Class Distribution Research Articles

A cloud‐based hybrid intrusion detection framework using XGBoost and ADASYN‐Augmented random forest for IoMT

AbstractInternet of Medical Things have vastly increased the potential for remote patient monitoring, data‐driven care, and networked healthcare delivery. However, the connectedness lays sensitive patient data and fragile medical devices open to security threats that need robust intrusion detection solutions within cloud‐edge services. Current approaches need modification to be able to handle the practical challenges that result from problems with data quality. This paper presents a hybrid intrusion detection framework that enhances the security of IoMT networks. There are three modules in the design. First, an XGBoost‐based noise detection model is used to identify data anomalies. Second, adaptive resampling with ADASYN is done to fine‐tune the class distribution to address class imbalance. Third, ensemble learning performs intrusion detection through a Random Forest classifier. This stacked model coordinates techniques that filter noise and preprocess imbalanced data, identifying threats with high accuracy and reliability. These results are then experimentally validated on the UNSW‐NB15 benchmark to demonstrate effective detection under realistically noisy conditions. The novel contributions of the work are a new hybrid structural paradigm coupled with integrated noise filtering, and ensemble learning. The proposed advanced oversampling with ADASYN gives a performance that surpasses all others with a reported 92.23% accuracy.

A critical appraisal of geroprotective activities of flavonoids in terms of their bio-accessibility and polypharmacology

Flavonoids, a commonly consumed natural product, elicit health-benefits such as antioxidant, anti-inflammatory, antiviral, anti-allergic, hepatoprotective, anti-carcinogenic and neuroprotective activities. Several studies have reported the beneficial role of flavonoids in improving memory, learning, and cognition in clinical settings. Their mechanism of action is mediated through the modulation of multiple signalling cascades. This polypharmacology makes them an attractive natural scaffold for designing and developing new effective therapeutics for complex neurological disorders like Alzheimer's disease and Parkinson's disease. Flavonoids are shown to inhibit crucial targets related to neurodegenerative disorders (NDDs), including acetylcholinesterase, butyrylcholinesterase, β-secretase, γ-secretase, α-synuclein, Aβ protein aggregation and neurofibrillary tangles formation. Conserved neuro-signalling pathways related to neurotransmitter biogenesis and inactivation, ease of genetic manipulation and tractability, cost-effectiveness, and their short lifespan make Caenorhabditis elegans one of the most frequently used models in neuroscience research and high-throughput drug screening for neurodegenerative disorders. Here, we critically appraise the neuroprotective activities of different flavonoids based on clinical trials and epidemiological data. This review provides critical insights into the absorption, metabolism, and tissue distribution of various classes of flavonoids, as well as detailed mechanisms of the observed neuroprotective activities at the molecular level, to rationalize the clinical data. We further extend the review to critically evaluate the scope of flavonoids in the disease management of neurodegenerative disorders and review the suitability of C. elegans as a model organism to study the neuroprotective efficacy of flavonoids and natural products.

DBSCAN SMOTE LSTM: Effective Strategies for Distributed Denial of Service Detection in Imbalanced Network Environments

In detecting Distributed Denial of Service (DDoS), deep learning faces challenges and difficulties such as high computational demands, long training times, and complex model interpretation. This research focuses on overcoming these challenges by proposing an effective strategy for detecting DDoS attacks in imbalanced network environments. This research employed DBSCAN and SMOTE to increase the class distribution of the dataset by allowing models using LSTM to learn time anomalies effectively when DDoS attacks occur. The experiments carried out revealed significant improvement in the performance of the LSTM model when integrated with DBSCAN and SMOTE. These include validation loss results of 0.048 for LSTM DBSCAN and SMOTE and 0.1943 for LSTM without DBSCAN and SMOTE, with accuracy of 99.50 and 97.50. Apart from that, there was an increase in the F1 score from 93.4% to 98.3%. This research proved that DBSCAN and SMOTE can be used as an effective strategy to improve model performance in detecting DDoS attacks on heterogeneous networks, as well as increasing model robustness and reliability.

Fault diagnosis method for bearings under variable working conditions based on transfer relation network

Abstract In order to achieve robust fault diagnosis under varying conditions with limited labeled data, this study combines metric-based meta-learning with feature-based domain adaptation. It introduces a new approach for variable-condition bearing fault diagnosis using transfer relation networks. To enhance the network’s ability to generalize across different domains, the paper integrates local maximum mean discrepancy (LMMD) into the relation network architecture. LMMD aligns the data distributions of various classes between the source and target domains, effectively addressing distributional differences and improving model generalization. To accurately and swiftly extract meaningful fault features, the study proposes a lightweight feature extraction module based on Shuffle Attention (SA). This module employs depth-wise separable convolutions for efficiency and integrates SA after each convolutional layer to bolster feature representation. Finally, experiments on two bearing datasets under varying conditions validate the efficacy and superiority of the proposed model over alternative methods.

Online imbalance learning with unpredictable feature evolution and label scarcity

Recently, online learning with imbalanced data streams has aroused wide concern, which reflects an uneven distribution of different classes in data streams. Existing approaches have conventionally been conducted on stationary feature space and they assume that we can obtain the entire labels of data streams in the case of supervised learning. However, in many real scenarios, e.g., the environment monitoring task, new features flood in, and old features are partially lost during the changing environment as the different lifespans of different sensors. Besides, each instance needs to be labeled by experts, resulting in expensive costs and scarcity of labels. To address the above problems, this paper proposes a novel Online Imbalance learning with unpredictable Feature evolution and Label scarcity (OIFL) algorithm. First, we utilize margin-based online active learning to selectively label valuable instances. After obtaining the labels, we handle imbalanced class distribution by optimizing F-measure and transforming F-measure optimization into a weighted surrogate loss minimization. When data streams arrive with augmented features, we combine the online passive-aggressive algorithm and structural risk minimization to update the classifier in the divided feature space. When data streams arrive with incomplete features, we leverage variance to identify the most informative features following the empirical risk minimization principle and continue to update the existing classifier as before. Finally, we obtain a sparse but reliable learner by the strategy of projecting truncation. We derive theoretical analyses of OIFL. Also, experiments on the synthetic datasets and real-world data streams to validate the effectiveness of our method.

213. A NEW MANOMETRIC TOOL TO EVALUATE THE EFFICACY OF LAPAROSCOPIC ANTIREFLUX SURGERY

Abstract Background High resolution manometry (HRM) has been proven able to describe the pathophysiological pathway leading to gastroesophageal reflux disease (GERD). Recently, a new manometric tool, the Milan Score (MS), has been introduced and validated to evaluate the risk of pathologic GERD, defined as Acid Exposure Time (AET) >6% at pH-study. Aim of this study is to validate this score in the post-operative assessment after laparoscopic antireflux surgery (LARS). Methods All patients who underwent HRM after LARS between October 2020 and May 2023 were included. The MS was calculated assessing four manometric variables: esophagogastric junction (EGJ) type, EGJ contractile integral (EGJ-CI), ineffective esophageal motility (IEM) and response to the straight leg raise (SLR) manoeuvre. The MS was considered pathologic if ≥137 (risk of GERD ≥50%). The risk of GERD was categorized into six classes, according to the MS score. The MS was compared with validated questionnaires for reflux symptoms, including GERD Questionnaire (GERD-Q), GERD Health-Related Quality of Life (GERD-HRQL) and Reflux Symptom Index (RSI), and with postoperative endoscopy findings. Results A total of 160 patients were included (63% males, age: 53 years, time from surgery: 30 months). Surgical techniques included magnetic sphincter augmentation in 54% of patients, Toupet fundoplication in 29% and Nissen or Dor fundoplication in 17%. The proportion of patients with MS ≥137 among those with pathologic questionnaires was 73% for GERD-Q (p<0.001), 75% for GERD-HRQL (p<0.001) and 78% for RSI (p<0.001). The rate of pathologic questionnaires increased for higher MSs. A MS ≥137 was related to recurrent hiatal hernia (23%, p=0.046) and esophagitis (21%, p=0.007) at endoscopy. Clinical and manometric outcomes were similar among different surgical techniques. Conclusions The MS is an efficient tool to assess the efficacy of LARS. Various surgical techniques have similar distribution in the different risk classes for GERD identified by MS, and similar clinical results. HRM with MS represent an easy and feasible assessment of surgical outcomes after LARS, providing an objective evaluation of the antireflux barrier after surgery.

Freshwater Turtles in an Arid Land: Population Ecology, Habitat and Ecological Niche Modelling of Pelomedusa subrufa olivacea in the Sahel

ABSTRACTTurtle ecology and conservation have been poorly explored in the West African Sahel regions, and this scarce information has produced a suboptimal management of their populations in the wild. In order to enhance the knowledge on the Sahelian turtle ecology, a field study was carried out in Burkina Faso on the ecology of Pelomedusa subrufa olivacea, a freshwater species inhabiting a wide range of waterbodies throughout West Africa. Reasoned sampling was carried out, resulting in the collection of a total of 196 individuals of Pelomedusa subrufa olivacea. This species shows a relatively balanced distribution of age and sex classes of individuals surveyed in the different study areas. The majority of individuals were observed in specific habitats, confirmed by an aggregative distribution. The potential habitats identified by the MaxEnt model highlight key areas for the conservation of this species in Burkina Faso. Conservation efforts should focus on protecting and restoring temporary and permanent aquatic habitats, and managing human activities to minimize the impact on turtle populations in the West African Sahel.

An intelligent approach to detect and predict online fraud transaction using XGBoost algorithm

The most popular payment method in recent years is the credit card. Due to the E-commerce industry’s explosive growth, the usage of credit cards for online purchases have been greatly increased as a result frauds has increased. Banks have been facing challenges to detect the credit card system fraud in recent years. Credit card fraud happens when the card was stolen for any unauthorized purposes or if the fraudster utilizes the credit card information for his own use. In order to prevent credit card fraud, it is essential to build detection measures. While detecting credit card theft with machine learning (ML), the features of credit card frauds play an important and they must be carefully selected. A fraud detection algorithm must be created in order to correctly locate and stop fraudulent activity as technology advances along with the amount of fraud cases. ML methods are essential for identifying fraudulent transactions. The implementation of fraud detection models is particularly difficult because of the sensitive nature of the data, the unbalanced class distributions, and the lack of data. In this work, an intelligent approach to detect and predict online fraud transaction using extreme gradient boosting (XGBoost) algorithm is described. The XGBoost model predicts whether a transaction is fraud or not. This model will achieve better performance interarm of recall, precision, accuracy and F1-score for credit card fraud detection.

The Medication Pile-Up: A Cross Sectional Study On Most Common Left Over Medicines Among Population

Unused and expired medications are potentially toxic and should be properly managed to prevent environmental hazards. Proper disposal of medicine is a widely recognized challenge that has garnered increasing attention in various settings. This review aims to evaluate the distribution of practice on the number of expired/unused drugs at home and distribution of classes of unused/expired drugs at home among general population

Improving class probability estimates in asymmetric health data classification: An experimental comparison of novel calibration methods

In the context of health data classification, imbalanced and asymmetric class distributions can significantly impact the performance of machine learning models. One critical aspect affected by these issues is the reliability of class probability estimates, which are crucial for informed decision-making in healthcare applications. Instead of predicting class values directly for a classification problem, it can be more convenient to predict the probability of an observation belonging to each possible class. This research aims to address the challenges posed by imbalanced and asymmetric responses in health data classification by evaluating the effectiveness of recent calibration methods in improving class probability estimates. We propose Beta calibration techniques and the Stratified Brier score and Jaccard's Score as novel calibration methods and evaluation metrics respectively. The experimental comparison involves implementing and assessing various calibration techniques to determine their impact on model performance and calibration accuracy of simulated and healthcare datasets with varying imbalance ratios. Our results show that the Beta calibration method consistently improved the classifiers' predictive ability. The findings of this study provide valuable insights into selecting the most suitable calibration method for enhancing class probability estimates in healthcare-related machine learning tasks.

Nearest neighbors and density-based undersampling for imbalanced data classification with class overlap

While addressing the problem of imbalanced data classification, most existing resampling methods primarily focus on balancing class distribution. However, they often overlook class overlap and fail to adequately consider the feature distributions of different classes. Consequently, when resampling is performed under such conditions, samples within areas of overlap remain susceptible to misclassification, failing to substantially improve overall performance. To address these shortcomings, we propose a novel data resampling technique, Nearest Neighbors and Density-based Undersampling (NDU). This method employs within-class k-nearest neighbors and between-class probability densities to design a weight assignment strategy. Leveraging this strategy, we establish an exclusive metric, the F_factor, to evaluate the importance of majority class samples in overlap areas. Subsequently, NDU promotes a gradient-based segmented undersampling strategy, which applies varying degrees of undersampling to majority class samples across segmented regions. Through experiments on binary imbalanced datasets with class overlap, we evaluate the efficiency of diverse resampling methods concerning classification performance. The results demonstrate that our proposed method effectively addresses class overlap challenges.

Application of Analytical Hierarchy Process in evaluation of neotectonic variability on drainage basin systems in the Edea – Eseka region (SW Cameroon Atlantic Coast)

Complex geology and tectonics of the SW Cameroon Atlantic Coast are responsible for the present-day landscapes of the Edea – Eseka Region (EER). The EER is tectonically active and shows differential tectonic uplift, contrasting relief, variations in erosion rates, in river incision, and in channel gradient. Drainage system divides are dynamic features of a landscape that migrate over time during the development of river networks. To study the neotectonic variability in this region, we investigate the drainage river system and the topographic expression of active regional tectonics across the EER. From the Digital elevation model (DEM, 30 m pixel resolution) using Geographic Information System (GIS) interpretive techniques, we extracted eleven morphometric parameters of thirty-two main drainage basins which were combined with Analytical Hierarchy Process (AHP) method. The inter-relationships between these indices grouped into four categories such as watershed geometry, relief characteristics, drainage texture analysis and regional tilting/uplift; can determine the influence of regional tectonic activity in the shape development of drainage basins. The results of the landscape analysis reveal significant variations of the morphometric parameters within the study area indicate a strong tectonic control. From the AHP values, the area is subdivided into high (∼25 %), moderate (∼43.75 %), and low (∼31.25 %) regional tectonic classes. The spatial distribution of different AHP classes shows a gradational pattern from coast to hinterland, suggesting a gradual decrease (from west to east) in the neotectonic activity in the EER drainage basin systems. The moderate-to-high neotectonic activity (∼68.75 %), demonstrates the complexity of the EER unstable tectonic character due to lithospheric mantle dynamism/asthenospheric upwelling as well as the Cameroon Volcanic Line (CVL) activity.

Achieving High Accuracy in Android Malware Detection through Genetic Programming Symbolic Classifier

The detection of Android malware is of paramount importance for safeguarding users’ personal and financial data from theft and misuse. It plays a critical role in ensuring the security and privacy of sensitive information on mobile devices, thereby preventing unauthorized access and potential damage. Moreover, effective malware detection is essential for maintaining device performance and reliability by mitigating the risks posed by malicious software. This paper introduces a novel approach to Android malware detection, leveraging a publicly available dataset in conjunction with a Genetic Programming Symbolic Classifier (GPSC). The primary objective is to generate symbolic expressions (SEs) that can accurately identify malware with high precision. To address the challenge of imbalanced class distribution within the dataset, various oversampling techniques are employed. Optimal hyperparameter configurations for GPSC are determined through a random hyperparameter values search (RHVS) method developed in this research. The GPSC model is trained using a 10-fold cross-validation (10FCV) technique, producing a set of 10 SEs for each dataset variation. Subsequently, the most effective SEs are integrated into a threshold-based voting ensemble (TBVE) system, which is then evaluated on the original dataset. The proposed methodology achieves a maximum accuracy of 0.956, thereby demonstrating its effectiveness for Android malware detection.

A new data complexity measure for multi-class imbalanced classification tasks

The skewed class distribution and data complexity may severely affect the imbalanced classification results. The cost of classification can be significantly reduced if these data complexity are measured and pre-processed prior to training, particularly when dealing with large-scale and high-dimensional datasets. Although many methods have been proposed to evaluate data complexity, most of them fail to fully consider the interaction among different data characteristics, or the connection between class imbalance and these characteristics, thus posing a serious challenge to effectively evaluate the difficulty of classification. This paper presents a new data complexity measure MFII (multi-factor imbalance index), which measures the combined effects of the skewed class distribution and data characteristics on classification difficulty. In particular, it further comprehensively investigates the impact of overlap size, confusion degree, and sub-cluster structure. VoR (value of resolution) and DoC (degree of consistency) are also proposed to evaluate the resolution and interpretability of complexity measures. The experimental results demonstrate that MFII has lower VoR and a stronger correlation with classification metrics, which indicates that MFII can more accurately evaluate the difficulty of multi-class imbalanced classification tasks.

Effect of environmental drivers on the spatiotemporal distribution of mackerel at age in the Nordic Seas during 2010−20

Abstract A joint spatio–temporal distribution model of mackerel (ages 3–10) was developed to investigate the age-based responses of mackerel to three environmental drivers: sea surface temperature (SST), mixed layer depth, and chlorophyll-a concentration during the summer months 2010–20 in the Nordic Seas. The study showed that SST was the most important variable amongst the ones tested and had the strongest impact on the distribution of the younger age classes (3–5), which had a narrower range of favourable SST and a stronger aversion to cold temperatures than older individuals. Consequently, the impact of SST differed regionally; in the polar front regions, SST explained up to 61% of the variability in the observed density of young individuals, where Arctic water masses likely acted as a barrier to these young individuals. That said, part of it could be confounded with the limited migration capability of young mackerels, which could not reach the furthest frontal regions. In warmer southern waters, the same environmental variables had less explanatory power for mackerel of all ages. Individuals in the south were likely not constrained by temperature and perhaps more influenced by other variables, such as food availability or ocean current (throughout their migration path), for which appropriate data are lacking. Moreover, the model showed that older mackerel were distributed more to the north and west, and their migration pattern changed when the 2013 year-class no longer migrated to the west compared to previous year-classes. Additionally, all-year classes started migrating more eastward from summer 2018.

Incorporating hydraulic gradient and pumping rate into GALDIT framework to assess groundwater vulnerability to salinity in coastal aquifers: a case study from Urmia Plain, Iran.

The critical role of groundwater in meeting diverse needs, including drinking, industrial, and agricultural, highlights the urgency of effective resource management. Excessive groundwater extraction, especially in coastal regions including Urmia Plain in NW Iran, disrupts the equilibrium between freshwater and saline boundaries within aquifers. Influential parameters governing seawater intrusion-groundwater occurrence (G), aquifer hydraulic conductivity (A), the height of groundwater level above the mean sea level (L), distance from the shore (D), impact of the existing status of seawater intrusion (I), and thickness of the saturated aquifer (T)-merge to shape the GALDIT vulnerability index for coastal aquifers. This study enriches the GALDIT framework by incorporating two additional hydrogeological variables: hydraulic gradient (i) and pumping rate (P). This expansion produces seven distinct vulnerability maps (GALDIT, GAiDIT, GAiDIT-P, GALDIT-i, GALDIT-iP, GALDIT-P, GAPDIT). In the Urmia Plain, the traditional GALDIT index reveals vulnerability values ranging from 2 to 8.1, categorized into six classes from negligible to very high vulnerability. However, the modified indices, GAiDIT and GAiDIT-P, yield a three-class categorization, ranging from low to high vulnerability. The introduction of the "i" and "P" parameters in GALDIT-i and GALDIT-iP enhances the precision of vulnerability mapping, altering class distribution and intensifying vulnerability ratings. The eastern, central, and coastal areas of the Urmia Plain demonstrate high to very high vulnerability levels, in contrast to the lower vulnerability observed in the western regions. Both the GALDIT-P (r = 0.82) and GALDIT-iP (r = 0.81) indices show strong correlations with Cl concentration, thereby improving mapping accuracy over the traditional GALDIT index (r = 0.72). A sensitivity analysis highlights the critical influence of the "i" parameter, suggesting its weighting should be revised. Parameter recalibration serves to amplify the significance of "G," "L," "D," and "i" parameters, while diminishing others. The integration of multiple hydrogeological variables considerably enhances the precision of groundwater vulnerability assessments.

Fuzzy Logic Prediction of Hypertensive Disorders in Pregnancy Using the Takagi–Sugeno and C-Means Algorithms

Hypertensive disorders in pregnancy, which include preeclampsia, eclampsia, and chronic hypertension, complicate approximately 10% of all pregnancies in the world, constituting one of the most serious causes of mortality and morbidity in gestation. To help predict the occurrence of hypertensive disorders, a study based on algorithms that help model this health problem using mathematical tools is proposed. This study proposes a fuzzy c-means (FCM) model based on the Takagi–Sugeno (T-S) type of fuzzy rule to predict hypertensive disorders in pregnancy. To test different modeling methodologies, cross-validation comparisons were made between random forest, decision tree, support vector machine, and T-S and FCM methods, which achieved 80.00%, 66.25%, 70.00%, and 90.00%, respectively. The evaluation consisted of calculating the true positive rate (TPR) over the true negative rate (TNR), with equal error rate (EER) curves achieving a percentage of 20%. The learning dataset consisted of a total of 371 pregnant women, of which 13.2% were diagnosed with a condition related to gestational hypertension. The dataset for this study was obtained from the Secretaría de Salud del Estado de Hidalgo (SSEH), México. A random sub-sampling technique was used to adjust the class distribution of the data set, and to eliminate the problem of unbalanced classes. The models were trained using a total of 98 samples. The modeling results indicate that the T-S and FCM method has a higher predictive ability than the other three models in this research.

A dual algorithmic approach to deal with multiclass imbalanced classification problems

Many real-world applications involve multiclass classification problems, and often the data across classes is not evenly distributed. Due to this disproportion, supervised learning models tend to classify instances towards the class with the maximum number of instances, which is a severe issue that needs to be addressed. In multiclass imbalanced data classification, machine learning researchers try to reduce the learning model's bias towards the class with a high sample count. Researchers attempt to reduce this unfairness by either balancing the data before the classifier learns it, modifying the classifier's learning phase to pay more attention to the class with a minimum number of instances, or a combination of both. The existing algorithmic approaches find it difficult to understand the clear boundary between the samples of different classes due to unfair class distribution and overlapping issues. As a result, the minority class recognition rate is poor. A new algorithmic approach is proposed that uses dual decision trees. One is used to create an induced dataset using a PCA based grouping approach and by assigning weights to the data samples followed by another decision tree to learn and predict from the induced dataset. The distinct feature of this algorithmic approach is that it recognizes the data instances without altering their underlying data distribution and is applicable for all categories of multiclass imbalanced datasets. Five multiclass imbalanced datasets from UCI were used to classify the data using our proposed algorithm, and the results revealed that the duo-decision tree approach pays better attention to both the minor and major class samples.

Spatial Distribution of Water Quality Classes of Rawa Pening Lake

Abstract Rawa Pening Lake is a source of water for irrigation and clean water for the people around the lake. The quality of water is the primary concern for sustainable functioning. This study aims to examine the water quality status of the lake under government regulations. The variables are temperature, total dissolved solid (TDS), total suspended solid (TSS), Escherichia coli (E. coli), dissolved oxygen (DO), biological oxygen demand (BOD), chemical oxygen demand, phosphate, nitrate, and oil. The study was conducted during the rainy season, from September to November 2020. It’s because of the season that farmers and the community use more of the lake water. The method used is purposive sampling, where a total of 12 locations represent each village, inlet, and outlet. The data analysis used is Storet to determine the water quality class and Inverse Distance Weighted (IDW) for the spatial distribution of water quality classes. The results showed that the water quality class of the lake suffered mild pollution. TSS and DO were variables that influenced that condition. It can be concluded that the lake has sucked sedimentation as a result of the deposits of mud and sand, which can damage the ecosystem of the lake.

Adversarial Multi-Teacher Distillation for Semi-Supervised Relation Extraction.

The shortage of labeled data has been a long-standing challenge for relation extraction (RE) tasks. Semi-supervised RE (SSRE) is a promising way through annotating unlabeled samples with pseudolabels as additional training data. However, some pseudolabels on unlabeled data might be erroneous and will bring misleading knowledge into SSRE models. For this reason, we propose a novel adversarial multi-teacher distillation (AMTD) framework, which includes multi-teacher knowledge distillation and adversarial training (AT), to capture the knowledge on unlabeled data in a refined way. Specifically, we first develop a general knowledge distillation (KD) technique to learn not only from pseudolabels but also from the class distribution of predictions by different models in existing SSRE methods. To improve the robustness of the model, we further empower the distillation process with a language model-based AT technique. Extensive experimental results on two public datasets demonstrate that our framework significantly promotes the performance of the base SSRE methods.