Constructing an Intrusion Detection Model based on Long Short-term Neural Networks

Intrusion detection plays a critical role in safeguarding computer networks from malicious activities and unauthorized access. Traditional machine learning (ML) models have been widely employed for intrusion detection, but their effectiveness can be limited due to the complex and evolving nature of network attacks. An efficient Convolutional Neural Network (CNN) that utilizes one-dimensional convolutions, batch normalization, and max pooling layers is designed to capture the attack patterns in network traffic data. By leveraging the inherent feature extraction capabilities of CNNs, the proposed architecture demonstrates improved performance in identifying network intrusions compared to traditional ML models. The effectiveness of the novel CNN architecture is evaluated by conducted comprehensive experiments on two benchmark intrusion detection datasets. The designed CNN performance was compared with four other ML models such as logistic regression, k-nearest neighbors, decision trees, and random forest. The experimental results revealed that the proposed CNN architecture outperformed the traditional ML models with highest accuracy of 97.68% and 97.39% and highest F1-score of 97.68% and 97.40% for. UNSW-NB15 and CICIDS2017 datasets, respectively. The proposed CNN architecture serves as a promising alternative to traditional ML models, offering improved performance in identifying and mitigating network attacks.

Accurate rainfall forecasting is crucial in activities such as agricultural planning, water resource management, and flood preparedness, so failure to accurately forecast rainfall might undermine these activities. This study aimed to improve the accuracy of daily rainfall prediction in Hai district, Kilimanjaro region, Tanzania, a region characterised by a bimodal rainfall pattern, by comparing rainfall prediction accuracies of Traditional Machine Learning (TML) and Deep Learning (DL) models. The 25-year daily rainfall dataset for Hai district was first pre-processed by cleaning, normalisation, and splitting into training (first 60%), validation (next 20%), and test (last 20%) sets. TML models (K-Nearest Neighbours (KNN) through its variant KNN Regressor and Support Vector Machine (SVM) through its variant Support Vector Regressor (SVR)) were developed, trained, and their performances compared with developed and trained DL models (Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU)). Each model’s test performance was evaluated using the Root Mean Squared Error (RMSE) metric. The findings revealed that the DL models, LSTM and GRU, achieved test RMSE scores of 6.35 mm and 6.49 mm, respectively, while the TML models, KNN and SVM, achieved test RMSE scores of 6.61 mm and 10.42 mm, respectively. The study demonstrated that DL models are more effective for accurate rainfall forecasting than TML models in regions with complex rainfall patterns. The insights gained will guide the development of more reliable, location-specific weather prediction systems, ultimately supporting informed decision-making in agriculture, environmental management, and flood risk reduction in Tanzania and other regions facing similar climatic challenges

The Turkish Music Emotion Dataset in the CL database is a dataset for music emotion classification, which contains many music samples and their corresponding emotion labels. This paper presents a comparative analysis of the performance of the traditional random forest machine learning model and the XGBoost model on the given dataset. The findings indicate that the traditional random forest machine learning model outperforms the XGBoost model in terms of accuracy, accuracy, and recall rate. The traditional random forest machine learning model achieves an accuracy of 80.8%, whereas the XGBoost model achieves an accuracy of 75%. The recall rate of the traditional random forest machine learning model is 80.8%, whereas the recall rate of the XGBoost model is 77.2%. The traditional random forest machine learning model achieved an F1 score of 80.5%, whereas the XGBoost model attained an F1 score of 75.3%. The comprehensive evaluation of the XGBoost model outperforms the traditional random forest machine learning model. Generally, the traditional random forest machine learning model demonstrates strong performance in the domain of music emotion classification. It exhibits favorable qualities such as robustness and interpretability, and possesses the ability to effectively handle noise and missing data. The XGBoost model, on the other hand, can be trained and predicted quickly, with high accuracy and generalization ability. Therefore, in practical application, it is necessary to select the appropriate model according to the specific situation, and optimize and adjust it to obtain the best classification effect.

Physics-supervised ensemble learning model for predicting failure modes of reinforced concrete columns

Graph theory provides a robust framework for modelling complex relationships in medical data, enhancing classification accuracy through relational learning. Unlike traditional machine learning (ML) models that treat data points independently, graph-based approaches support structural dependencies to improve feature representation. This study explores the application of Graph Attention Networks (GAT), GraphSAGE, Graph Convolutional Network(GCN) and Graph Isomorphism Network (GIN) for breast cancer classification, employing k-nearest neighbor (KNN) graphs to construct a structured dataset where nodes represent patients and edges capture feature similarities. The effectiveness of the graph-based approaches is evaluated against traditional ML classifiers, including Decision Trees, Random Forest, LightGBM, and XGBoost. Experimental results indicate that GCN, GIN, GAT and GraphSAGE are beat conventional methods, with GCN, GAT and GraphSAGE achieved 100% test-accuracy and with GIN achieved 99.42%, to confirm the percentage of accuracy, authors conducted extensive experiments, including robustness testing by reducing KNN connections, introducing noise, and shuffling train-test splits. Results demonstrate that graph-based models are significantly best than traditional ML models, and these graph-based models maintain same classification accuracy while maintaining stability under robustness tests. The findings confirm that graph-based learning provides a scalable, interpretable, and highly accurate alternative for medical classification tasks, proving its effectiveness in distinguishing between benign and malignant tumors.

This chapter is focused on a specific topic in modern machine learning, i.e., deep learning. First of all, we introduce a few fundamental aspects, including perceptron and why we need multi-layer structures, how the convolutional neural networks extract features layer by layer, the back-propagation learning algorithm, and the functional layers of convolutional neural networks. Then, we will focus on the safety and security vulnerabilities of deep learning, explaining uncertainty estimation, adversarial attack on the robustness, poisoning attack, model stealing, membership inference and model inversion. Unlike traditional machine learning models that we discussed in the previous chapters where the structure or the training algorithm of a machine learning model may be considered for the design of the attacks, most attacks for deep learning do not consider the internal structure of a deep learning model, although the gradient may be used in some cases. These black-box or grey-box attacks suggest that many of the attack algorithms for deep learning may also be applicable to traditional machine learning models, which explains why we frequently refer to algorithms in the chapter when discussing safety threads for traditional machine learning models.

The overwhelming volume of data generated online continuous to grow at an exponential and unprecedented rate. Over 80% of such data is unstructured. Scientific research publications constitute a significant portion of such unstructured data. Systematic literature review (SLR) activity is a rigorous and challenging process. The key challenge in SLR is the automatic extraction of the relevant data from the sheer volume of research publications. Lack of a unified framework has been identified as the key problem. A canonical model, based on the structure of the papers was proposed as the framework for data extraction purposes in SLR. Implemented as a classification problem, traditional machine learning models were used to realise the canonical model. A good accuracy was reported in these traditional models. However, there is room for improvement. This paper presents the result of the work on the same problem using convolutional neural network (CNN), which is more sophisticated (deeper). The results show an improvement over the traditional machine learning models with an accuracy of 85%. Unlike the previous CNN NLP works, this work also demonstrates the application of CNN on a bigger NLP dataset such as the data from the scientific research publications. The result also shows that the CNN performs even better in NLP tasks with bigger datasets.

Diabetic peripheral neuropathy (DPN) is one of the most common and debilitating complications of diabetes mellitus. Early, subclinical stages of DPN are often asymptomatic and remain undetected until significant nerve damage occurs, limiting treatment options. Artificial intelligence (AI) has emerged as a promising tool to enhance early detection by identifying subtle patterns in electrophysiological, imaging, or sensor-based data that may not be recognized by conventional diagnostic methods. However, the current landscape of AI applications in subclinical DPN remains unclear. The aim of this study was to map and synthesize the existing literature on the use of AI-based methods for the early detection of subclinical DPN. A comprehensive search of PubMed, Scopus, Web of Science, and Google Scholar was conducted up to August 25, 2025. Eligible studies included those applying AI or machine learning techniques to identify or predict subclinical DPN in patients with type 1 or type 2 diabetes. Non-English articles, studies without AI implementation, and reviews were excluded. Data were charted on study characteristics, AI methodology, dataset type, and reported outcomes. Preliminary evidence suggests that AI has been applied across multiple modalities, including nerve conduction studies, corneal confocal microscopy, wearable sensor data, and electrophysiological signals. Techniques ranged from traditional machine learning models such as support vector machines and random forests to deep learning architectures including convolutional neural networks. While several studies reported high sensitivity and accuracy for early detection, most were limited by small sample sizes, lack of external validation, and heterogeneous definitions of “subclinical” DPN. In conclusion, AI-based approaches demonstrate substantial potential for the early identification of subclinical DPN, which could enable earlier interventions and improve patient outcomes. Nonetheless, the field is still in its early stages, and robust multicenter datasets, standardized definitions, and explainable AI models are required to facilitate clinical adoption. Future research should focus on validation in diverse populations and integration into routine diabetic care pathways.

This study investigates the feasibility of using tear sample analysis, based on protein corona formation on gold nanoparticles combined with electrospray ionization mass spectrometry (ESI-MS) and machine learning techniques, as a non-invasive approach for the detection of choroidal melanoma. The aim is to assess whether protein-nanoparticle interactions can support early and reliable identification of this ocular condition. Tear samples were collected using Schirmer strips from six healthy individuals and six patients diagnosed with choroidal melanoma, with subsequent augmentation to 18 samples per group. Gold nanoparticles (AuNPs, ~ 20 nm) were synthesized via citrate reduction and incubated with tear samples to form protein coronas, which were analyzed using ESI-MS. Eight statistical and entropy-based features (mean, variance, skewness, kurtosis, Shannon entropy, approximate entropy, sample entropy, and permutation entropy) were extracted from spectral data. Additionally, Continuous Wavelet Transform (CWT) with Mexican hat wavelet was applied to convert mass spectrometry data into 128 × 128 RGB images for deep learning analysis. Classification was performed using traditional machine learning models (Random Forest, Support Vector Machine, Decision Tree, Deep Neural Network) and transfer learning with pre-trained CNNs (VGG16, ResNet50, Xception), evaluated through 5-fold cross-validation. Significant differences in spectral intensity parameters were observed between healthy individuals and choroidal melanoma patients (p < 0.001), with notably lower Mean_Intensity values in cancer patients (56.41 ± 46.06 vs. 111.02 ± 10.01, Cohen’s d = 1.64). While m/z parameters showed moderate differences that didn’t reach statistical significance (p = 0.082), entropy-based features demonstrated strong discriminative power. Among traditional machine learning models, Random Forest achieved the highest accuracy (0.959 ± 0.003) and ROC AUC (0.993 ± 0.000) with remarkable computational efficiency (3.90 s per fold). For deep learning approaches using CWT-generated images, VGG16 demonstrated superior performance (Accuracy: 0.976 ± 0.008, ROC AUC: 0.997 ± 0.002) despite requiring significantly higher computational resources (1349.52 s per fold). This study demonstrates that tear sample analysis using protein corona formation on gold nanoparticles with ESI-MS and advanced machine learning techniques offers a promising non-invasive approach for choroidal melanoma detection with performance metrics that compare favorably to existing methods. The significant differences in spectral intensity parameters between groups suggest distinctive proteomic signatures that can be leveraged for diagnostic purposes. While both traditional machine learning and deep learning approaches achieved exceptional performance, each offers distinct advantages in terms of computational efficiency and feature extraction capabilities.

Quality control of hazelnuts is a major concern in many regions across the world, but particularly in Turkey as the world's largest hazelnut producer. Using image processing and deep learning techniques, this study intended to detect and classify healthy hazelnuts and hazelnuts infected with the Brown Marmorated Stink Bug. Infected hazelnut samples were collected from the 2021 production period by experts. A Guppy Pro CCD camera-based image acquisition system was used to capture hazelnut images. A total of 400 RGB hazelnut images were captured to train machine learning models. Image segmentation process was carried out to subtract hazelnut images from the background using the Thresholding technique. Moment features were extracted from RGB and l*a*b* spaces to be used to train traditional machine learning models. Furthermore, the most relevant and discriminative feature set was selected using the Boruta feature selection method. Traditional machine learning models including Random Forest, Support Vector Machine, Logistic Regression, Naive Bayes, and Decision Tree were trained twice, once with all features and another with the selected feature set only. The overall accuracy, statistical characteristics of the confusion matrix, and model training time were all calculated to evaluate and compare models performances. As a result, threshold value of 50 was determined from the gray level histogram and was able to separate hazelnut image from the background perfectly. Only seven moment features were identified as the most discriminative features out of 24 features. The SVM model with all feature vectors had the greatest classification accuracy of 98.75 %. When only the selected features were employed, the performance of Random Forest and Logistic Regression models improved to 97.5 and 96.25 %, respectively.

An analysis of machine learning models for sentiment analysis of Tamil code-mixed data

Neuroimaging research has begun adopting deep learning to model structural differences in the brain. This is a break from previous approaches that rely largely on anatomical volumetric or thickness-based features. Currently, most studies employ either convolutional deep learning based models or traditional machine learning models that use volumetric features. Because of this split, it is unclear which approach yields better predictive performance, or whether the two approaches will lead to different neuroanatomical conclusions, potentially even when applied to the same dataset. To address these questions, we present the largest single study of sex differences in the brain using 21,390 UK Biobank T1-weighted brain MRIs, which we analyzed through both traditional volumetric and 3D convolutional neural network models. Overall, we find that 3D-CNNs outperformed traditional machine learning models, with sex classification area under the ROC curve of 0.849 and 0.683, respectively. When performing sex classification using only single regions of the brain, we observed better performance from 3D-CNNs in all regions tested, indicating sex differences in the brain likely represent both structural and volumetric changes. In addition, we find little consensus in terms of brain region prioritization between the two approaches. In summary, we find that 3D-CNNs show exceptional sex classification performance, extract additional relevant structural information from brain regions beyond volume, and possibly because of this, prioritize sex differences in neuroanatomical regions differently than volume-based approaches.

We aimed to identify existing hypertension risk prediction models developed using traditional regression-based or machine learning approaches and compare their predictive performance. We systematically searched MEDLINE, EMBASE, Web of Science, Scopus, and the grey literature for studies predicting the risk of hypertension among the general adult population. Summary statistics from the individual studies were the C-statistic, and a random-effects meta-analysis was used to obtain pooled estimates. The predictive performance of pooled estimates was compared between traditional regression-based models and machine learning-based models. The potential sources of heterogeneity were assessed using meta-regression, and study quality was assessed using the PROBAST (Prediction model Risk Of Bias ASsessment Tool) checklist. Of 14,778 articles, 52 articles were selected for systematic review and 32 for meta-analysis. The overall pooled C-statistics was 0.75 [0.73-0.77] for the traditional regression-based models and 0.76 [0.72-0.79] for the machine learning-based models. High heterogeneity in C-statistic was observed. The age (p = 0.011), and sex (p = 0.044) of the participants and the number of risk factors considered in the model (p = 0.001) were identified as a source of heterogeneity in traditional regression-based models. We attempted to provide a comprehensive evaluation of hypertension risk prediction models. Many models with acceptable-to-good predictive performance were identified. Only a few models were externally validated, and the risk of bias and applicability was a concern in many studies. Overall discrimination was similar between models derived from traditional regression analysis and machine learning methods. More external validation and impact studies to implement the hypertension risk prediction model in clinical practice are required.

A vibration-based 1DCNN-BiLSTM model for structural state recognition of RC beams

Macroeconomics has a profound impact on the financial condition and loan behavior of individual borrowers. This article provides a specific analysis of the macroeconomic impact based on data from P2P lending platform LendingClub. Firstly, traditional machine learning models are used to train predictive data. By comparing the predictive performance of macro sensitive and nonsensitive micro features at similar scales, it is found that macro-sensitive micro features are more suitable for model training; Further inclusion of representative macro indicators leads to an improvement in performance, confirming the direct impact of macroeconomic factors on credit default predictions. Given the limitations of traditional machine learning models in dealing with feature multicollinearity and nonlinear relationship of the data, DNN (Deep Neural Network) models are introduced to optimize the performance. The research results indicate that at the feature selection level, macro-related features have a significant impact on credit default prediction. At the level of model evaluation, neural network models have better learning and default prediction performance compared to traditional machine learning models for imbalanced and nonlinear credit datasets in the real world.