Question Classification in Albanian Through Deep Learning Approaches

In online courses, discussion forums play a key role in enhancing student interaction with peers and instructors. Due to large enrolment sizes, instructors often struggle to respond to students in a timely manner. To address this problem, both traditional Machine Learning (ML) (e.g., Random Forest) and Deep Learning (DL) approaches have been applied to classify educational forum posts (e.g., those required urgent responses vs. that did not). However, there lacks an in-depth comparison between these two kinds of approaches. To better guide people to select an appropriate model, we aimed at providing a comparative study on the effectiveness of six frequently-used traditional ML and DL models across a total of seven different classification tasks centering around two datasets of educational forum posts. Through extensive evaluation, we showed that (i) the up-to-date DL approaches did not necessarily outperform traditional ML approaches; (ii) the performance gap between the two kinds of approaches can be up to 3.68% (measured in F1 score); (iii) the traditional ML approaches should be equipped with carefully-designed features, especially those of common importance across different classification tasks. Based on the derived findings, we further provided insights to help instructors and educators construct effective classifiers for characterizing educational forum discussions, which, ultimately, would enable them to provide students with timely and personalized learning support.

Human emotions play a key role in numerous decision-making processes. The ability to correctly identify likes and dislikes as well as excitement and boredom would facilitate novel applications in neuromarketing, affective entertainment, virtual rehabilitation and forensic neuroscience that leverage on sub-conscious human affective states. In this neuroinformatics investigation, we seek to recognize human preferences and excitement passively through the use of electroencephalography (EEG) when a subject is presented with some 3D visual stimuli. Our approach employs the use of machine learning in the form of deep neural networks to classify brain signals acquired using a brain-computer interface (BCI). In the first part of our study, we attempt to improve upon our previous work, which has shown that EEG preference classification is possible although accuracy rates remain relatively low at 61%-67% using conventional deep learning neural architectures, where the challenge mainly lies in the accurate classification of unseen data from a cohort-wide sample that introduces inter-subject variability on top of the existing intra-subject variability. Such an approach is significantly more challenging and is known as subject-independent EEG classification as opposed to the more commonly adopted but more time-consuming and less general approach of subject-dependent EEG classification. In this new study, we employ deep networks that allow dropouts to occur in the architecture of the neural network. The results obtained through this simple feature modification achieved a classification accuracy of up to 79%. Therefore, this study has shown that the use of a deep learning classifier was able to achieve an increase in emotion classification accuracy of between 13% and 18% through the simple adoption of the use of dropouts compared to a conventional deep learner for EEG preference classification. In the second part of our study, users are exposed to a roller-coaster experience as the emotional stimuli which are expected to evoke the emotion of excitement, while simultaneously wearing virtual reality goggles, which delivers the virtual reality experience of excitement, and an EEG headset, acquires the raw brain signals detected when exposed to this excitement stimuli. Here, a deep learning approach is used to improve the excitement detection rate to well above the 90% accuracy level. In a prior similar study, the use of conventional machine learning approaches involving k-Nearest Neighbour (kNN) classifiers and Support Vector Machines (SVM) only achieved prediction accuracy rates of between 65% and 89%. Using a deep learning approach here, rates of 78%-96% were achieved. This demonstrates the superiority of adopting a deep learning approach over other machine learning approaches for detecting human excitement when immersed in an immersive virtual reality environment.

Intrusion detection is a major challenge for security experts in the cyber world. Traditional IDS failed to detect complex and unknown cyber-attacks. Machine learning has become a vibrant technology for cybersecurity. There exists several machine learning algorithms to detect intrusion. Most classifiers are well suited to detect the attacks. However, improving accuracy and detecting unknown attacks in existing IDSs is a great challenge. Therefore, the detailed comparative study of various machine learning approaches such as artificial neural networks, support vector machine, decision tree, and hybrid classifiers used by researchers for intrusion detection are done. Deep learning is an emerging approach which suits well for large data. Deep learning techniques find optimal feature set and classify low-frequency attacks better than other techniques. This study also summarizes literatures in deep learning approaches such as deep auto-encoder, Boltzmann machine, recurrent neural networks, convolutional neural networks, and deep neural networks. Moreover, the datasets used in various literatures and the analysis of deep learning approaches based on the performance metrics are also done. Future directions to detect intrusion are also provided. This study in fact will be helpful to develop IDS based on artificial intelligence approaches such as machine learning and deep learning.KeywordsMachine learningIntrusion detectionFeature selectionDeep learningCyber securityClassifier

Investigating the learning approaches of students in nursing education

Deep learning (DL) is now generally acknowledged as the benchmark and evolution in machine learning (ML) fields. Further more, it has steadily suited the most extensively in computational techniques for ML, delivering excellent outcomes in several challenging intellectual works that have equal or still outperformed human ability. DL has the advantage of learning from enormous amounts of data. Here, the DL approach has been applied to classify thunderstorms and non-thunderstorms with a meteorological dataset. Daily observational hourly data sets from 2016 to 2021 have been used to classify the incidence of thunderstorms and non-thunderstorms. Three DL approaches are used: Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM) to classify thunderstorm incidences. These DL techniques are compared with conventional ML techniques, showing that DL approaches outperformed ML. The CNN method provides the highest performance with 92.01% accuracy among all DL and ML approaches.

There has been a lot of interest in creating HRM processes that leverage deep learning and machine learning (ML) approaches since these methods have the potential to completely transform how businesses manage their human resources. Effective decision-making in today's competitive climate requires the HRM (Human Resource Management) profession to use strong DSS (Decision Support System) technology. The issue of prediction, decision-making, testing support, and prediction in an HRM system is the main emphasis of this investigation. A novel decision support system for HR procedures is covered in the study. Deep learning and machine learning approaches have been presented as essential tools for monitoring different HR metrics in the systems created and executed analytical process. The paper includes a description of the proposed methodology as well as a discussion of the experiment results.  

Question classification in Persian using word vectors and frequencies

With the increasing rate and types of cyber attacks against information systems and communication infrastructures, many tools are needed to detect and mitigate against such attacks, for example, Intrusion Detection Systems (IDSs). Unfortunately, traditional Signature‐based IDSs (SIDSs) perform poorly against previously unseen adversarial attacks. Anomaly‐based IDSs (AIDSs) use Machine Learning (ML) and Deep Learning (DL) approaches to overcome these limitations. However, AIDS performance can be poor when trained on imbalanced datasets. To address the challenge of AIDS performance caused by these unbalanced training datasets, generative adversarial models are proposed to obtain adversarial attacks from one side and analyse their quality from another. According to extensive usage and reliability criteria for generative adversarial models in different disciplines, Generative Adversarial Networks (GANs) , Bidirectional GAN (BiGAN) , and Wasserstein GAN (WGAN) are employed to serve AIDS. The authors have extensively assessed their abilities and robustness to deliver high‐quality attacks for AIDS. AIDSs are constructed, trained, and tuned based on these models to measure their impacts. The authors have employed two datasets: NSL‐KDD and CICIDS‐2017 for generalisation purposes, where ML and DL approaches are utilised to implement AIDSs. Their results show that the WGAN model outperformed GANs and BiGAN models in binary and multiclass classifications for both datasets.

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.

With the development of information and technology, especially with the boom in big data, healthcare support systems are becoming much better. Patient data can be collected, retrieved, and stored in real time. These data are valuable and meaningful for monitoring, diagnosing, and further applications in data analysis and decision-making. Essentially, the data can be divided into three types, namely, statistical, image-based, and sequential data. Each type has a different method of retrieval, processing, and deployment. Additionally, the application of machine learning (ML) and deep learning (DL) in healthcare support systems is growing more rapidly than ever. Numerous high-performance architectures are proposed to optimize decision-making. As reliability and stability are the most important factors in the healthcare support system, enhancing the predicted performance and maintaining the stability of the model are always the top priority. The main idea of our study comes from ensemble techniques. Numerous studies and data science competitions show that by combining several weak models into one, ensemble models can attain outstanding performance and reliability. We propose three deep ensemble learning (DEL) approaches, each with stable and reliable performance, that are workable on the above-mentioned data types. These are deep-stacked generalization ensemble learning, gradient deep learning boosting, and deep aggregation learning. The experiment results show that our proposed approaches achieve more vigorous and reliable performance than traditional ML and DL techniques on statistical, image-based, and sequential benchmark datasets. In particular, on the Heart Disease UCI dataset, representing the statistical type, the gradient deep learning boosting approach dominates the others with accuracy, recall, F1-score, Matthews correlation coefficient, and area under the curve values of 0.87, 0.81, 0.83, 0.73, and 0.91, respectively. On the X-ray dataset, representing the image-based type, the deep aggregation learning approach shows the highest performance with values of 0.91, 0.97, 0.93, 0.80, and 0.94, respectively. On the Depresjon dataset, representing the sequence type, the deep-stacked generalization ensemble learning approach outperforms the others with values of 0.91, 0.84, 0.86, 0.8, and 0.94, respectively. Overall, we conclude that applying DL models using our proposed approaches is a promising method for the healthcare support system to enhance prediction and diagnosis performance. Furthermore, our study reveals that these approaches are flexible and easy to apply to achieve optimal performance.

Today’s security attacks on computer networks are becoming more complex and severe, which has prompted security researchers to use a variety of machine learning techniques to safeguard the information and reputation of their clients. Detecting network infiltration has long been a difficult task. Machine learning advancements have raised the way for improving intrusion detection systems (IDS). This development has led to intrusion detection’s integration into network security. Using supervised machine learning techniques, intrusion detection has attained great detection accuracy. However, it is unlikely that a machine learning (ML) classifier will be able to correctly identify all attacks, particularly obscure ones.An approach based on deep learning is presented for more precise intrusion detection. This review article presents an extensive survey and classification of deep learning-based intrusion detection techniques with an emphasis on these approaches. The main background ideas about the IDS architecture and several machine and deep learning approaches are initially presented. Then, it categorizes these schemes based on the many types of methodologies each one employs. It explains how accurate intrusion detection is achieved through the use of machine and deep learning networks. The researched IDS frameworks are then fully analysed, with final thoughts and suggested directions for the future underlined.

Bring your own device (BYOD) paradigm that permits employees to come with their own mobile devices to join the organizational network is rapidly changing the organizational operation method by enhancing flexibility, productivity, and efficiency. Despite these benefits, security issues remain a concern in organizational settings. A considerable number of studies have been conducted and published in this domain without a detailed review of the security solution mechanisms. Moreover, some reviews conducted focused more on conventional approaches such as mobile content management, and application content management. Hence, the implementation of security in BYOD using the conventional method is ineffective. Thus, machine learning approaches seem to be the promising approach, which provides a solution to the security problem in the BYOD environment. This study presents a comprehensive systematic mapping review that focused on the application of the machine learning approach for the mitigation of security threats and attacks in the BYOD environment by highlighting the current trends in the existing studies. Five academic databases were searched and a total of 753 of the primary studies published between 2012 and 2021 were initially retrieved. These studies were screened based on their title, abstract and full text to check their eligibility and relevance for the study. However, forty primary studies were included and analyzed in the systematic mapping review (SMR). Based on the analysis and bubble plot mapping, significant research trends were identified on security threats and attacks, machine learning approaches, datasets usage, and evaluation metrics. The SMR result demonstrates the rise in the number of investigations regarding malware and unauthorized access to existing security threats and attacks. The SMR study indicates that supervised learning approaches such as SVM, DT, and RF are the most employed learning model by the previous research. Thus, there is an open research issue in the application of unsupervised learning approaches such as clustering and deep learning approaches. Therefore, the SMR has set the pace for creating new ground research in the machine learning implementation in the BYOD environment, which will offer invaluable insight into the study field, and researchers can employ it to find a research gap in the research domain.

A comprehensive review on detection of plant disease using machine learning and deep learning approaches

Recent advancements in remote sensing technologies, as well as high-resolution satellite images, have opened up new avenues for comprehending the earth's surfaces. However, owing to the significant unpredictability in satellite data, satellite images categorization is a difficult task. Availability of the satellite dataset is a challenging task in the field of remote sensing. To overcome this challenge a novel sentinel-2 image dataset is proposed. Two different techniques for categorizing a large-scale dataset containing various types of land-use and land-cover surfaces are proposed and compared for this goal. In this article, an enhanced version of ResNet50 has been proposed to predict the multiple classes from sentinel 2 images. Furthermore, the outcome of ResNet50 is compared with traditional (shallow) machine learning models and deep learning models to check the working efficiency of the proposed approach. The shallow approach had the best F1-score of 0.87, while the deep approach ResNet50 achieved the best F1-score of 0.924. It has been realized from the outcome that the deep learning approaches are most robust than the machine learning approach in terms of classifying the multi-label satellite images classification.

Introduction While the majority of intracranial aneurysms (IAs) remain asymptomatic, rupture results in subarachnoid hemorrhage, a devastating event with high morbidity and mortality. Traditional rupture risk assessment relies on morphology, size, and location, yet these parameters lack individualized precision. Recent advances in machine learning (ML) and radiomics provide an opportunity to integrate high‐dimensional imaging features and clinical data to predict rupture risk with greater accuracy. This systematic review and meta‐analysis evaluates the performance of ML‐ and radiomics‐based approaches for IA rupture prediction. Methods We reviewed studies applying ML or radiomics for IA rupture risk prediction, including systematic reviews, retrospective datasets, and prospective validation studies. Eligible reports used angiographic imaging (CTA, MRA, or DSA) with reference standards of rupture status or clinical outcomes. Extracted data included sample size, sensitivity, specificity, and area under the curve (AUC). Random‐effects models were used to synthesize predictive performance. Subgroup analyses evaluated conventional ML algorithms, radiomics‐based models, and deep learning approaches. Results Four representative studies highlight the evolving field. A meta‐analysis by Akhtar et al. (2024) demonstrated pooled sensitivity and specificity of 83% for ML rupture prediction, with AUC ∼0.85. Stumpo et al. (2022) reported that ML models consistently outperformed conventional risk scores, achieving sensitivity and specificity near 80%. Hu et al. (2023), using digital subtraction angiography in 263 patients, achieved exceptional performance with an AUC of 0.982, sensitivity of 94.4%, and specificity of 97.5% in distinguishing ruptured from unruptured aneurysms. In contrast, Heo et al. (2020) leveraged a national claims dataset to develop population‐level ML models, reaching AUROC 0.765 for rupture prediction, demonstrating the feasibility of integrating epidemiological and imaging data. Pooled analysis across studies yielded an average AUC of 0.85 (95% CI: 0.80‐0.89), with sensitivity ∼0.85 and specificity ∼0.86. Notably, radiomics models incorporating texture, intensity, and morphological signatures demonstrated superior discrimination compared to size‐based parameters alone. However, performance was heterogeneous across datasets, and generalizability was limited by small sample sizes and retrospective designs. Conclusion Machine learning and radiomics approaches extend aneurysm assessment “beyond detection,” offering promising accuracy in rupture risk prediction. With pooled AUCs near 0.85 and select studies reporting &gt;0.95 performance, these models surpass traditional size‐based criteria. However, variability across cohorts and lack of standardized imaging features limit clinical translation. Future directions include prospective multicenter validation, integration of radiomics with clinical and hemodynamic markers, and development of explainable AI frameworks to ensure reproducibility. Ultimately, ML‐guided rupture risk stratification holds potential to personalize management and reduce subarachnoid hemorrhage incidence.