Classification Framework Research Articles

Empowering Brain Tumor Diagnosis through Explainable Deep Learning

Brain tumors are among the most lethal diseases, and early detection is crucial for improving patient outcomes. Currently, magnetic resonance imaging (MRI) is the most effective method for early brain tumor detection due to its superior imaging quality for soft tissues. However, manual analysis of brain MRI scans is prone to errors, largely influenced by the radiologists’ experience and fatigue. To address these challenges, computer-aided diagnosis (CAD) systems are more significant. These advanced computer vision techniques such as deep learning provide accurate predictions based on medical images, enhancing diagnostic precision and reliability. This paper presents a novel CAD framework for multi-class brain tumor classification. The framework employs six pre-trained deep learning models as the base and incorporates comprehensive data preprocessing and augmentation strategies to enhance computational efficiency. To address issues related to transparency and interpretability in deep learning models, Gradient-weighted Class Activation Mapping (Grad-CAM) is utilized to visualize the decision-making processes involved in tumor classification from MRI scans. Additionally, a user-friendly Brain Tumor Detection System has been developed using Streamlit, demonstrating its practical applicability in real-world settings and providing a valuable tool for clinicians. All simulation results are derived from a public benchmark dataset, showing that the proposed framework achieves state-of-the-art performance, with accuracy approaching 99% in ResNet-50, Xception, and InceptionV3 models.

Advances in Detection and Monitoring of Coal Spontaneous Combustion: Techniques, Challenges, and Future Directions

Coal spontaneous combustion (CSC) is a multifaceted research domain that has been widely explored in the literature, ranging from analytical and numerical modeling to the development of fire suppression materials and methods. A comprehensive review of the literature has revealed several distinct research trajectories, or “roadmaps”, identified through criteria such as the volume of studies addressing each theme, the presence of review papers dedicated to a specific roadmap, and the explicit mention of coal spontaneous combustion in the title or keywords. This classification framework has outlined six primary roadmaps: (1) spread, quantification, and impact; (2) mechanisms, models, factors, and parameters; (3) experimental studies and models; (4) detection, monitoring, and prediction; (5) prevention and control; and (6) applications. While interconnections exist between these roadmaps, and all ultimately converge towards roadmap 5 (prevention and control), each roadmap constitutes a distinct research cluster. The focus of this review is on roadmap 4, specifically addressing the methods and technologies for detection, monitoring, and prediction of CSC events. This review encompasses studies published from 2010 to the present, providing a thorough examination of the various detection techniques employed, with particular emphasis on their limitations and the strategies proposed to overcome these challenges. A critical analysis highlights the key advantages and disadvantages of each category of techniques, offering insights into their practical applications and the potential for future advancements in this field. The present review aims to contribute to the refinement of detection and monitoring methods for CSC, with the goal of enhancing early detection capabilities and improving fire management strategies.

Strategic redesign of business processes in the digital age: A framework

Organizations constantly seek ways to improve their business processes by using digital technologies as enablers. However, simply substituting an existing technology with a new one has limited value compared to using the capabilities of digital technologies to redesign business processes. Therefore, process analysts try to understand how the capabilities of digital technologies can enable the redesign of business processes. In this paper, we conduct a systematic literature review and examine 40 case studies where digital technologies were used to redesign business processes. We identified that, within the context of business process improvement, capabilities of digitalization, communication, analytics, digital representation, and connectivity can enable business process redesign. Furthermore, we note that these capabilities enable applying nine redesign heuristics. Based on our review, we map how each capability can facilitate the implementation of specific redesign heuristics. Finally, we illustrate how such a capability-driven approach can be applied to Metaverse as an example of a digital technology. Our mapping and classification framework can aid analysts in identifying candidate redesigns that capitalize on the capabilities of digital technologies.

Optimizing gene selection for Alzheimer’s disease classification: A Bayesian approach to filter and embedded techniques

Alzheimer’s disease (AD) classification, which is crucial for identifying AD-associated genes, relies heavily on effective feature selection (FS) to tackle the curse of dimensionality. Traditional methods like filter, wrapper, and embedded techniques have their drawbacks, including ignoring feature independence, sensitivity to classifier choices, and high computational costs. Hybrid approaches combining these methods seek to harness their collective strengths but face challenges, particularly in selecting the optimal number of features from each method. This selection is typically manual or requires time-intensive k-fold cross-validation (KFCV), significantly increasing computational demands and complicating the process with the need for extensive parameter optimization across families, thereby escalating the complexity and resource requirements of model development. To overcome these challenges, this work proposes a framework for optimal FS and classification in AD using a combination of filter and embedded techniques, enhanced with hyperparameter tuning. Firstly, gene expression data (GED) from the AD Neuroimaging Initiative (ADNI) is preprocessed. Then, Chi-square filter selection is applied to decrease correlated features. Next, Logistic Regression with ElasticNet penalty (LREN) is employed to further refine the feature set. Finally, Bayesian Optimization (BO) is introduced to automatically determine the optimal number of features (k for Chi-square and max_features for LREN), iteratively evaluating different combinations to find the set that maximizes model accuracy. The selection process is used primarily in the function of BO to tune automatically the (k and max_features while minimizing the number of features and maximizing the accuracy of the Support Vector Machine (SVM). The SVM was used as a classifier to overcome the problem of embedded selection sensitivity to the model of selection. The tuned features are then used to select relevant features from the ADNI dataset and fitted to different models. We evaluated the performance of five classifiers—logistic regression (LR), SVM, Ridge Classifier (RC), stochastic gradient descent classifier (SGD), and Gaussian Naïve Bayes(GNB) across various metrics. Among these, SVM achieved 100% performance in all metrics. This approach significantly reduced the FS time and the number of initial features to 0.6% and 0.02%, respectively. Notably, it identified 6 out of 20 selected features as directly AD-related. Comparative analysis reveals that the proposed method outperforms existing approaches on the ADNI dataset and other datasets. Statistical tests were conducted to assess the significance of the results compared to other methods, confirming a significant improvement and underscoring the effectiveness of the proposed framework in optimal FS and biological relevance confirmation.

Exploratory parallel hybrid sampling framework for imbalanced data classification

Current engineering application scenarios often face the challenge of imbalanced data, hybrid sampling is an effective method to deal with the imbalanced data classification issue, which can avoid the issues of overfitting and mistakenly deleting useful majority samples when using oversampling approach and undersampling approach alone. However, at present most of the hybrid sampling approaches are implemented serially, and the implementation of oversampling and undersampling approaches alone will cause mutual interference and influence between them. This study proposes a parallel hybrid sampling framework based on the idea of parallel engineering and theoretically analyzes its superiority. The experimental results show that when applied to five classification algorithms with three performance evaluation metrics,the proposed framework outperforms the two mainstream hybrid sampling frameworks. Moreover, the proposed framework can effectively reduce the time consumption of hybrid sampling process.

Unravelling sleep patterns: Supervised contrastive learning with self-attention for sleep stage classification

Sleep data scoring is a crucial and primary step for diagnosing sleep disorders to know the sleep stages from the PSG signals. This study uses supervised contrastive learning with a self-attention mechanism to classify sleep stages. We propose a deep learning framework for automatic sleep stage classification, which involves two training phases: (1) the feature representation learning phase, in which the feature representation network (encoder) learns to extract features from the electroencephalogram (EEG) signals, and (2) the classification network training phase, where a pre-trained encoder (trained during phase I) along with the classifier head is fine-tuned for the classification task. The PSG data shows a non-uniform distribution of sleep stages, with wake (W) (around 30% of total samples) and N2 stages (around 58% and 37% of total samples in Physionet EDF-Sleep 2013 and 2018 datasets, respectively) being more prevalent, leading to an imbalanced dataset. The imbalanced data issue is addressed using a weighted softmax cross-entropy loss function that assigns higher weights to minority sleep stages. Additionally, an oversampling technique (the synthetic minority oversampling technique (SMOTE) (Chawla et al., 2002)[1] ) is applied to generate synthetic samples for minority classes. The proposed model is evaluated on the Physionet EDF-Sleep 2013 and 2018 datasets using Fpz-Cz and Pz-Oz EEG channels. It achieved an overall accuracy of 94.1%, a macro F1 score of 92.64, and a Cohen’s Kappa coefficient of 0.92. Ablation studies demonstrated the importance of triplet loss-based pre-training and oversampling for enhancing performance. The proposed model requires minimal pre-processing, eliminating the need for extensive signal processing expertise, and thus is well-suited for clinicians diagnosing sleep disorders.

A unified multimodal classification framework based on deep metric learning

Multimodal classification algorithms play an essential role in multimodal machine learning, aiming to categorize distinct data points by analyzing data characteristics from multiple modalities. Extensive research has been conducted on distilling multimodal attributes and devising specialized fusion strategies for targeted classification tasks. Nevertheless, current algorithms mainly concentrate on a specific classification task and process data about the corresponding modalities. To address these limitations, we propose a unified multimodal classification framework proficient in handling diverse multimodal classification tasks and processing data from disparate modalities. UMCF is task-independent, and its unimodal feature extraction module can be adaptively substituted to accommodate data from diverse modalities. Moreover, we construct the multimodal learning scheme based on deep metric learning to mine latent characteristics within multimodal data. Specifically, we design the metric-based triplet learning to extract the intra-modal relationships within each modality and the contrastive pairwise learning to capture the inter-modal relationships across various modalities. Extensive experiments on two multimodal classification tasks, fake news detection and sentiment analysis, demonstrate that UMCF can extract multimodal data features and achieve superior classification performance than task-specific benchmarks. UMCF outperforms the best fake news detection baselines by 2.3% on average regarding F1 scores.

Morphological diversity and taxonomic implications of seedling structures in selected species of Fabaceae from Karachi (Pakistan)

Seedling morphology is a valuable tool for plant identification and classification, particularly in early growth stages. This study investigates the morphological characters of seedlings from randomly selected taxa within the Fabaceae family, focusing on cotyledons, first two leaves, and subsequent leaves to support taxonomic differentiation. Not all subfamilies within Fabaceae are fully represented in this study. Seedlings from 14 randomly selected taxa were analyzed using morphological traits such as cotyledon shape, phyllotaxy, leaf shape, and venation patterns. An artificial key was constructed, and three dendrograms were developed based on cotyledon morphology, first two leaves, and subsequent leaves to illustrate taxonomic relationships. Statistical analyses were employed to assess clustering patterns among the taxa. The artificial key categorized the taxa into subfamilies within Fabaceae, including Caesalpinoideae, Mimosoideae, and Papilionoideae, based on cotyledon shape and leaf morphology. Dendrogram analysis revealed distinct clustering patterns, grouping species according to key morphological features. Not all subfamilies of Fabaceae were covered, but the analysis provided clear separation among the species studied. The morphological traits observed were consistent with previous taxonomic findings and offered a reliable basis for classification. The morphological features of seedlings, especially cotyledons and eophylls, serve as reliable taxonomic markers for identifying and classifying species within Fabaceae. Although the study does not encompass all subfamilies, the randomly selected taxa demonstrated clear taxonomic distinctions. Dendrograms combined with artificial keys provided a useful framework for classification. Further studies should expand the scope to include more taxa, covering all subfamilies of Fabaceae. Integrating molecular and other taxonomic tools such as anatomy, cytology, and chemistry can enhance the precision of classification frameworks and provide deeper insights into the evolutionary relationships within the family.

Soil Properties Classification in Sustainable Agriculture Using Genetic Algorithm-Optimized and Deep Neural Networks

Optimization of land management and agricultural practices require precise classification of soil properties. This study presents a method to fine-tune deep neural network (DNN) hyperparameters for multiclass classification of soil properties using genetic algorithms (GAs) with knowledge-based generation of hyperparameters. The focus is on classifying soil attributes, including nutrient availability (0.78 ± 0.11), nutrient retention capacity (0.86 ± 0.05), rooting conditions (0.85 ± 0.07), oxygen availability to roots (0.84 ± 0.05), excess salts (0.96 ± 0.02), toxicity (0.96 ± 0.01), and soil workability (0.84 ± 0.09), with these accuracies representing the results from classification with variations from cross-validation. A dataset from the USA, which includes land-use distribution, aspect distribution, slope distribution, and climate data for each plot, is utilized. A GA is applied to explore a wide range of hyperparameters, such as the number of layers, neurons per layer, activation functions, optimizers, learning rates, and loss functions. Additionally, ensemble methods such as random forest and gradient boosting machines were employed, demonstrating comparable accuracy to the DNN approach. This research contributes to the advancement of precision agriculture by providing a robust machine learning (ML) framework for accurate soil property classification. By enabling more informed and efficient land management decisions, it promotes sustainable agricultural practices that optimize resource use and enhance soil health for long-term ecological balance.

Early fire detection using wavelet based features

In recent years, millions of hectares of vegetation worldwide have been destroyed by wildfires and forest fires. Computer vision-based fire classification, which separates pixels from image or video datasets into fire and non-fire categories, has gained more attention recently due to technological innovations. Fire pixels in an image or video can be classified using either a deep learning strategy or a traditional machine learning approach. Deep learning algorithms could process enormous volumes of data, but their training model performance is constrained because they fail to consider the differences in complexity between training samples. Moreover, it is not obvious to train a deep learning model without a dedicated GPU unit.Similarly, deep learning techniques that have a scarcity of training data and insufficient features exhibit poor performance in intricate real-world fire situations. Consequently, to categorize fire and non-fire pixels from the processed photos from the publicly accessible datasets, Corsican and FLAME, as well as the aerial private dataset Firefront_Gestosa, the current study uses a lightweight technique based on SVM and a refined set of features.The present research implemented a novel framework for fire detection and classification from a variety of RGB and Infra-red images acquired during real missions, addressing the significant requirement for swift and accurate recognition of diverse types of flames, ranging from wildfires to industrial and domestic fires. The framework employs wavelet decomposition-based features, including wavelet length, standard deviation, variance, energy, and Shannon’s entropy, extracted through a sliding window sampling method within a machine learning approach. It should be noted that managing multidimensional data to train a model is difficult in machine learning applications. This issue is solved adopting a feature selection approach, which eliminates redundant or unnecessary data that affects the functionality of the model. Thus, to enhance model performance, feature selection using ranking algorithms based on theoretical mutual information is applied in combination to the Support Vector Machine (SVM) with Radial Basis Function (RBF) kernel.Extensive experiments demonstrate exceptional results, notably with Haar wavelets, achieving an impressive overall accuracy of 99.43% and remarkable performance across specificity, precision, recall, F-measure, and G-mean metrics. Thus, the present study showcases the potential of advanced image processing techniques to significantly advance fire detection and classification, thereby contributing to fire prevention, management, and research in various contexts.

Metacognitive strategies in mathematical modelling: a case study with engineering students

During the last years, mathematical modelling has been entering the field of engineering education because it is a bridge between mathematics and industry that also promotes the development of skills that require the engineer of the twenty-first century. Nevertheless, the modelling process is involved and requires the deployment of cognitive skills of superior level, particularly metacognitive skills. This contribution presents the results of a multiple qualitative case study on metacognitive strategies used by groups of engineering students associated with each transition of the mathematical modelling process. During the development of the course, observations and retrospective interviews were carried out, which evidenced the use of metacognitive planning strategies from simplification to interpretation; metacognitive monitoring strategies throughout the modelling process, metacognitive regulation strategies from mathematization to mathematical work and metacognitive evaluation strategies during simplification, mathematization and validation. The results expand the classification framework of metacognitive strategies for engineering students.

Hybrid FCMG-OP-FIS model approach to convert regression into classification data for machine learning-based AQI prediction

Air pollution from vehicle emissions, industrial activities, and medical facilities poses significant health risks in urban areas, underscoring the necessity for robust air quality index (AQI) monitoring. This paper presents a novel method for AQI prediction by integrating a fuzzy centre merge graph with an optimal value-based fuzzy inference system (FCMG-OP-FIS) and machine learning (ML). Traditional ML techniques encounter difficulties when converting regression datasets into classification formats, particularly when unable to label the dataset using the traditional method. The proposed FCMG-OP-FIS model efficiently converts regression data into a classification framework. Unlike traditional AQI prediction methods that rely solely on pollutant data, this approach incorporates both pollutant and meteorological data to improve prediction accuracy. The innovative fuzzy centre merge graph (FCMG) balances the dataset for optimal solutions and facilitates input grouping for Simulink, simplifying rule management. The FCMG-OP-FIS model generates a regression output for AQI, which is subsequently classified into levels (healthy, moderate, or unhealthy) using IF-THEN rules. To enhance accuracy further, a random forest classifier (RFC) is trained on the FCMG-OP-FIS classified output data. The regression output of the FCMG-OP-FIS model is validated using metrics such as RMSE (0.48), MSE (0.23), MAE (0.23), and MAPE (1.77%). Additionally, the classification output from the RFC model employs advanced validation techniques including stratified shuffle validation, grid search cross-validation, and confusion matrix analysis, achieving an accuracy rate of 99%, with the F1 score, precision, and recall over all at 99%. These results demonstrate the effectiveness of the proposed model in accurately labelling data for classification and predicting AQI through ML, highlighting its potential for practical application in environmental monitoring and management.

SigDA: A Superimposed Domain Adaptation Framework for Automatic Modulation Classification

SigDA: A Superimposed Domain Adaptation Framework for Automatic Modulation Classification

Exploring sample relationship for few-shot classification

Few-shot classification (FSC) is a challenging problem, which aims to identify novel classes with limited samples. Most existing methods employ vanilla transfer learning or episodic meta-training to learn a feature extractor, and then measure the similarity between the query image and the few support examples of novel classes. However, these approaches merely learn feature representations from individual images, overlooking the exploration of the interrelationships among images. This neglect can hinder the attainment of more discriminative feature representations, thus limiting the potential improvement of few-shot classification performance. To address this issue, we propose a Sample Relationship Exploration (SRE) module comprising the Sample-level Attention (SA), Explicit Guidance (EG) and Channel-wise Adaptive Fusion (CAF) components, to learn discriminative category-related features. Specifically, we first employ the SA component to explore the similarity relationships among samples and obtain aggregated features of similar samples. Furthermore, to enhance the robustness of these features, we introduce the EG component to explicitly guide the learning of sample relationships by providing an ideal affinity map among samples. Finally, the CAF component is adopted to perform weighted fusion of the original features and the aggregated features, yielding category-related embeddings. The proposed method is a plug-and-play module which can be embedded into both transfer learning and meta-learning based few-shot classification frameworks. Extensive experiments on benchmark datasets show that the proposed module can effectively improve the performance over baseline models, and also perform competitively against the state-of-the-art algorithms. The source code is available at https://github.com/Chenguoz/SRE.

Precise and Accurate Short-term Forecasting of Solar Energetic Particle Events with Multivariate Time-series Classifiers

Solar energetic particle (SEP) events are one of the most crucial aspects of space weather that require continuous monitoring and forecasting using robust methods. We demonstrate a proof of concept of using a data-driven supervised classification framework on a multivariate time-series data set covering solar cycles 22, 23, and 24. We implement ensemble modeling that merges the results from three proton channels (E ≥ 10 MeV, 50 MeV, and 100 MeV) and the long-band X-ray flux (1–8 Å) channel from the Geostationary Operational Environmental Satellite missions. Our task is binary classification, such that the aim of the model is to distinguish strong SEP events from nonevents. Here, strong SEP events are those crossing the Space Weather Prediction Center’s “S1” threshold of solar radiation storm and proton fluxes below that threshold are weak SEP events. In addition, we consider periods of nonoccurrence of SEPs following a flare with magnitudes ≥C6.0 to maintain a natural imbalance of sample distribution. In our data set, there are 244 strong SEP events comprising the positive class. There are 189 weak events and 2460 “SEP-quiet” periods for the negative class. We experiment with summary statistic, one-nearest neighbor, and supervised time-series forest (STSF) classifiers and compare their performance to validate our methods for prediction windows from 5 minutes up to 60 minutes. We find the STSF model to perform better under all circumstances. For an optimal classification threshold of ≈0.3 and a 60 minutes prediction window, we obtain a true skill statistic TSS = 0.850, Heidke skill score HSS = 0.878, and Gilbert skill score GSS = 0.783.

Application of simulation and machine learning in supply chain management: A synthesis of the literature using the Sim-ML literature classification framework

Stochastic modeling techniques, such as discrete-event and agent-based simulation, are widely used in supply chain management (SCM) for capturing real-world uncertainties. Over the last decade, data-driven approaches like machine learning (ML) have also gained prominence in SCM, employing methods such as supervised learning (SL), unsupervised learning (UL), and reinforcement learning (RL). As supply chains grow in complexity, hybrid models combining simulation (Sim) and ML are becoming increasingly common, and the field stands to gain from a structured review of this literature. Towards this, we developed the Sim-ML Literature Classification Framework, which includes a hierarchical taxonomy comprising five SC criteria, 22 Sim-ML classes and over 75 Sim-ML subclasses. We applied this framework to synthesize 99 papers, revealing significant diversity in how Sim-ML models are used to address supply chain challenges. Key findings include the recognition of the breadth of study objectives, identifying various forms of model hybridization achieved by combining discrete/continuous simulation techniques with SL, UL, and RL approaches, and the data flow mechanisms such as sequential and feedback methods employed by the simulation and ML elements of the hybrid model. Our findings also identify some gaps in the literature; for example, optimization is rarely incorporated into Sim-ML models. Also, most studies present Sim-ML models for addressing problems in general supply chains, likely due to the lack of access to industrial data. The review also highlights that Industry 4.0 technologies, such as digital twins and blockchain, are underrepresented in current research, as are topics like sustainability and transportation. These gaps suggest significant opportunities for future research. We provide guidelines for practitioners on applying Sim-ML models to manage supply chain drivers, mitigate the impact of disruptions, and integrate emerging technologies. Our review serves as a valuable resource for researchers, practitioners, and students interested in leveraging Sim-ML approaches in SCM.

Clinical knowledge-guided hybrid classification network for automatic periodontal disease diagnosis in X-ray image

Accurate classification of periodontal disease through panoramic X-ray images carries immense clinical importance for effective diagnosis and treatment. Recent methodologies attempt to classify periodontal diseases from X-ray images by estimating bone loss within these images, supervised by manual radiographic annotations for segmentation or keypoint detection. However, these annotations often lack consistency with the clinical gold standard of probing measurements, potentially causing measurement inaccuracy and leading to unstable classifications. Additionally, the diagnosis of periodontal disease necessitates exceptional sensitivity. To address these challenges, we introduce HC-Net, an innovative hybrid classification framework devised for accurately classifying periodontal disease from X-ray images. This framework comprises three main components: tooth-level classification, patient-level classification, and a learnable adaptive noisy-OR gate. In the tooth-level classification, we initially employ instance segmentation to individually identify each tooth, followed by tooth-level periodontal disease classification. For patient-level classification, we utilize a multi-task strategy to concurrently learn patient-level classification and a Classification Activation Map (CAM) that signifies the confidence of local lesion areas within the panoramic X-ray image. Eventually, our adaptive noisy-OR gate acquires a hybrid classification by amalgamating predictions from both levels. In particular, we incorporate clinical knowledge into the workflows used by professional dentists, targeting the enhanced handling of sensitivity of periodontal disease diagnosis. Extensive empirical testing on a dataset amassed from real-world clinics demonstrates that our proposed HC-Net achieves unparalleled performance in periodontal disease classification, exhibiting substantial potential for practical application.

Enhancing brain cancer type prediction through machine learning algorithms and feature selection techniques

Abstract The manual identification of brain cancer types is often fraught with inaccuracies, leading to potential delays in diagnosis and treatment planning. This study presents a novel approach to predict brain cancer types using advanced machine learning (ML) algorithms integrated with sophisticated feature selection techniques. A multi-class classification framework was developed and evaluated, incorporating six ML models: Bernoulli Naive Bayes, K-nearest neighbors classifier, decision tree classifier, Gaussian process classifier (GPC), passive aggressive classifier, and perceptron. To enhance model performance, feature selection methods including the Gini index, mutual information, and principal component analysis (PCA) were employed. A comprehensive case study was conducted to assess the predictive accuracy of these models. The GPC, when trained and validated on features derived via PCA, outperformed other models in terms of predictive accuracy and generalization. Specifically, the dimensions identified by PCA (d1, d2, d3, and d4) were most effective in distinguishing between different brain cancer types. This methodology resulted in a significant improvement across various performance metrics. Compared to the baseline GPC model using all original features, the PCA-enhanced GPC achieved remarkable increases in Accuracy, Precision, Recall, and F1 Score by 294.31%, 22.14%, 294.31%, and 878.18%, respectively. These findings underscore the potential of combining ML algorithms with targeted feature selection techniques to advance the accuracy of brain cancer type prediction, offering substantial benefits for clinical decision-making and patient outcomes.

Profiling Astroturfers on Facebook: A Complete Framework for Labeling, Feature Extraction, and Classification

The practice of online astroturfing has become increasingly pervasive in recent years, with the growth in popularity of social media. Astroturfing consists of promoting social, political, or other agendas in a non-transparent or deceitful way, where the promoters masquerade as normative users while acting behind a mask that conceals their true identity, and at times that they are not human. In politics, astroturfing is currently considered one of the most severe online threats to democracy. The ability to automatically identify astroturfers thus constitutes a first step in eradicating this threat. We present a complete framework for handling a dataset of profiles, from data collection and efficient labeling, through feature extraction, and finally, to the identification of astroturfers lurking in the dataset. The data were collected over a period of 15 months, during which three consecutive elections were held in Israel. These raw data are unique in scope and size, consisting of several million public comments and reactions to posts on political candidates’ pages. For the manual labeling stage, we present a technique that can zoom in on a sufficiently large subset of astroturfer profiles, thus making the procedure highly efficient. The feature extraction stage consists of a temporal layer of features, which proves useful for identifying astroturfers. We then applied and compared several algorithms in the classification stage, and achieved improved results, with an F1 score of 77% and accuracy of 92%.

Fruit and vegetable leaf disease recognition based on a novel custom convolutional neural network and shallow classifier.

Fruits and vegetables are among the most nutrient-dense cash crops worldwide. Diagnosing diseases in fruits and vegetables is a key challenge in maintaining agricultural products. Due to the similarity in disease colour, texture, and shape, it is difficult to recognize manually. Also, this process is time-consuming and requires an expert person. We proposed a novel deep learning and optimization framework for apple and cucumber leaf disease classification to consider the above challenges. In the proposed framework, a hybrid contrast enhancement technique is proposed based on the Bi-LSTM and Haze reduction to highlight the diseased part in the image. After that, two custom models named Bottleneck Residual with Self-Attention (BRwSA) and Inverted Bottleneck Residual with Self-Attention (IBRwSA) are proposed and trained on the selected datasets. After the training, testing images are employed, and deep features are extracted from the self-attention layer. Deep extracted features are fused using a concatenation approach that is further optimized in the next step using an improved human learning optimization algorithm. The purpose of this algorithm was to improve the classification accuracy and reduce the testing time. The selected features are finally classified using a shallow wide neural network (SWNN) classifier. In addition to that, both trained models are interpreted using an explainable AI technique such as LIME. Based on this approach, it is easy to interpret the inside strength of both models for apple and cucumber leaf disease classification and identification. A detailed experimental process was conducted on both datasets, Apple and Cucumber. On both datasets, the proposed framework obtained an accuracy of 94.8% and 94.9%, respectively. A comparison was also conducted using a few state-of-the-art techniques, and the proposed framework showed improved performance.