Classification Accuracy Performance Research Articles

Application of machine learning models based on decision trees in classifying the factors affecting mortality of COVID-19 patients in Hamadan, Iran

BackgroundDue to the high mortality of COVID-19 patients, the use of a high-precision classification model of patient’s mortality that is also interpretable, could help reduce mortality and take appropriate action urgently. In this study, the random forest method was used to select the effective features in COVID-19 mortality and the classification was performed using logistic model tree (LMT), classification and regression tree (CART), C4.5, and C5.0 tree based on important features.MethodsIn this retrospective study, the data of 2470 COVID-19 patients admitted to hospitals in Hamadan, west Iran, were used, of which 75.02% recovered and 24.98% died. To classify, at first among the 25 demographic, clinical, and laboratory findings, features with a relative importance more than 6% were selected by random forest. Then LMT, C4.5, C5.0, and CART trees were developed and the accuracy of classification performance was evaluated with recall, accuracy, and F1-score criteria for training, test, and total datasets. At last, the best tree was developed and the receiver operating characteristic curve and area under the curve (AUC) value were reported.ResultsThe results of this study showed that among demographic and clinical features gender and age, and among laboratory findings blood urea nitrogen, partial thromboplastin time, serum glutamic-oxaloacetic transaminase, and erythrocyte sedimentation rate had more than 6% relative importance. Developing the trees using the above features revealed that the CART with the values of F1-score, Accuracy, and Recall, 0.8681, 0.7824, and 0.955, respectively, for the test dataset and 0.8667, 0.7834, and 0.9385, respectively, for the total dataset had the best performance. The AUC value obtained for the CART was 79.5%.ConclusionsFinding a highly accurate and qualified model for interpreting the classification of a response that is considered clinically consequential is critical at all stages, including treatment and immediate decision making. In this study, the CART with its high accuracy for diagnosing and classifying mortality of COVID-19 patients as well as prioritizing important demographic, clinical, and laboratory findings in an interpretable format, risk factors for prognosis of COVID-19 patients mortality identify and enable immediate and appropriate decisions for health professionals and physicians.

Early Prediction of Planning Adaptation Requirement Indication Due to Volumetric Alterations in Head and Neck Cancer Radiotherapy: A Machine Learning Approach.

Simple SummaryEarly prediction of significant alterations of head and neck (HN) cancer volume due to radiation therapy (RT) could provide an indication for necessary planning adaptations of the RT dose, tumor and organs at risk anatomy. However, the irregularities of the underlying cancer tissue and the patient-specific responses to RT render the prognostics for the tumor’s behavior exceedingly complex. In this study, a data-driven machine learning approach is proposed that incorporates the radiomic features of the low-dosage cone beam CT (CBCT) images clinically used in image-guided radiotherapy treatments in a feature selection and classification framework. The proposed model achieved high prediction performance, while able to identify indicative image characteristics for early prediction, further investigated in terms of their implications in HN cancer treated with RT.Background: During RT cycles, the tumor response pattern could affect tumor coverage and may lead to organs at risk of overdose. As such, early prediction of significant volumetric changes could therefore reduce potential radiation-related adverse effects. Nevertheless, effective machine learning approaches based on the radiomic features of the clinically used CBCT images to determine the tumor volume variations due to RT not having been implemented so far. Methods: CBCT images from 40 HN cancer patients were collected weekly during RT treatment. From the obtained images, the Clinical Target Volume (CTV) and Parotid Glands (PG) regions of interest were utilized to calculate 104 delta-radiomics features. These features were fed on a feature selection and classification procedure for the early prediction of significant volumetric alterations. Results: The proposed framework was able to achieve 0.90 classification performance accuracy while detecting a small subset of discriminative characteristics from the 1st week of RT. The selected features were further analyzed regarding their effects on temporal changes in anatomy and tumor response modeling. Conclusion: The use of machine learning algorithms offers promising perspectives for fast and reliable early prediction of large volumetric deviations as a result of RT treatment, exploiting hidden patterns in the overall anatomical characteristics.

Systematic exploration of the underlying mechanism of gemcitabine resistance in pancreatic adenocarcinoma.

Resistance to gemcitabine is the main challenge of chemotherapy for pancreatic ductal adenocarcinoma (PDAC). Hence, the development of a response signature to gemcitabine is essential for precision therapy of PDAC. However, existing quantitative signatures of gemcitabine are susceptible to batch effects and variations in sequencing platforms. Therefore, based on within‐sample relative expression ordering of pairwise genes, we developed a transcriptome‐based gemcitabine signature consisting of 28 gene pairs (28‐GPS) that could predict response to gemcitabine for PDAC at the individual level. The 28‐GPS was superior to previous quantitative signatures in terms of classification accuracy and prognostic performance. Resistant samples classified by 28‐GPS showed poorer overall survival, higher genomic instability, lower immune infiltration, higher metabolic level and higher‐fidelity DNA damage repair compared with sensitive samples. In addition, we found that gemcitabine combined with phosphoinositide 3‐kinase (PI3K) inhibitor may be an alternative treatment strategy for PDAC. Single‐cell analysis revealed that cancer cells in the same PDAC sample showed both the characteristics of sensitivity and resistance to gemcitabine, and the activation of the TGFβ signalling pathway could promote progression of PDAC. In brief, 28‐GPS could robustly determine whether PDAC is resistant or sensitive to gemcitabine, and may be an auxiliary tool for clinical treatment.

Hybrid data-scaling method for fault classification of compressors

Fault diagnosis of compressors in air conditioners is challenging owing to the imbalance and nonlinearity of the vibration data because of the contrasting failure modes. This study proposes a hybrid data-scaling method combining Min-Max normalization and Box-Cox transform methods. The Min-Max normalization method was employed to scale the multi-domain data with different failure modes whereas the Box-Cox transformation method transformed the nonlinear distributions of features into normal distributions, thereby rendering the classification of unbalanced and insufficient data easier. The primary features for fault diagnosis were extracted using an embedded feature extraction method and were consequently used to generate fault classification models such as support vector machine (SVM), K-nearest neighbor (KNN), random forest (RF), and extreme gradient boosting (XGBoost) to classify refrigerant deficiencies and motor demagnetization defects. The proposed hybrid data-scaling demonstrates the most accurate and robust classification performance relative to conventional data-scaling methods, regardless of the types of classification models.

A Fine‐Grained Flash‐Memory Fragment Recognition Approach for Low‐Level Data Recovery

Data recovery from flash memory in the mobile device can effectively reduce the loss caused by data corruption. Type recognition of data fragment is an essential prerequisite to the low-level data recovery. Previous works in this field classify data fragment based on its file type. Still, the classification efficiency is low, especially when the data fragment is a part of a composite file. We propose a fine-grained approach to classifying data fragment from the low-level flash memory to improve the classification accuracy and efficiency. The proposed method redefines flash-memory-page data recognition problem based on the encoding format of the data segment, and applies a hybrid machine learning algorithm to detect the data type of the flash page. The hybrid algorithm can significantly decompose the given data space and reduce the cost of training. The experimental results show that our method achieves better classification accuracy and higher time performance than the existing methods.

Machine learning-based classification of the movements of children with profound or severe intellectual or multiple disabilities using environment data features.

Communication interventions have broadened from dialogical meaning-making, assessment approaches, to remote-controlled interactive objects. Yet, interpretation of the mostly pre-or protosymbolic, distinctive, and idiosyncratic movements of children with intellectual disabilities (IDs) or profound intellectual and multiple disabilities (PIMD) using computer-based assistive technology (AT), machine learning (ML), and environment data (ED: location, weather indices and time) remain insufficiently unexplored. We introduce a novel behavior inference computer-based communication-aid AT system structured on machine learning (ML) framework to interpret the movements of children with PIMD/IDs using ED. To establish a stable system, our study aimed to train, cross-validate (10-fold), test and compare the classification accuracy performance of ML classifiers (eXtreme gradient boosting [XGB], support vector machine [SVM], random forest [RF], and neural network [NN]) on classifying the 676 movements to 2, 3, or 7 behavior outcome classes using our proposed dataset recalibration (adding ED to movement datasets) with or without Boruta feature selection (53 child characteristics and movements, and ED-related features). Natural-child-caregiver-dyadic interactions observed in 105 single-dyad video-recorded (30-hour) sessions targeted caregiver-interpreted facial, body, and limb movements of 20 8-to 16-year-old children with PIMD/IDs and simultaneously app-and-sensor-collected ED. Classification accuracy variances and the influences of and the interaction among recalibrated dataset, feature selection, classifiers, and classes on the pooled classification accuracy rates were evaluated using three-way ANOVA. Results revealed that Boruta and NN-trained dataset in class 2 and the non-Boruta SVM-trained dataset in class 3 had >76% accuracy rates. Statistically significant effects indicating high classification rates (>60%) were found among movement datasets: with ED, non-Boruta, class 3, SVM, RF, and NN. Similar trends (>69%) were found in class 2, NN, Boruta-trained movement dataset with ED, and SVM and RF, and non-Boruta-trained movement dataset with ED in class 3. These results support our hypotheses that adding environment data to movement datasets, selecting important features using Boruta, using NN, SVM and RF classifiers, and classifying movements to 2 and 3 behavior outcomes can provide >73.3% accuracy rates, a promising performance for a stable ML-based behavior inference communication-aid AT system for children with PIMD/IDs.

An Improved Homogeneous Ensemble Technique for Early Accurate Detection of Type 2 Diabetes Mellitus (T2DM)

The objective of the present study is to improve the genetic algorithm (GA) supremacy in selecting the most suitable and relevant features within a highly dimensional dataset. This results in cost reduction and improving classification performance. During text classification, employing terms such as features using vector space representation can result in a high dimensionality of future space. This condition presents some issues, including high computation cost in data analysis and deteriorating classification accuracy performance. Several computational feature selection techniques can be applied in eliminating the least significant features within a dataset, including a genetic algorithm. The present study improved the performance of the classifier in classifying Pima Indian diabetes data. Despite the popularity of GA in the feature selection area, it does not provide the most optimal features due to one of its underlying issues: premature convergence due to insufficient population diversity in the future generations. GA was improved in its crossover operator using two steps: define a variable slice point on the size of the gene to be interchanged for every offspring generation and apply feature frequency scores in deciding the interchanging of genes. The above obtained results to the proposed technique will be better results than the results for standard GA. Our proposed algorithm attained an accuracy of 97.5%, precision of 98, recall of 97% and F1-score of 97%.

Active Learning Algorithm Based on Fast Optimization of Support Vectors

For the solution to the problems of being difficult to gain mass class-labeled samples in the supervised learning process and of reducing the cost of data labeling, a fast optimization of support vectors based on convex hull vector is proposed with the learning mechanism of Support Vector Machine (SVM). By means of calculating the hull vectors of the sample set, label those chosen hull vectors that are largest possible to be support vectors, and also add the unlabeled samples with high confidence coefficient of classifiers to the training sample set. The very information beneficial to the learner in the unlabeled samples set will be exploited. Hence, the thick convex hull method and the modified weighted SVM are separately directed for the nonlinear separable problem and the unbalanced training sample set. Via experimental testing on the UCI data set, the results demonstrate that the algorithm harvests SVM classifiers of higher classification accuracy and better generalization performance with fewer labeled samples, so as to cut down the labeling cost of samples for SVM training and learning.

Identifying and Mapping Alteration Minerals Using HySpex Airborne Hyperspectral Data and Random Forest Algorithm

Airborne hyperspectral remote sensing data provide rapid, non-destructive, and near laboratory quality reflectance spectra for mineral mapping and lithological discrimination, thereby ushering an innovative era of remote sensing. In this study, NEO HySpex cameras, which comprise 504 spectral channels in the spectral ranges of 0.4–1.0 μm and 1.0–2.5 μm, were mounted on a delta wing XT-912 aircraft. The designed flexibility and modular nature of the HySpex aircraft hyperspectral imaging system made it relatively easy to test, transport, install, and remove the system multiple times before the acquisition flights. According to the design fight plan, including the route distance, length, height, and flight speed, we acquired high spectral and spatial resolutions airborne hyperspectral images of Yudai porphyry Cu (Au, Mo) mineralization in Kalatag District, Eastern Tianshan terrane, Northwest China. By comparing the features of the HySpex hyperspectral data and standard spectra data from the United States Geological Survey database, endmember pixels of spectral signatures for most alteration mineral assemblages (goethite, hematite, jarosite, kaolinite, calcite, epidote, and chlorite) were extracted. After a HySpex data processing workflow, the distribution of alteration mineral assemblages (iron oxide/hydroxide, clay, and propylitic alterations) was mapped using the random forest (RF) algorithm. The experiments demonstrated that the workflow for processing data and RF algorithm is feasible and active, and show a good performance in classification accuracy. The overall classification accuracy and Kappa classification of alteration mineral identification were 73.08 and 65.73%, respectively. The main alteration mineral assemblages were primarily distributed around pits and grooves, consistent with field-measured data. Our results confirm that HySpex airborne hyperspectral data have potential application in basic geology survey and mineral exploration, which provide a viable alternative for mineral mapping and identifying lithological units at a high spatial resolution for large areas and inaccessible terrains.

Multi-granularity relabeled under-sampling algorithm for imbalanced data

The imbalanced classification problem turns out to be one of the important and challenging problems in data mining and machine learning. The performances of traditional classifiers will be severely affected by many data problems, such as class imbalanced problem, class overlap and noise. When the number of one class in the data set is larger than other classes, class imbalanced problem will inevitably occur. Therefore, many researchers are committed to solving the problem of category imbalance and improving the overall classification performances of the classifier. The Tomek-Link algorithm was only used to clean data when it was proposed. In recent years, there have been reports of combining Tomek-Link algorithm with sampling technique. The Tomek-Link sampling algorithm can effectively reduce the class overlap on data, remove the majority instances that are difficult to distinguish, and improve the algorithm classification accuracy. However, the Tomek-Links under-sampling algorithm only considers the boundary instances that are the nearest neighbors to each other globally and ignores the potential local overlapping instances. When the number of minority instances is small, the under-sampling effect is not satisfactory, and the performance improvement of the classification model is not obvious. Therefore, on the basis of Tomek-Link, a multi-granularity relabeled under-sampling algorithm (MGRU) is proposed. This algorithm fully considers the local information of the data set in the local granularity subspace, and detects the local potential overlapping instances in the data set. Then, the overlapped majority instances are eliminated according to the global relabeled index value, which effectively expands the detection range of Tomek-Links. The simulation results show that when we select the optimal global relabeled index value for under-sampling, the classification accuracy and generalization performance of the proposed under-sampling algorithm are significantly better than other baseline algorithms.

상호 다중 모델을 이용한 멀티로터 프로펠러 고장 감지

Many studies are being promoted due to the miniaturization of equipment installed in the UAV(Unmanned Aerial Vehicle). Among them, the quadrotor of MAV(Multirotor Aerial vehicle) is the most popular UAV and has been developed in various fields. Practical utilization of UAV requires stable flight or emergency action in fault of UAV parts, but a quadrotor with one motor damaged cannot perform stable flight due to unbalanced force applied to the quadrotor frame. For this reason the development of hexa- or octorotor with more motors is underway and the need to develop FDI(Fault Diagnosis and Isolation) algorithms to use with MAV is increasing. In this paper we designed a simulation based on MAV dynamic and FDI used to classify fault that occurred in the simulation. For fault diagnosis the model based FDI algorithm IMM(Interacting Multiple Model) was applied because the fault affects the system dynamic and output. IMM uses multiple filter models in simultaneously and then compare to the filters estimation and target system output to give weight to suitable filter model. IMM showed accurate and fast fault perceive and classification performance when a fault occurred in the MAV simulation.

Multi-layer adaptive convolutional neural network unsupervised domain adaptive bearing fault diagnosis method

Deep learning provides a feasible fault diagnosis method for intelligent mechanical systems. However, this method requires a large amount of marking data, which greatly limits its application in the actual industry. Therefore, this paper proposes a multi-layer adaptive convolutional neural network unsupervised domain adaptive bearing fault diagnosis method (MACNN), which is especially suitable for bearing fault classification under variable working conditions. First, a new method to improve domain alignment is proposed (LD-CORAL). This method uses Log-Euclidean distance to measure deep coral loss, which solves the problem that the covariance matrix cannot be aligned correctly in the manifold structure. Then, it proposes multi-layer adaptation of LD-CORAL loss in the fully connected layer, and combines center-based discriminative loss to improve the feature learning ability of the model, which can improve the classification accuracy and domain adaptation performance of the model. Finally, in order to verify the effectiveness and feasibility of the proposed method, the method is applied to the multi-fault diagnosis of gearbox bearings under variable working conditions. Comparing the classification results of different methods, the conclusion shows that this method is more effective for bearing fault classification under variable working conditions.

Seleksi Fitur dengan Artificial Bee Colony untuk Optimasi Klasifikasi Data Teh menggunakan Support Vector Machine

Tea quality can be recognized through the aroma it produces. Tea classification using e-nose generally only detects aroma using a general gas sensor. However, redundancy of sensor features can cause a decreasing in the system performance. Therefore we need a system that can select features so the classification performance becomes optimal. A software system of feature selection was built to optimize classification performance. Input data for the system is e-nose sensor response to 3 black tea qualities. The features are sensors on the e-nose instrument. Feature selection is implemented using wrapper approach, ABC algorithm is used for feature selection, then the selected features are evaluated by SVM classification. The results of the ABC-SVM system are then compared with the SVM only system. The results showed that from 12 e-nose sensors, sensors that most characterized black tea quality were TGS 2600, TGS 813, TGS 825, TGS 2602, TGS 2611, TGS 832, TGS 2612, TGS 2620 and TGS 822. Meanwhile, MQ-7, TGS 826 and TGS 2610 sensors are redundant in the system because the gas detected by the 3 sensors can be represented by other sensors. With the reduction in features to 9, the classification accuracy performance increased by 16.7%.

Benchmarking Spectroscopic Techniques Combined with Machine Learning to Study Oak Barrels for Wine Ageing.

Due to its physical, chemical, and structural properties, oakwood is widely used in the production of barrels for wine ageing. When in contact with the wine, oak continuously releases aromatic compounds such as lignin, tannin, and cellulose to the liquid. Due to the release process, oak loses its characteristic aromatic compounds in time; hence, the flavour that it gives to the enclosed wine decreases for repeated wine refills and a barrel replacement is required. Currently, the estimation of the maximum number of refills is empirical and its underestimation or overestimation can impose unnecessary costs and impair the quality of the wine. Therefore, there is a clear need to quantify the presence of the aforementioned aromatic compounds in an oak barrel prior to a refill. This work constitutes a study to examine noninvasive optical biosensing techniques for the characterization of an oak barrel used in wine ageing, towards the development of a model to unveil its lifespan without inducing structural damage. Spectroscopic diagnostic techniques, such as reflectance, fluorescence, and Raman scattering measurements are employed to assess the change in the chemical composition of the oakwood barrel (tannin and lignin presence) and its dependence on repeated refills. To our knowledge, this is the first time that we present a benchmarking study of oak barrel ageing characteristics through spectroscopic methods for the wine industry. The spectroscopic data are processed using standard chemometric techniques, such as Linear Discriminant Analysis and Partial Least Squares Discriminant Analysis. Results of a study of fresh, one-time-used, and two-times-used oak barrel samples demonstrate that reflectance spectroscopy can be a valuable tool for the characterization of oak barrels. Moreover, reflectance spectroscopy has demonstrated the most accurate classification performance. The highest accuracy has been obtained by a Partial Least Squares Discriminant Analysis model that has been able to classify all the oakwood samples from the barrels with >99% accuracy. These preliminary results pave a way for the application of cost-effective and non-invasive biosensing techniques based on reflectance spectroscopy for oak barrels assessment.

Quantum-inspired complex convolutional neural networks

Quantum-inspired neural network is one of the interesting researches at the junction of the two fields of quantum computing and deep learning. Several models of quantum-inspired neurons with real parameters have been proposed, which are mainly used for three-layer feedforward neural networks. In this work, we improve the quantum-inspired neurons by exploiting the complex-valued weights which have richer representational capacity and better non-linearity. We then extend the method of implementing the quantum-inspired neurons to the convolutional operations, and naturally draw the models of quantum-inspired convolutional neural networks (QICNNs) capable of processing high-dimensional data. Five specific structures of QICNNs are discussed which are different in the way of implementing the convolutional and fully connected layers. The performance of classification accuracy of the five QICNNs are tested on the MNIST and CIFAR-10 datasets. The results show that the QICNNs can perform better in classification accuracy on MNIST dataset than the classical CNN. More learning tasks that our QICNN can outperform the classical counterparts will be found.

The identification of significant features towards travel mode choice and its prediction via optimised random forest classifier: An evaluation for active commuting behavior

IntroductionPhysical activity is the foundation to staying healthy, but sedentary activities have become not uncommon that ought to be mitigated immediately. The study aims to highlight the role of a transport system that encourages physical activity among users by applying an active door-to-door transport system. Users’ mode choice is studied to understand their preferences for active commuting. The use of machine learning has since been ubiquitous in a myriad of fields, including transportation studies and hence is also investigated towards its efficacy in predicting travel mode choice. MethodologyThe application of the Random Forest (RF) model to identify travel mode choice is explored using the Revealed/Stated Preferences (RP/SP) Survey data in Kuantan City during weekdays. A total of 386 respondents were involved in this survey. The efficacy of the tuned RF models towards predicting the travel mode choice is evaluated via the Classification Accuracy (CA) performance indicator. In addition, a Feature Importance study is also carried out in order to identify significant factors that contribute towards travel mode choice. ResultsThe results from the present investigation demonstrated that the default RF model has acceptable predictability for both training and test dataset of users’ mode choice, with a CA of 70.2% and 69.3%, respectively. Upon identifying the significant features and further refining the hyperparameters of the RF model heuristically, it was shown that with 145 trees, the CA improved to up to 71.6% and 70.1% for both the training and test dataset, respectively. Through the feature selection technique, the most significant features that affect users mode choice are total travel time (TT), waiting time at a public transport stop (WT), region, walking distance from the last stop to destination (WD2), and walking distance from home to the nearest bus stop (WD1). ConclusionsThe study has illustrated the efficacy of the optimised RF in predicting travel mode choice as well as identified the significant factors for the selection. The findings of the present study provide significant insight for policymakers to improve the performance of the public transportation system so that the users will benefit in terms of health and well-being from active commuting.

Automatic coronary plaque detection, classification, and stenosis grading using deep learning and radiomics on computed tomography angiography images: a multi-center multi-vendor study.

An automatic system utilizing both the advantages of the neural network and the radiomics was proposed for coronary plaque detection, classification, and stenosis grading. This study retrospectively included 505 patients with 127,763 computed tomography angiography (CTA) images from 5 medical center. A convolutional neural network (CNN) model was used to segment the coronary artery, detect the plaque candidate, and extract the image patch with high computation efficiency. The manually designed radiomics feature extractor was utilized to collect plaque patterns, followed by the different classifiers to perform the plaque classification and stenosis grading. The CNN model achieved 100% of sensitivity and the highest positive predictive value (83.9%) than U-Net and baseline model in plaque candidate detection. Twenty-six representative radiomics features were selected to construct the classifiers. Among different models, the gradient-boosting decision tree (GBDT) achieved the best performance in plaque classification (accuracy: 87.0%, sensitivity: 83.2%, specificity: 91.4%) and stenosis grading (accuracy: 90.9%, sensitivity: 84.1%, specificity: 95.7%). GBDT also achieved the highest AUC of 0.873 in plaque classification and 0.910 in stenosis grading. The computation time of processing one patient was 56.2 ± 5.7 s which was significantly less than radiologist manual analysis (285.6 ± 134.5 s, p = 0.0001). In this study, an automatic workflow was proposed to detect and analyze coronary plaques with high accuracy and efficiency, showing the potential in clinical application. • The proposed automatic system integrated deep learning and radiomics to perform the coronary plaque analysis. • The proposed automatic system achieved high accuracy in both plaque classification and stenosis grading. • The proposed automatic system was five times more efficient than radiologist manual analysis.

Enhance Teaching-Learning-Based Optimization for Tsallis-Entropy-Based Feature Selection Classification Approach

Feature selection is an effective method to reduce the number of data features, which boosts classification performance in machine learning. This paper uses the Tsallis-entropy-based feature selection to detect the significant feature. Support Vector Machine (SVM) is adopted as the classifier for classification purposes in this paper. We proposed an enhanced Teaching-Learning-Based Optimization (ETLBO) to optimize the SVM and Tsallis entropy parameters to improve classification accuracy. The adaptive weight strategy and Kent chaotic map are used to enhance the optimal ability of the traditional TLBO. The proposed method aims to avoid the main weaknesses of the original TLBO, which is trapped in local optimal and unbalance between the search mechanisms. Experiments based on 16 classical datasets are selected to test the performance of the ETLBO, and the results are compared with other well-established optimization algorithms. The obtained results illustrate that the proposed method has better performance in classification accuracy.

Penerapan Binary Particle Swarm Optimization Support Vector Machine untuk Klasifikasi Komentar Cyberbullying di Instagram

Freedom of speech on social media is sometimes inappropriate with the ethics of communicating and has led to cyberbullying. Instagram is the most commonly used social media in cyberbullying. Cyberbullying needs to be minimized because it has many adverse effects. One way that can be done is by identifying cyberbullying comments so those comments can be deleted automatically. The method used in this study is text classification using Support Vector Machine (SVM) algorithm with the application of Binary Particle Swarm Optimization (BPSO) optimization method as features selection. The study aims to build a cyberbullying comments classification model and compare the classification model performance with and without the application of features selection. The experimental results showed that modeling with SVM produces a reasonably accurate classification performance over 72% for all classification performance on each C. The application of BPSO for features selection can improve classification performance by increasing accuracy and specificity. However, the model without features selection on C = 0,1 is chosen in this study case because it has the highest sensitivity with good accuracy and specificity that can detect cyberbullying comments more accurately.

Stacking-Based Ensemble Learning Method for Multi-Spectral Image Classification

Higher dimensionality, Hughes phenomenon, spatial resolution of image data, and presence of mixed pixels are the main challenges in a multi-spectral image classification process. Most of the classical machine learning algorithms suffer from scoring optimal classification performance over multi-spectral image data. In this study, we propose stack-based ensemble-based learning approach to optimize image classification performance. In addition, we integrate the proposed ensemble learning with XGBoost method to further improve its classification accuracy. To conduct the experiment, the Landsat image data has been acquired from Bishoftu town located in the Oromia region of Ethiopia. The current study’s main objective was to assess the performance of land cover and land use analysis using multi-spectral image data. Results from our experiment indicate that, the proposed ensemble learning method outperforms any strong base classifiers with 99.96% classification performance accuracy.