonesia in 2021. Not every earthquake was fatal; many of them were considered common. In this work, the author compares Elliptic Envelope, Isolation Forest, One-Class SVM, and Local Outlier Factor. 4 types of anomaly detection algorithms to locate earthquakes whose status is abnormal or out of the ordinary utilizing outliers. The application of anomaly detection for each algorithm will be tested in two ways; the first test will only use the default parameters, and the second test will use the parameter (Tuning Hyperparameters) at the contamination/nu parameter of 0.025 or 2.5%. Contamination/nu is a value that indicates the amount of data considered an anomaly—Accuracy, Recall, Precision, F1-Score, AUC, and Specificity. Experiments have shown that Isolation Forest has a higher value than all other experiments in detecting anomalous status in earthquakes. In comparing performance using default parameters, Isolation Forest had a precision of 13.02%, recall (sensitivity) of 99.35%, specificity of 82.80%, accuracy of 83.24%, AUC of 91.08%, and F1-score of 23.03%. After tuning the hyperparameters, the performance of each model increased, with Isolation Forest had a precision of 37.21%, recall (sensitivity) of 36.85%, specificity of 98.41%, accuracy of 98.42%, AUC of 67.63%, and F1-score of 37.03%.

The core aim of this study is to determine the most effective outlier detection methodologies for multivariate psychological datasets, particularly those derived from Omani students. Due to their complex nature, such datasets demand robust analytical methods. To this end, we employed three sophisticated algorithms: local outlier factor (LOF), one-class support vector machine (OCSVM), and isolation forest (IF). Our initial findings showed 155 outliers by both LOF and IF and 147 by OCSVM. A deeper analysis revealed that LOF detected 55 unique outliers based on differences in local density, OCSVM isolated 44 unique outliers utilizing its transformed feature space, and IF identified 76 unique outliers leveraging its tree-based mechanics. Despite these varying results, all methods had a consensus for just 44 outliers. Employing ensemble techniques, both averaging and voting methods identified 155 outliers, whereas the weighted method highlighted 151, with a consensus of 150 outliers across the board. In conclusion, while individual algorithms provide distinct perspectives, ensemble techniques enhance the accuracy and consistency of outlier detection. This underscores the necessity of using multiple algorithms with ensemble techniques in analyzing psychological datasets, facilitating a richer comprehension of inherent data structures.

This study presents a comprehensive evaluation of five prominent unsupervised machine learning anomaly detection algorithms: One-Class Support Vector Machine (One-Class SVM), One-Class SVM with Stochastic Gradient Descent (SGD), Isolation Forest (iForest), Local Outlier Factor (LOF), and Robust Covariance (Elliptic Envelope). Through systematic analysis on a synthetically simulated dataset, the study assessed each algorithm’s predictive performance using accuracy, precision, recall, and F1 score specifically for outlier detection. The evaluation reveals that One-Class SVM, Isolation Forest, and Robust Covariance are more effective in identifying outliers in the synthetic simulated dataset, with Isolation Forest slightly outperforming the other algorithms in terms of balancing precision and recall. One-Class SVM with SGD shows promise in precision but needs adjustment to improve recall. Local Outlier Factor may require parameter tuning or may not be as suitable for this particular dataset’s characteristics. The findings reveal significant variations in performance, highlighting the strengths and limitations of each method in identifying anomalies. This research contributes to the field of machine learning by demonstrating that the selection of an anomaly detection algorithm should be a considered decision, taking into account the specific characteristics of the data and the operational context of its application. Future work should explore parameter optimization, the impact of dataset characteristics on model performance, and the application of these models to real-world datasets to validate their efficacy in practical anomaly detection scenarios.

Management of Scots pine ( L.) in Norway requires a forest growth and yield model suitable for describing stand dynamics of even-aged forests under contemporary climatic conditions with and without the effects of silvicultural thinning. A system of equations forming such a stand-level growth and yield model fitted to long-term experimental data is presented here. The growth and yield model consists of component equations for (i) dominant height, (ii) stem density (number of stems per hectare), (iii) total basal area, (iv) and total stem volume fitted simultaneously using seemingly unrelated regression. The component equations for stem density, basal area, and volume include a thinning modifier to forecast stand dynamics in thinned stands. It was shown that thinning significantly increased basal area and volume growth while reducing competition related mortality. No significant effect of thinning was found on dominant height. Model examination by means of various fit statistics indicated no obvious bias and improvement in prediction accuracy in comparison to existing models in general. An application of the developed stand-level model comparing different management scenarios exhibited plausible long-term behavior and we propose this is therefore suitable for national deployment.Pinus sylvestris

In Komatiland Forests (South Africa) the objectives of growth and yield research are to develop a range of empirical stand-level growth and yield models for thinned pine stands. The models are used for resource description, growth and yield predictions for the purpose of management planning and for the development of optimum stand-level management regimes. The growth and yield research programme consists of four main components, namely a field programme, long term data management, growth modelling and the development of simulation systems. For each of these components, a strategy has been developed. In the field, programme data are collected for each of the target model components from a number of sources, such as spacing trials, permanent sample plots (PSPs), silvicultural response trials, plantation inventories and destructive sampling for volume and taper data. The modelling strategy is to develop multi-component model architectures for modelling stand-level growth, namely dominant height, unthinned basal area and survival. For thinned stands, additional functions for the modelling of the basal area thinning ratio and the basal area response after thinning are required. Depending on the data, both the Chapman-Richards-type and the Schumacher-type functions are used for modelling unthinned stand-level basal area. Various methods are used for modelling basal area response after thinning, e.g. the index of suppression or the age-adjustment method. A major challenge in growth modelling is to develop models for thinned stands based on PSP data only, while conforming to the hypothesis of thinned stand growth. Stand structure is modelled using the Weibull function in conjunction with the method of moments approach for recovering the relevant Weibull parameters. Finally, the models are built into simulation systems for stand-level scenario analysis, e.g. the development of rule-based thinning and pruning systems, and also forestry scenario analysis. However, the main function of stand-level growth and yield models is still to provide for more accurate company planning systems.

Pada setiap semester dalam universitas terdapat kuisioner berupa penilaian terhadap kinerja dosen. Evaluasi kinerja dosen yang terdapat di Universitas Negeri Surabaya merupakan proses penting untuk memastikan bahwa dosen telah memenuhi tugas dan tanggung jawabnya dalam menyampaikan pendidikan berkualitas terhadap mahasiswanya. Pada penelitian ini terdapat 22 instrumen pertanyaan menggunakan Skala Likert yang diisi oleh mahasiswa untuk menilai kinerja dosen. Terdapat 1055 dosen yang diolah untuk mendeteksi bagaimana kinerja dosen apakah sesuai dengan Rancangan Pembelajaran Semeste (RPS) atau terdapat dosen yang ketika mengajar tidak sesuai RPS. Oleh karena itu, metode deteksi anomali diterapkan untuk mengetahui kinerja dosen yang menyimpang atau tidak seperti biasanya. Dengan metode tersebut, maka dapat digunakan algoritma Local Outlier Factor (LOF) dan Isolation Forest karena lebih efisien dalam menangani data yang besar dan bekerja dengan cepat dalam ruang fitur. Data yang digunakan belum terdapat label untuk menghitung sehingga digunakan metode klastering kmeans untuk memperoleh label dari LOF dan IF. Kemudian pada cluster kmeans didapatkan 3 cluster, yaitu cluster 0 terdiri dari 279 data points, cluster 1 terdiri dari 597 data points, dan cluster 2 terdiri dari 179 data points. Dari hasil cluster tersebut akan digunakan untuk memperoleh nilai dari label LOF dan label IF dalam perhitungan evaluasi hasil komparasi. Pada anomali yang diterapkan dengan algoritma LOF yaitu terdapat 19 dosen terdeteksi anomali dan pada algoritma IF terdapat 22 dosen terdeteksi anomali. Pada evaluasi yang digunakan untuk memperoleh hasil komparasi yaitu menggunakan rand index score dan silhouette score. Didapatkan nilai dari rand index dari LOF sebesar 0.438 dan IF sebesar 0.441. Kemudian hasil dari silhouette score LOF sebesar 0.0019 dan IF sebesar 0.0377. Kata Kunci : Kinerja dosen, LOF, IF, rand index, silhouette score

Abnormality detection, also known as outlier detection or novelty detection, seeks to identify data that do not match an expected distribution. In medical imaging, this could be used to find data samples with possible pathology or, more generally, to exclude samples that are normal. This may be done by learning a model of normality, against which new samples are evaluated. In this paper four methods, each representing a different family of techniques, are compared: one-class support vector machine, isolation forest, local outlier factor, and fast-minimum covariance determinant estimator. Each method is evaluated on patches of CT interstitial lung disease where the patches are encoded with one of four embedding methods: principal component analysis, kernel principal component analysis, a flat autoencoder, and a convolutional autoencoder. The data consists of 5500 healthy patches from one patient cohort defining normality, and 2970 patches from a second patient cohort with emphysema, fibrosis, ground glass opacity, and micronodule pathology representing abnormality. From this second cohort 1030 healthy patches are used as an evaluation dataset. Evaluation occurs in both the accuracy (area under the ROC curve) and runtime efficiency. The fast-minimum covariance determinant estimator is demonstrated to have a fair time scaling with dataset dimensionality, while the isolation forest and one-class support vector machine scale well with dimensionality. The one-class support vector machine is the most accurate, closely followed by the isolation forest and fast-minimum covariance determinant estimator. The embeddings from kernel principal component analysis are the most generally useful.

Credit card fraud presents a persistent threat to financial institutions, exacerbated by the rise of digital payments and the complexity of ‎fraudulent schemes. This study investigates machine learning (ML) approaches for fraud detection in severely imbalanced datasets, focusing ‎on three key objectives: comparing classification and anomaly detection models under extreme class imbalance, identifying transaction ‎features with the highest discriminative power, and optimizing decision thresholds using cost-sensitive evaluation to minimize business ‎impact. Utilizing a dataset of 999 transactions with a fraud rate of 0.2% (498.5:1 imbalance), we implemented supervised methods (logistic ‎regression, random forest, gradient boosting) and unsupervised anomaly detection (Isolation Forest, One-Class SVM, Local Outlier ‎Factor). Results show that ensemble-based models, particularly Gradient Boosting, achieved superior performance (AUC-ROC = 0.956; ‎AUC-PR = 0.378) with perfect recall and improved precision relative to other methods. Feature analysis identified anonymized PCA-‎derived variables (V14, V10, V12) as the most discriminative indicators of fraudulent activity. Threshold optimization at 0.9 minimized ‎operational costs ($2,985) while maintaining full recall, yielding an estimated annual net benefit of $68,985 and a return on investment of ‎‎186.7%. This study contributes to the literature by integrating algorithm benchmarking, feature importance evaluation, and cost-sensitive ‎threshold optimization in an end-to-end fraud detection framework. The findings underscore the importance of ensemble learning, ‎imbalanced evaluation metrics (AUC-PR, precision, recall), and business-driven threshold calibration for developing effective and ‎economically viable fraud prevention systems. Future research should explore larger datasets, adaptive learning to address concept drift, and ‎explainable AI techniques to enhance interpretability and regulatory compliance‎.

This study presents a comparative analysis of three widely adopted unsupervised anomaly detection algorithms—Isolation Forest, Local Outlier Factor (LOF), and One-Class Support Vector Machine (SVM)—with the aim of evaluating their effectiveness in detecting network intrusions. Using a publicly available cybersecurity dataset, this study applied Principal Component Analysis (PCA) to reduce dimensionality and optimize computational performance. Each model was trained exclusively on normal traffic data and was tested against mixed data containing both normal and attack instances. The performance was assessed using key metrics, including precision, recall, and F1-score, along with confusion matrices, to evaluate the classification behavior. The results indicate that the One-Class SVM achieved the best overall performance, with the highest recall (99.06%) and F1-score (0.8511), making it highly effective in detecting a broad range of attack types while maintaining a manageable false-positive rate. While Isolation Forest achieved strong precision (78.56%), it underperformed in recall, making it more suitable for applications where false positives must be minimized. LOF delivered a balanced but less robust performance owing to its higher false-alarm rate.

The growth of cyber threats and network traffic has highlighted the need for effective methods for detecting anomalies. The purpose of the study was to develop a hybrid model for detecting anomalies in telecommunications networks with increased accuracy based on comparative analysis of uncontrolled algorithms. Four main algorithms were compared: Isolation Forest, Local Outlier Factor (LOF), One-Class Support Vector Machine (SVM), and Elliptic Envelope using simulated network traffic data. Analysis methods included data normalisation using Z-score and Min-Max Scaling to eliminate large-scale differences between traits. An ensemble of 100 decision trees was used to improve the accuracy of anomaly detection. As a result, it was found that Isolation Forest provided the highest accuracy of anomaly detection (F1-Score = 85.8%) and high processing speed (processing time per 10,000 records in 2.5 seconds), which is important for real-world conditions of telecommunications networks with large amounts of data. LOF showed high accuracy in detecting local anomalies, but with greater computational complexity. The one-class SVM algorithm detected global anomalies, but showed lower accuracy for local ones. Elliptic Envelope had limited performance due to the assumption of normal data distribution. Additionally, a comprehensive model was developed that combined the advantages of Isolation Forest, LOF, and Density-Based Spatial Clustering of applications with Noise, which allowed increasing the F1-Score to 88% and exceeding the results of individual models. The hybrid model showed adaptability to multimodal distributions and efficiency in detecting local anomalies. Practical significance lies in improving the accuracy and stability of network security systems and form the basis for adaptive real-time algorithms, which allowed cybersecurity and telecommunications specialists to more effectively monitor and protect networks from threats

Objectives. The transformation of modern electric grids into decentralized smart grids presents new challenges in the field of cybersecurity. The purpose of this work is to conduct research and analysis into the effectiveness of different machine-learning methods for identifying anomalies in decentralized smart networks, including cyberattacks and emergency modes, as well as to develop recommendations on the optimal combination of these methods for ensuring effective cybersecurity under conditions of changing electrical loads.Methods. We consider several machine learning methods for identifying anomalies in power systems that simulate network behavior under conditions of cyberattacks and emergency modes. The relative effectiveness of such methods as multifractal analysis using wavelets, the Isolation Forest model, local outlier factor (LOF), k-means clustering, and one-class support vector machine (One-Class SVM), is analyzed.Results. The comparison of machine learning methods reveals the varying effectiveness of anomaly detection methods used to detect cyber threats and deviations in electrical systems. Isolation Forest is best at detecting abrupt changes related to cyberattacks with high accuracy and a minimum of false positives. While LOF can also be effective in detecting cyberattacks, its increased sensitivity to minor deviations increases the number of false positives. K-means and One-Class SVMs are less effective in detecting abrupt anomalies but are useful for general clustering of data and detecting both abrupt and smooth changes, respectively.Conclusions. The obtained research results indicate the advantages of using a combination of machine learning algorithms to ensure the reliable protection of smart networks from cyberattacks taking into account the nature of the electrical load.

BACKGROUND Patient heterogeneity is a key challenge in immunotherapy for IDH-wildtype glioblastoma (GBM), where hypermutated tumors or highly immunosuppressive tumor microenvironments (TME) act as clinical outliers affecting treatment response and trial stratification. We developed Alert-GBM, a radiogenomic AI model designed to flag such outliers based on radiomic signatures from diagnostic imaging. MATERIAL AND METHODS We used multicenter open-access radiogenomic datasets (n = 176) to train unsupervised outlier detection models. Principal Component Analysis (PCA) served as a first-pass filter to harmonize data before applying Isolation Forest (IF) modeling. Three IF models were trained using inter-dataset leave-one-out cross-validation (LOOCV) to simulate real-world performance and were benchmarked against each other. The final model was selected using stratified 10-fold cross-validation (CV). Outliers were validated through visual inspection, statistical profiling, comparison with other outlier detection methods (Local Outlier Factor, One-Class SVM, Mahalanobis distance), and correlation with biological and immune profiles from imaging and omics data. RESULTS The PCA filter identified 3 initial outliers based on MRI metadata. The final IF model, following stratified 10-fold CV, detected 6 outliers across the datasets, with anomaly scores plotted. Flagged cases included large, highly enhancing tumors, minimally enhancing tumors, and post-operative scans. Visualizations using PCA, t-SNE, and UMAP were generated to illustrate separability. False positives and negatives were assessed using immune-based scores, and the distribution of anomaly scores was analyzed with KDE plots. Cross-validation against alternative outlier models confirmed consistency of the flagged cases. CONCLUSION Alert-GBM is a proof-of-concept AI architecture for outlier detection in GBM MRI radiogenomics, capable of flagging cases with atypical immune TME profiles. Integrating such models with radiogenomic immune predictors at the time of diagnosis may support multidisciplinary decision-making and improve patient stratification for immunotherapy trials. Incorporating a human-in-the-loop framework ensures that AI outputs remain clinically interpretable and actionable.

The escalating sophistication of cyber threats necessitates advanced anomaly detection techniques that transcend traditional signature-based methods. This paper presents an automated cybersecurity framework leveraging the Isolation Forest algorithm for unsupervised anomaly detection in network traffic. Using the NSL-KDD dataset, we demonstrate that Isolation Forest achieves 95.2% detection accuracy with a 4.7% false-positive rate, outperforming conventional methods such as One-Class SVM (88.1% accuracy) and Local Outlier Factor (82.3% accuracy) in both computational efficiency and precision. Key advantages include: (1) real-time processing capability (8.2s training time, 4× faster than density-based approaches), (2) effective identification of rare attack types (U2R/R2L), and (3) elimination of dependency on labeled training data. The proposed system integrates dynamic threshold tuning and SHAP-based feature weighting to enhance detection stability and reduce false alarms. The results validate Isolation Forest as a scalable and reliable solution for modern intrusion detection systems, with strong implications for SIEM integration and real-time cybersecurity automation. Challenges in parameter tuning and encrypted traffic analysis are discussed, alongside future directions involving hybrid deep learning architectures.

For Long Term Evolution Advanced (LTE-A) network, although there exist many studies that focus on improving the performance with relays, security issues are often neglected. Due to the broadcast nature of wireless channels, relay nodes in LTE-A network may act maliciously, affect communication, reduce quality, and cause delays. Recently, physical (PHY) layer security has attracted researchers to provide secure communication and data privacy. In this study, we propose using unsupervised learning approach at the destination node to detect malicious relay attacks in cooperative LTE-A network based on received source signal in the PHY layer. Outlier detection algorithms such as one class support vector machine (OCSVM), local outlier factor (LOF) and isolation forest ( $i$ Forest) are applied to detect various malicious relay behaviors such as garbling, regenerative, and false data injection type attacks. As input to these algorithms, feature vectors are constructed by using amplitude, phase, and relative phase information of modulated baseband symbols. The performance of the outlier detectors are evaluated with respect to precision, accuracy, and under the area curve (AUC) measures under changing signal-to-noise ratio (SNR) levels, different modulation types, allocated number of resource blocks (RBs), and varying data size. The results demonstrate the effectiveness of our proposed outlier detection approach for detecting malicious relays in the LTE-A network. Accuracy and precision of the algorithms are observed to be above 90% for 10 dB and larger SNR levels for the relay attack scenarios considered here. AUC values for all algorithms for all SNR levels is also above 0.9 for the attack detection cases, and the performance of the LOF algorithm with 0.95 and above AUC values is superior to other algorithms. The results verify the contribution of this study, which is the demonstration of the effectiveness of one class outlier detection approaches for detecting malicious relays in the LTE-A network.