Random Oversampling Methods Research Articles

Neutrosophic set and optimized deep learning for classification of chicken Eimeria species: a practical solution for poultry industry

AbstractTo optimize infection control and bolster productivity within the poultry industry, it is imperative to accurately classify Chicken Eimeria species. There are several methods for determining Eimeria disease in chickens. Traditional methods involve watching for clinical symptoms, and macroscopic lesions, and studying the parasite’s biology and oocyst morphology. These methods are frequently time-consuming and labor-intensive, necessitating the manual collection and analysis of samples, which can be especially difficult in large chicken farms. Deep learning algorithms, on the other hand, provide automated, accurate, and non-invasive methods for the detection of Eimeria. This paper proposed a classification model for the automatic classification of chicken Eimeria species. The proposed model is mainly based on integrating neutrosophic set theory and InceptionV3 deep-learning architecture. Three primary phases make up the proposed chicken Eimeria species classification model: the data preprocessing phase, the neutrosophic image conversion phase, and the image classification phase. To address the issue of class imbalance in the adopted dataset and enhance the model’s generalizability, the random oversampling method, and data augmentation techniques are employed during the data preprocessing phase. The preprocessed data is considered to feed the neutrosophic set-based segmentation algorithm, where true, false, and intermediate subsets are extracted. Finally, the true subset is utilized to feed the optimized InceptionV3. To determine the optimal hyperparameter values for InceptionV3, a modified version of the Brown Bear optimization algorithm is proposed in this paper. To evaluate the effectiveness of the proposed model, a real benchmark dataset comprising images of different Eimeria species is adopted. The experimental results revealed that the proposed model offers a more efficient and accurate alternative to traditional methods and state-of-the-art models, enabling faster and more effective diagnosis and treatment of Eimeria infections. It achieved an overall accuracy, specificity, sensitivity, and F1-score of nearly 100%. Additionally, the results showed that the high performance of the proposed model can reduce labor costs and boost throughput, thereby enhancing economic viability even more.

Machine-Learning-Assisted Identification of Steam Channeling after Cyclic Steam Stimulation in Heavy-Oil Reservoirs

Cyclic steam stimulation (CSS) is one efficient technology for enhancing heavy-oil recovery. However, after multiple cycles, steam channeling severely limits the thermal recovery because high-temperature steam preferentially breaks through to the producers. To solve the issues of steam breakthrough, it is essentially important and necessary to recognize steam channeling. In this work, a machine-learning-assisted identification model, based on a random-forest ensemble algorithm, is developed to predict the occurrence of steam channeling during steam huff-and-puff processes. The set of feature attributes is constructed based on the permeability ratio, steam quality, and steam-injection speed, which provides the reference for the construction of the training-sample set, steam-channeling reconstruction set, and prediction set. Based on the realistic data, the Pearson correlation coefficient is implemented to confirm the linear correlation among different characteristics; thus, the dimension reduction of the characteristic parameters is achieved. The random oversampling method is adopted to treat the unbalanced training-sample set. Our results show that this model can accurately describe the current state of steam channeling and predict steam propagation in the following cycles.

Metro Track Geometry Defect Identification Model Based on Car-Body Vibration Data and Differentiable Architecture Search

Efficient and low-cost modes for detecting metro track geometry defects (TGDs) are essential for condition-prediction-based preventive maintenance, which can help improve the safety of metro operations and reduce the maintenance cost of metro tracks. Compared with the traditional TGD detection method that utilizes the track geometry car, the method that uses a portable detector to acquire the car-body vibration data (CVD) can be used on an ordinary in-service train without occupying the metro schedule line, thereby improving efficiency and reducing the cost. A convolutional neural network-based identification model for TGD, built on a differentiable architecture search, is proposed in this study to employ only the CVD acquired by a portable detector for integrated identification of the type and severity level of TGDs. Second, the random oversampling method is introduced, and a strategy for applying this method is proposed to improve the poor training effect of the model caused by the natural class-imbalance problem arising from the TGD dataset. Subsequently, a comprehensive performance-evaluation metric (track geometry defect F-score) is designed by considering the actual management needs of the metro infrastructure. Finally, a case study is conducted using actual field data collected from Beijing Subway to validate the proposed model.

Classification Performance of Machine Learning Methods for Identifying Resistance, Resilience, and Susceptibility to Haemonchus contortus Infections in Sheep.

This study investigated the feasibility of using easy-to-measure phenotypic traits to predict sheep resistant, resilient, and susceptible to gastrointestinal nematodes, compared the classification performance of multinomial logistic regression (MLR), linear discriminant analysis (LDA), random forest (RF), and artificial neural network (ANN) methods, and evaluated the applicability of the best classification model on each farm. The database comprised 3654 records of 1250 Santa Inês sheep from 6 farms. The animals were classified into resistant (2605 records), resilient (939 records), and susceptible (110 records) according to fecal egg count and packed cell volume. A random oversampling method was performed to balance the dataset. The classification methods were fitted using the information of age class, the month of record, farm, sex, Famacha© degree, body weight, and body condition score as predictors, and the resistance, resilience, and susceptibility to gastrointestinal nematodes as the target classes to be predicted considering data from all farms randomly. An additional leave-one-farm-out cross-validation technique was used to assess prediction quality across farms. The MLR and LDA models presented good performances in predicting susceptible and resistant animals. The results suggest that the use of readily available records and easily measurable traits may provide useful information for supporting management decisions at the farm level.

Construction of Mitochondrial Protection and Monitoring Model of Lon Protease Based on Machine Learning under Myocardial Ischemia Environment.

The localization of a protein's submitochondrial structure is important for therapeutic design of associated disorders caused by mitochondrial abnormalities because many human diseases are directly tied to mitochondria. When Lon protease expression changes, glycolysis replaces respiratory metabolism in the cell, which is a common occurrence in cancer cells. The fact that protein formation is a dynamic research object makes it impossible to reproduce the unique living environment of proteins in an experimental setting, which surely makes it more challenging to determine protein function through experiments. This research suggests a model of Lon protease-based mitochondrial protection under myocardial ischemia based on ML (machine learning). To ensure the balance of all submitochondrial proteins, the data set is processed using a random oversampling method, each overlapping fixed-length subsequence that is created from the protein sequence functions as a channel in the convolution layer. The results demonstrate that applying the oversampling strategy increases the ROC value by 17.6%-21.3%. Our prediction method is successful as evidenced by the fact that ML prediction outperforms the predictions of other conventional classifiers.

Real-Time Pedestrian Conflict Prediction Model at the Signal Cycle Level Using Machine Learning Models

Compared with traditional traffic studies, real-time safety analyses can be better incorporated into proactive traffic management strategies to improve traffic safety. However, few studies have investigated the real-time pedestrian safety model. Intersections usually have mixed traffic conditions with more pedestrian-vehicle interactions. This paper uses conflict indicators, PET (Post Encroachment Time) and TTC (Time to Collision) to identify pedestrians’ conflicts from CCTV (closed-circuit television) videos. The high-resolution traffic data from the Automated Traffic Signal Performance Measures (ATSPM) system are used to derive traffic flow-related variables. The pedestrian exposure is also estimated. Pedestrians’ conflicts are predicted using multiple machine learning models and Logistic Regression. The resampling methods, random over-sampling, and random under-sampling are compared. The best model, Extreme Gradient Boosting (XGBT) with random over-sampling method can achieve AUC (area under the ROC curve) value of 0.841 and recall value of 0.739 on the test data set. The proposed model can predict pedestrians’ conflicts one cycle ahead, which can be 2–3 min. The proposed model has the potential to be implemented in the Connected and Automated Vehicles (CAV) environment to adjust signal timing accordingly and enhance traffic safety.

Detecting Internet of Things Attacks by Using Hybrid Learning and Feature Selection Method

Internet of Things (IoT) produces an enormous amount of data, which is used in all areas of our lives and increases the number of data on the Internet with each passing day. Smart watches, robot vacuum cleaners, refrigerators with cameras, and more can all be considered IoT devices. Ease of access to the Internet provides people with advantages as well as disadvantages. Malware and intruders have easier access to the devices we use and our information via the internet. At this point, data security gains great importance especially in IoT devices because accessing our personal data via smart watches or refrigerators we use can pose a great threat to individuals and their families. This study focus the importance of data preprocessing and developing a hybrid machine learning-based intrusion detection system (IDS) for IoT. Decision Tree, which is a popular machine learning algorithm, and n_Balot dataset were preferred for investigations. Accordingly, it is aimed to create a hybrid model by applying K-means and Decision Tree algorithms to the n_Balot dataset with under sampling and feature selection. In the data preprocessing, feature selection was performed with Chi-Square method and under sampling performed with RandomOverSampling method. Then, clustering was done by applying K-means to the processed dataset, and the results obtained with the clustering were classified with the Decision tree algorithm. As a result of the study, while the error rate was 0.39% in the predictions made only with the decision tree, the error rate was reduced to 0.01% with the developed hybrid model.

Performance Analysis of Two-Stage Iterative Ensemble Method over Random Oversampling Methods on Multiclass Imbalanced Datasets

Data imbalance occurring among multiclass datasets is very common in real-world applications. Existing studies reveal that various attempts were made in the past to overcome this multiclass imbalance problem, which is a severe issue related to the typical supervised machine learning methods such as classification and regression. But, still there exists a need to handle the imbalance problem efficiently as the datasets include both safe and unsafe minority samples. Most of the widely used oversampling techniques like SMOTE and its variants face challenges in replicating or generating the new data instances for balancing them across multiple classes, particularly when the imbalance is high and the number of rare samples count is too minimal thus leading the classifier to misclassify the data instances. To lessen this problem, we proposed a new data balancing method namely a two-stage iterative ensemble method to tackle the imbalance in multiclass environment. The proposed approach focuses on the rare minority sample’s influence on learning from imbalanced datasets and the main idea of the proposed approach is to balance the data without any change in class distribution before it gets trained by the learner such that it improves the learner’s learning process. Also, the proposed approach is compared against two widely used oversampling techniques and the results reveals that the proposed approach shows a much significant improvement in the learning process among the multiclass imbalanced data.

A novel melanoma prediction model for imbalanced data using optimized SqueezeNet by bald eagle search optimization.

Skin lesion classification plays a crucial role in diagnosing various gene and related local medical cases in the field of dermoscopy. In this paper, a new model for the classification of skin lesions as either normal or melanoma is presented. The proposed melanoma prediction model was evaluated on a large publicly available dataset called ISIC 2020. The main challenge of this dataset is severe class imbalance. This paper proposes an approach to overcome this problem using a random over-sampling method followed by data augmentation. Moreover, a new hybrid version of a convolutional neural network architecture and bald eagle search (BES) optimization is proposed. The BES algorithm is used to find the optimal values of the hyperparameters of a SqueezeNet architecture. The proposed melanoma skin cancer prediction model obtained an overall accuracy of 98.37%, specificity of 96.47%, sensitivity of 100%, f-score of 98.40%, and area under the curve of 99%. The experimental results showed the robustness and efficiency of the proposed model compared with VGG19, GoogleNet, and ResNet50. Additionally, the results showed that the proposed model was very competitive compared with the state of the art.

Evaluating resampling methods and structured features to improve fall incident report identification by the severity level.

This study aims to improve the classification of the fall incident severity level by considering data imbalance issues and structured features through machine learning. We present an incident report classification (IRC) framework to classify the in-hospital fall incident severity level by addressing the imbalanced class problem and incorporating structured attributes. After text preprocessing, bag-of-words features, structured text features, and structured clinical features were extracted from the reports. Next, resampling techniques were incorporated into the training process. Machine learning algorithms were used to build classification models. IRC systems were trained, validated, and tested using a repeated and randomly stratified shuffle-split cross-validation method. Finally, we evaluated the system performance using the F1-measure, precision, and recall over 15 stratified test sets. The experimental results demonstrated that the classification system setting considering both data imbalance issues and structured features outperformed the other system settings (with a mean macro-averaged F1-measure of 0.733). Considering the structured features and resampling techniques, this classification system setting significantly improved the mean F1-measure for the rare class by 30.88% (P value < .001) and the mean macro-averaged F1-measure by 8.26% from the baseline system setting (P value < .001). In general, the classification system employing the random forest algorithm and random oversampling method outperformed the others. Structured features provide essential information for categorizing the fall incident severity level. Resampling methods help rebalance the class distribution of the original incident report data, which improves the performance of machine learning models. The IRC framework presented in this study effectively automates the identification of fall incident reports by the severity level.

Analysis of Consciousness Level Using Galvanic Skin Response during Therapeutic Effect.

The neurological status of patients in the Intensive Care Units (ICU) is determined by the Glasgow Coma Scale (GCS). Patients in coma are thought to be unaware of what is happening around them. However, many studies show that the family plays an important role in the recovery of the patient and is a great emotional resource. In this study, Galvanic Skin Response (GSR) signals were analyzed from 31 patients with low consciousness levels between GCS 3 and 8 to determine relationship between consciousness level and GSR signals as a new approach. The effect of family and nurse on unconscious patients was investigated by GSR signals recorded with a new proposed protocol. The signals were recorded during conversation and touching of the patient by the nurse and their families. According to numerical results, the level of consciousness can be separated using GSR signals. Also, it was found that family and nurse had statistically significant effects on the patient. Patients with GCS 3,4, and 5 were considered to have low level of consciousness, while patients with GCS 6,7, and 8 were considered to have high level of consciousness. According to our results, it is obtained lower GSR amplitude in low GCS (3, 4, 5) compared to high GCS (7, 8). It was concluded that these patients were aware of therapeutic affect although they were unconscious. During the classification stage of this study, the class imbalance problem, which is common in medical diagnosis, was solved using Synthetic Minority Over-Sampling Technique (SMOTE), Adaptive Synthetic Sampling (ADASYN) and random oversampling methods. In addition, level of consciousness was classified with 92.7% success using various decision tree algorithms. Random Forest was the method which provides higher accuracy compared to all other methods. The obtained results showed that GSR signal analysis recorded in different stages gives very successful GCS score classification performance according to literature studies.

Mortality Prediction from Hospital-Acquired Infections in Trauma Patients Using an Unbalanced Dataset.

ObjectivesMachine learning has been widely used to predict diseases, and it is used to derive impressive knowledge in the healthcare domain. Our objective was to predict in-hospital mortality from hospital-acquired infections in trauma patients on an unbalanced dataset.MethodsOur study was a cross-sectional analysis on trauma patients with hospital-acquired infections who were admitted to Shiraz Trauma Hospital from March 20, 2017, to March 21, 2018. The study data was obtained from the surveillance hospital infection database. The data included sex, age, mechanism of injury, body region injured, severity score, type of intervention, infection day after admission, and microorganism causes of infections. We developed our mortality prediction model by random under-sampling, random over-sampling, clustering (k-mean)-C5.0, SMOTE-C5.0, ADASYN-C5.5, SMOTE-SVM, ADASYN-SVM, SMOTE-ANN, and ADASYN-ANN among hospital-acquired infections in trauma patients. All mortality predictions were conducted by IBM SPSS Modeler 18.ResultsWe studied 549 individuals with hospital-acquired infections in a trauma hospital in Shiraz during 2017 and 2018. Prediction accuracy before balancing of the dataset was 86.16%. In contrast, the prediction accuracy for the balanced dataset achieved by random under-sampling, random over-sampling, clustering (k-mean)-C5.0, SMOTE-C5.0, ADASYN-C5.5, and SMOTE-SVM was 70.69%, 94.74%, 93.02%, 93.66%, 90.93%, and 100%, respectively.ConclusionsOur findings demonstrate that cleaning an unbalanced dataset increases the accuracy of the classification model. Also, predicting mortality by a clustered under-sampling approach was more precise in comparison to random under-sampling and random over-sampling methods.

Data Augmentation for Electricity Theft Detection Using Conditional Variational Auto-Encoder

Due to the strong concealment of electricity theft and the limitation of inspection resources, the number of power theft samples mastered by the power department is insufficient, which limits the accuracy of power theft detection. Therefore, a data augmentation method for electricity theft detection based on the conditional variational auto-encoder (CVAE) is proposed. Firstly, the stealing power curves are mapped into low dimensional latent variables by using the encoder composed of convolutional layers, and the new stealing power curves are reconstructed by the decoder composed of deconvolutional layers. Then, five typical attack models are proposed, and the convolutional neural network is constructed as a classifier according to the data characteristics of stealing power curves. Finally, the effectiveness and adaptability of the proposed method is verified by a smart meters’ data set from London. The simulation results show that the CVAE can take into account the shapes and distribution characteristics of samples at the same time, and the generated stealing power curves have the best effect on the performance improvement of the classifier than the traditional augmentation methods such as the random oversampling method, synthetic minority over-sampling technique, and conditional generative adversarial network. Moreover, it is suitable for different classifiers.

BCV-Predictor: A bug count vector predictor of a successive version of the software system

Predicting the number of bugs in a software system intensifies the software quality and turns down the testing effort required in software development. It reduces the overall cost of software development. The evolution of hardware, platform, and user requirements leads to develop the next version of a software system. In this article, we formulate a problem and its novel solution, i.e., we are considering the prediction of the bug count vector of a successive version of a software system. After predicting the bug count vector in the next version of a software, the developer team leader can adequately allocate the developers in respective fault dense modules, in a more faulty dense module, more number of developers required. We have conducted our experiment over seven PROMISE repository datasets of different versions. We build metadata using a concatenation of different versions of the same software system for conducting experiments. We proposed a novel architecture using deep learning called BCV-Predictor. BCV-Predictor predicts the bug count vector of the next version software system; it is trained using metadata. To the best of our knowledge, no such work has been done in these aspects. We also address overfitting and class imbalance problem using random oversampling method and dropout regularization techniques. We conclude that BCV-Predictor is conducive to predicting the bug count vector of the next version of the software. We found five out of seven meta datasets reaches to more than 80% accuracy. In all seven meta datasets, Mean Squared Error (MSE) lies from 0.71 to 4.715, Mean Absolute Error (MAE) lies from 0.22 to 1.679, MSE and MAE over validation set lie between 0.84 to 4.865, and 0.22 to 1.709 respectively. We also compared the performance of BCV-Predictor with eleven baselines techniques and found the proposed approach outperform on most of the meta-datasets.

A survey on addressing high-class imbalance in big data

In a majority–minority classification problem, class imbalance in the dataset(s) can dramatically skew the performance of classifiers, introducing a prediction bias for the majority class. Assuming the positive (minority) class is the group of interest and the given application domain dictates that a false negative is much costlier than a false positive, a negative (majority) class prediction bias could have adverse consequences. With big data, the mitigation of class imbalance poses an even greater challenge because of the varied and complex structure of the relatively much larger datasets. This paper provides a large survey of published studies within the last 8 years, focusing on high-class imbalance (i.e., a majority-to-minority class ratio between 100:1 and 10,000:1) in big data in order to assess the state-of-the-art in addressing adverse effects due to class imbalance. In this paper, two techniques are covered which include Data-Level (e.g., data sampling) and Algorithm-Level (e.g., cost-sensitive and hybrid/ensemble) Methods. Data sampling methods are popular in addressing class imbalance, with Random Over-Sampling methods generally showing better overall results. At the Algorithm-Level, there are some outstanding performers. Yet, in the published studies, there are inconsistent and conflicting results, coupled with a limited scope in evaluated techniques, indicating the need for more comprehensive, comparative studies.

Machine learning approaches to supporting the identification of photoreceptor-enriched genes based on expression data

BackgroundRetinal photoreceptors are highly specialised cells, which detect light and are central to mammalian vision. Many retinal diseases occur as a result of inherited dysfunction of the rod and cone photoreceptor cells. Development and maintenance of photoreceptors requires appropriate regulation of the many genes specifically or highly expressed in these cells. Over the last decades, different experimental approaches have been developed to identify photoreceptor enriched genes. Recent progress in RNA analysis technology has generated large amounts of gene expression data relevant to retinal development. This paper assesses a machine learning methodology for supporting the identification of photoreceptor enriched genes based on expression data.ResultsBased on the analysis of publicly-available gene expression data from the developing mouse retina generated by serial analysis of gene expression (SAGE), this paper presents a predictive methodology comprising several in silico models for detecting key complex features and relationships encoded in the data, which may be useful to distinguish genes in terms of their functional roles. In order to understand temporal patterns of photoreceptor gene expression during retinal development, a two-way cluster analysis was firstly performed. By clustering SAGE libraries, a hierarchical tree reflecting relationships between developmental stages was obtained. By clustering SAGE tags, a more comprehensive expression profile for photoreceptor cells was revealed. To demonstrate the usefulness of machine learning-based models in predicting functional associations from the SAGE data, three supervised classification models were compared. The results indicated that a relatively simple instance-based model (KStar model) performed significantly better than relatively more complex algorithms, e.g. neural networks. To deal with the problem of functional class imbalance occurring in the dataset, two data re-sampling techniques were studied. A random over-sampling method supported the implementation of the most powerful prediction models. The KStar model was also able to achieve higher predictive sensitivities and specificities using random over-sampling techniques.ConclusionThe approaches assessed in this paper represent an efficient and relatively inexpensive in silico methodology for supporting large-scale analysis of photoreceptor gene expression by SAGE. They may be applied as complementary methodologies to support functional predictions before implementing more comprehensive, experimental prediction and validation methods. They may also be combined with other large-scale, data-driven methods to facilitate the inference of transcriptional regulatory networks in the developing retina. Furthermore, the methodology assessed may be applied to other data domains.