Good Classification Performance Research Articles

A novel discriminant algorithm for differential diagnosis of mild to moderate thalassemia and iron deficiency anemia.

Mild to moderate thalassemia trait (TT) and iron deficiency anemia (IDA) are the most common conditions of microcytic hypochromic anemia (MHA) and they exhibit highly similar clinical and laboratory features. It is sometimes difficult to make a differential diagnosis between TT and IDA in clinical practice. Therefore, a simple, effective, and reliable index is needed to discriminate between TT and IDA. Data of 598 patients (320 for TT and 278 for IDA) were enrolled and randomly assigned to training set (278 of 598, 70%) and validation set (320 of 598, 30%). Stepwise discriminant analysis was used to define the best diagnostic formula for the discrimination between TT and IDA in training set. The accuracy and diagnostic performance of formula was tested and verified by receiver operating characteristic (ROC) analysis in validation set and its diagnostic performance was compared with other published indices. A novel formula, Thalassemia and IDA Discrimination Index (TIDI) = -13.932 + 0.434 × RBC + 0.033 × Hb + 0.025 ×MCHC + 53.593 × RET%, was developed to discriminate TT from IDA. TIDI showed a high discrimination performance in ROC analysis, with the Area Under the Curve (AUC) = 0.936, Youden' s index = 78.7%, sensitivity = 89.5%, specificity = 89.2%, respectively. Furthermore, the formula index also obtained a good classification performance in distinguishing 5 common genotypes of TT from IDA (AUC from 0.854-0.987). The new, simple algorithm can be used as an effective and robust tool for the differential diagnosis of mild to moderate TT and IDA in Guangxi region, China.

A Hierarchical Fault Diagnosis Model for Planetary Gearbox with Shift-invariant Dictionary and OMPAN

Abstract Planetary gearbox has been widely applied in the mechanical transmission system, and the failure types of planetary gearbox are more and more diversified. The conventional fault diagnosis methods focus on identifying the faults in the fault library, but ignored the faults outside the fault library. However, it is impossible to build a fault library for all failure types. Targeting the problem of identifying the faults outside the fault library, a hierarchical fault diagnosis method for planetary gearbox with shift-invariant dictionary and orthogonal matching pursuit with adaptive noise (OMPAN) is proposed in this paper. By k-means singular value decomposition (K-SVD) dictionary learning method and shift-invariant strategy, a shift-invariant dictionary is constructed so that the normal modulation components of signals can be completed decomposed. OMPAN algorithm is proposed, which uses the white Gaussian noise to improve the solution method of the orthogonal matching pursuit (OMP) algorithm so that it can separate the modulation components in the signal more accurately. The fault feature extraction is developed via shift-invariant dictionary and OMPAN. A hierarchical classifier is proposed with 3 sub-classifiers so that both the faults in the fault library and the faults outside the fault library are identified. The effectiveness of the proposed hierarchical fault diagnosis method is validated by a planetary gearbox experiment. Result show that the proposed shift-invariant dictionary and OMPAN method has achieved a superior performance in highlighting fault features compared with other two sparse decomposition methods. The proposed hierarchical fault diagnosis approach has achieved a good performance both in classification of the faults in the fault library and identification of the faults outside the fault library.

Automatically detecting OSAHS patients based on transfer learning and model fusion

Objective. Snoring is the most typical symptom of obstructive sleep apnea hypopnea syndrome (OSAHS) that can be used to develop a non-invasive approach for automatically detecting OSAHS patients. Approach. In this work, a model based on transfer learning and model fusion was applied to classify simple snorers and OSAHS patients. Three kinds of basic models were constructed based on pretrained Visual Geometry Group-16 (VGG16), pretrained audio neural networks (PANN), and Mel-frequency cepstral coefficient (MFCC). The XGBoost was used to select features based on feature importance, the majority voting strategy was applied to fuse these basic models and leave-one-subject-out cross validation was used to evaluate the proposed model. Main results. The results show that the fused model embedded with top-5 VGG16 features, top-5 PANN features, and MFCC feature can correctly identify OSAHS patients (AHI > 5) with 100% accuracy. Significance. The proposed fused model provides a good classification performance with lower computational cost and higher robustness that makes detecting OSAHS patients at home possible.

A Neoteric Feature Extraction Technique to Predict the Survival of Gastric Cancer Patients.

At the time of cancer diagnosis, it is crucial to accurately classify malignant gastric tumors and the possibility that patients will survive. This study aims to investigate the feasibility of identifying and applying a new feature extraction technique to predict the survival of gastric cancer patients. A retrospective dataset including the computed tomography (CT) images of 135 patients was assembled. Among them, 68 patients survived longer than three years. Several sets of radiomics features were extracted and were incorporated into a machine learning model, and their classification performance was characterized. To improve the classification performance, we further extracted another 27 texture and roughness parameters with 2484 superficial and spatial features to propose a new feature pool. This new feature set was added into the machine learning model and its performance was analyzed. To determine the best model for our experiment, Random Forest (RF) classifier, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naïve Bayes (NB) (four of the most popular machine learning models) were utilized. The models were trained and tested using the five-fold cross-validation method. Using the area under ROC curve (AUC) as an evaluation index, the model that was generated using the new feature pool yields AUC = 0.98 ± 0.01, which was significantly higher than the models created using the traditional radiomics feature set (p < 0.04). RF classifier performed better than the other machine learning models. This study demonstrated that although radiomics features produced good classification performance, creating new feature sets significantly improved the model performance.

Email spam detection by deep learning models using novel feature selection technique and BERT

Due to the influx of advancements in technology and the increased simplicity of communication through emails, there has been a severe threat to the global economy and security due to upsurge in volume of unsolicited During the training of models, high-dimensional and redundant datasets may reduce the classification results of the model due to high memory costs and high computation. An important data processing technique is feature selection which helps in selecting relevant features and subsets of information from the dataset. Therefore, choosing efficient feature selection techniques is very important for the best performance of classification of a model. Moreover, most of the research has been performed using traditional machine learning techniques, which are not enough to deal with the huge amount of data and its variations. Also,spammers are becoming smarter with technological advancement. Therefore, there is a need for hybrid techniques consisting of deep learning and conventional algorithms to cope with these problems. We have proposed a novel scheme in this paper for email spam detection, which will result in an improved feature selection approach from the original dataset and increase the accuracy of the classifier as well. The literature has been studied to explore the efficient machine learning models that have been applied by different researchers for email spam detection and feature selection to acquire the best results. Our method, GWO-BERT, has given remarkable results with deep learning techniques such as CNN, biLSTM and LSTM. We have compared our models with RF and LSTM and used dataset: “Lingspam,” which is a publicly available dataset. With different experiments, our technique, GWO-BERT, obtained 99.14% accuracy, which is almost equal to 100 percent.

Optimizing vitiligo diagnosis with ResNet and Swin transformer deep learning models: a study on performance and interpretability

Vitiligo is a hypopigmented skin disease characterized by the loss of melanin. The progressive nature and widespread incidence of vitiligo necessitate timely and accurate detection. Usually, a single diagnostic test often falls short of providing definitive confirmation of the condition, necessitating the assessment by dermatologists who specialize in vitiligo. However, the current scarcity of such specialized medical professionals presents a significant challenge. To mitigate this issue and enhance diagnostic accuracy, it is essential to build deep learning models that can support and expedite the detection process. This study endeavors to establish a deep learning framework to enhance the diagnostic accuracy of vitiligo. To this end, a comparative analysis of five models including ResNet (ResNet34, ResNet50, and ResNet101 models) and Swin Transformer series (Swin Transformer Base, and Swin Transformer Large models), were conducted under the uniform condition to identify the model with superior classification capabilities. Moreover, the study sought to augment the interpretability of these models by selecting one that not only provides accurate diagnostic outcomes but also offers visual cues highlighting the regions pertinent to vitiligo. The empirical findings reveal that the Swin Transformer Large model achieved the best performance in classification, whose AUC, accuracy, sensitivity, and specificity are 0.94, 93.82%, 94.02%, and 93.5%, respectively. In terms of interpretability, the highlighted regions in the class activation map correspond to the lesion regions of the vitiligo images, which shows that it effectively indicates the specific category regions associated with the decision-making of dermatological diagnosis. Additionally, the visualization of feature maps generated in the middle layer of the deep learning model provides insights into the internal mechanisms of the model, which is valuable for improving the interpretability of the model, tuning performance, and enhancing clinical applicability. The outcomes of this study underscore the significant potential of deep learning models to revolutionize medical diagnosis by improving diagnostic accuracy and operational efficiency. The research highlights the necessity for ongoing exploration in this domain to fully leverage the capabilities of deep learning technologies in medical diagnostics.

Identification of immune subtypes associated with neutrophils in tuberculosis infection based on weighted gene co-expression network analysis

Tuberculosis (TB) is caused by Mycobacterium tuberculosis and is a major global health concern. Neutrophils play a significant role in TB infection and patient outcomes. This study aimed to identify gene modules associated with neutrophil infiltration in TB samples using WGCNA. Gene ontology and enrichment analyses were performed, and a random forest model was constructed to identify differentially expressed genes. K-means clustering was used to classify samples into subtypes, and immune-related scores, PD-L1 expression, HLA expression, and gene enrichment analysis were evaluated. The blue module showed significant correlation with neutrophils and enrichment in immune-related processes. The model exhibited good classification performance, and subtype 1 demonstrated higher immune-related scores, PD-L1 expression, HLA class I molecule expression, and immune-related pathway enrichment. These findings enhance our understanding of TB pathogenesis and provide potential targets for diagnosis and treatment strategies.

An overlapping conscious relief-based feature subset selection method

Feature selection is considered as a fundamental prepossessing step in various data mining and machine learning based works. The quality of features is essential to achieve good classification performance and to have better data analysis experience. Among several feature selection methods, distance-based methods are gaining popularity because of their eligibility in capturing feature interdependency and relevancy with the endpoints. However, most of the distance-based methods only rank the features and ignore the class overlapping issues. Features with class overlapping data work as an obstacle during classification. Therefore, the objective of this research work is to propose a method named overlapping conscious MultiSURF (OMsurf) to handle data overlapping and select a subset of informative features discarding the noisy ones. Experimental results over 20 benchmark dataset demonstrates the superiority of OMsurf over six existing state-of-the-art methods

Application of Deep Learning to Diagnose and Classify Adolescent Idiopathic Scoliosis

A deep learning-based model for automatic diagnosis and classification of adolescent idiopathic scoliosis has been constructed. This model mainly included key points detection and Cobb angle measurement. 748 full-length standing spinal X-ray images were retrospectively collected, of which 602 images were used to train and validate the model, and 146 images were used to test the model performance. The results showed that the model had good diagnostic and classification performance, with an accuracy of 94.5%. Compared with experts' measurement, 94.9% of its Cobb angle measurement results were within the clinically acceptable range. The average absolute difference was 2.1°, and the consistency was also excellent (r2≥0.9552, P<0.001). In the future, this model could be applied clinically to improve doctors' diagnostic efficiency.

OPTIMIZATION OF POTATO LEAF DISEASE IDENTIFICATION WITH TRANSFER LEARNING APPROACH USING MOBILENETV1 ARCHITECTURE

Diseases affecting potato leaves frequently lead to significant setbacks for farmers, reducing the overall harvest and the quality of the potatoes. Given the critical need for prompt disease detection, this research introduces the use of the MobileNet framework grounded in the Convolutional Neural Network (CNN) for adept detection of potato leaf ailments. During the research, potato leaf images undergo processing, and their distinct features are gleaned using CNN. Then, harnessing the MobileNet framework, these images undergo classification to ascertain the existence of diseases. The aspiration is that the formulated model can pinpoint diseases with notable precision, rapid feedback, and enhanced computational adeptness. Initial findings underscore the potential of this methodology in discerning potato leaf diseases, providing renewed optimism for farmers grappling with plant health issues. Experiments using the Transfer Learning approach showed good performance in classification and displayed a high accuracy rate of 99.2%.

Cigarette tasting Chinese text classification for low-resource scenarios

At present, the Chinese text field is facing challenges from low resource issues such as data scarcity and annotation difficulties. Moreover, in the domain of cigarette tasting, cigarette tasting texts tend to be colloquial, making it difficult to obtain valuable and high-quality tasting texts. Therefore, in this paper, we construct a cigarette tasting dataset (CT2023) and propose a novel Chinese text classification method based on ERNIE and Comparative Learning for Low-Resource scenarios (ECLLR). Firstly, to address the issues of limited vocabulary diversity and sparse features in cigarette tasting text, we utilize Term Frequency-Inverse Document Frequency (TF-IDF) to extract key terms, supplementing the discriminative features of the original text. Secondly, ERNIE is employed to obtain sentence-level vector embedding of the text. Finally, contrastive learning model is used to further refine the text after fusing the keyword features, thereby enhancing the performance of the proposed text classification model. Experiments on the CT2023 dataset demonstrate an accuracy rate of 96.33% for the proposed method, surpassing the baseline model by at least 11 percentage points, and showing good text classification performance. It is thus clear that the proposed approach can effectively provide recommendations and decision support for cigarette production processes in tobacco companies.

Validation of a Multivariable Model to Predict Suicide Attempt in a Mental Health Intake Sample

Given that suicide rates have been increasing over the past decade and the demand for mental health care is at an all-time high, targeted prevention efforts are needed to identify individuals seeking to initiate mental health outpatient services who are at high risk for suicide. Suicide prediction models have been developed using outpatient mental health encounters, but their performance among intake appointments has not been directly examined. To assess the performance of a predictive model of suicide attempts among individuals seeking to initiate an episode of outpatient mental health care. This prognostic study tested the performance of a previously developed machine learning model designed to predict suicide attempts within 90 days of any mental health outpatient visit. All mental health intake appointments scheduled between January 1, 2012, and April 1, 2022, at Kaiser Permanente Northern California, a large integrated health care delivery system serving over 4.5 million patients, were included. Data were extracted and analyzed from August 9, 2022, to July 31, 2023. Suicide attempts (including completed suicides) within 90 days of the appointment, determined by diagnostic codes and government databases. All predictors were extracted from electronic health records. The study included 1 623 232 scheduled appointments from 835 616 unique patients. There were 2800 scheduled appointments (0.17%) followed by a suicide attempt within 90 days. The mean (SD) age across appointments was 39.7 (15.8) years, and most appointments were for women (1 103 184 [68.0%]). The model had an area under the receiver operating characteristic curve of 0.77 (95% CI, 0.76-0.78), an area under the precision-recall curve of 0.02 (95% CI, 0.02-0.02), an expected calibration error of 0.0012 (95% CI, 0.0011-0.0013), and sensitivities of 37.2% (95% CI, 35.5%-38.9%) and 18.8% (95% CI, 17.3%-20.2%) at specificities of 95% and 99%, respectively. The 10% of appointments at the highest risk level accounted for 48.8% (95% CI, 47.0%-50.6%) of the appointments followed by a suicide attempt. In this prognostic study involving mental health intakes, a previously developed machine learning model of suicide attempts showed good overall classification performance. Implementation research is needed to determine appropriate thresholds and interventions for applying the model in an intake setting to target high-risk cases in a manner that is acceptable to patients and clinicians.

Prediction of postoperative visual acuity restoration in macula off rhegmatogenous retinal detachment using artificial intelligence

PurposeTo assess feasibility of automatic segmentation of OCT biomarkers of visual acuity (VA) and the possibility of prediction of postoperative VA after successful reattachment in macula off rhegmatogenous retinal detachment (RRD) eyes using artificial intelligence (AI). Designretrospective case control study MethodsPatients operated of pars plana vitrectomy (PPV) for macula-off non-traumatic RRD with available good quality OCT acquisitions were included. Ellipsoid zone(EZ) foveal damage and reflectivity, external limiting membrane(ELM) foveal damage, foveal flattening, outer nuclear layer(ONL) thickness and the presence of cysts and hyperreflective foci(HRFs) was assessed on preoperative OCT B scan images by both a trained segmenter and human graders. Different machine learning(ML)models were tested for detection of cases with VA>0.4 logMar at 6 months from surgery.Segmentation performance of the model was compared with ground truth segmentation provided by human graders. Postoperative VA prediction based on the segmented OCT biomarkers, preoperative VA and age was compared with actual postoperative VA to assess accuracy of the model. ResultsA total of 58 eyes of 58 patients were included. A significant difference in preoperative VA, foveal flattening, foveal EZ and ELM damage, EZ reflectivity and presence of HRF in the ONL was detected between groups(all p < 0.001).The segmenter showed good agreement with human assessment in both qualitative and quantitative variables. The Optimizable Naïve Bayes model was the best performing ML model and showed an accuracy of 86.2 % in detection of cases with postoperative VA>0.4 logMar. ConclusionsThe results confirm the prognostic relevance of EZ and ELM integrity and reflectivity, foveal flattening, ONL cysts and ONL HRF in macula off RRD, and, for the first time in literature, reports feasibility of the segmentation of these factors in preoperative OCT B scan images. We also report good classification performances of Naïve Bayes models based on OCT biomarkers, preoperative VA and age in distinguishing patients that should expect a postoperative VA>0.4 logMar at 6 months from surgery.

Semi-supervised Learning of Dynamical Systems with Neural Ordinary Differential Equations: A Teacher-Student Model Approach

Modeling dynamical systems is crucial for a wide range of tasks, but it remains challenging due to complex nonlinear dynamics, limited observations, or lack of prior knowledge. Recently, data-driven approaches such as Neural Ordinary Differential Equations (NODE) have shown promising results by leveraging the expressive power of neural networks to model unknown dynamics. However, these approaches often suffer from limited labeled training data, leading to poor generalization and suboptimal predictions. On the other hand, semi-supervised algorithms can utilize abundant unlabeled data and have demonstrated good performance in classification and regression tasks. We propose TS-NODE, the first semi-supervised approach to modeling dynamical systems with NODE. TS-NODE explores cheaply generated synthetic pseudo rollouts to broaden exploration in the state space and to tackle the challenges brought by lack of ground-truth system data under a teacher-student model. TS-NODE employs an unified optimization framework that corrects the teacher model based on the student's feedback while mitigating the potential false system dynamics present in pseudo rollouts. TS-NODE demonstrates significant performance improvements over a baseline Neural ODE model on multiple dynamical system modeling tasks.

Quantifying cerebral blood flow changes using arterial spin labeling: A comparative study of idiopathic rapid eye movement sleep behavior disorder and Parkinson's disease

IntroductionIdiopathic rapid eye movement sleep behavior disorder (iRBD) and Parkinson's disease (PD) have been found to have changes in cerebral perfusion and overlap of some of the lesioned brain areas. However, a consensus regarding the specific location and diagnostic significance of these cerebral blood perfusion alternations remains elusive in both iRBD and PD. The present study evaluated the patterns of cerebral blood flow changes in iRBD and PD. Material and methodsA total of 59 right-handed subjects were enrolled, including 15 patients with iRBD, 20 patients with PD, and 24 healthy controls (HC). They were randomly divided into groups at a ratio of 4 to 1 for training and testing. A PASL sequence was employed to obtain quantitative cerebral blood flow (CBF) maps. The CBF values were calculated from these acquired maps. In addition, AutoGluon was employed to construct a classifier for CBF features selection and classification. An independent t-test was performed for CBF variations, with age and sex as nuisance variables. The performance of the feature was evaluated using receiver operating characteristic (ROC) curves. A significance level of P < 0.05 was considered significant. CBF in several brain regions, including the left median cingulate and paracingulate gyri and the right middle occipital gyrus (MOG), showed significant differences between PD and HC, demonstrating good classification performance. The combined model that integrates all features achieved even higher performance with an AUC of 0.9380. Additionally, CBF values in multiple brain regions, including the right MOG and the left angular gyrus, displayed significant differences between PD and iRBD. Particularly, CBF values in the left angular gyrus exhibited good performance in classifying PD and iRBD. The combined model achieved improved performance, with an AUC of 0.8533. No significant differences were found in brain regions when comparing CBF values between iRBD and HC subjects. ConclusionsASL-based quantitative CBF change features can offer reliable biomarkers to assist in the diagnosis of PD. Regarding the characteristic of CBF in the right MOG, it is anticipated to serve as an imaging biomarker for predicting the progression of iRBD to PD.

Climate policy uncertainty and the U.S. economic cycle

Given the concerns arising from climate change, countries, regions, and organizations worldwide have developed and implemented policy frameworks and measures aimed at addressing the challenges posed by climate change. However, the implementation pathways of these policies may entail significant uncertainties, presenting challenges to economic development. This study uses the vector autoregressive (VAR) model to examine the influence of climate policy uncertainty (CPU) on the U.S. economic cycle. The economic cycle variables are extracted from four popular economic indicators based on the Hodrick-Prescott (HP) filter. The results show that CPU changes effectively impact economic cycle, and a positive CPU shock can trigger negative reactions in the economy (recession) in the subsequent period. Moreover, we find that CPU changes are a Granger cause of the economic cycle and have good prediction classification performance for economic expansions and recessions. We provide new insights into the relationship between CPU and the economic cycle for policymakers.

An ensemble method with a hybrid of genetic algorithm and K-prototypes algorithm for mixed data classification

Due to challenges posed by mixed data clustering, this study aims to introduce an innovative clustering-based classification algorithm that possesses the advantages of both classification and clustering techniques for mixed data analysis. The proposed algorithm employs the K-prototypes algorithm with a genetic algorithm to optimize weights and centroids and utilizes the bagging method to build multiple classifiers, thereby enhancing classification performance. Furthermore, it incorporates four mutation mechanisms, including Gaussian, Cauchy, Levy, and single-point mutations, to explore optimal solutions. This study suggests using a 20% sampling ratio for the bootstrap sampling in the proposed algorithm. This ratio has been proven to be sufficient for achieving good classification performance while reducing computational time. Experimental results indicate that the proposed algorithm outperforms benchmark classifiers, demonstrating superior classification performance across five performance indicators. In addition, the loan eligibility case study offers valuable insights into applying the proposed algorithm in real-world scenarios, demonstrating that the proposed algorithm can achieve superior classification performance compared to other algorithms. It also offers managerial implications to help different industries and fields understand the appropriate timing and scenarios for implementing the algorithm.

Machine learning approach using 18F-FDG-PET-radiomic features and the visibility of right ventricle 18F-FDG uptake for predicting clinical events in patients with cardiac sarcoidosis.

To investigate the usefulness of machine learning (ML) models using pretreatment 18F-FDG-PET-based radiomic features for predicting adverse clinical events (ACEs) in patients with cardiac sarcoidosis (CS). This retrospective study included 47 patients with CS who underwent 18F-FDG-PET/CT scan before treatment. The lesions were assigned to the training (n = 38) and testing (n = 9) cohorts. In total, 49 18F-FDG-PET-based radiomic features and the visibility of right ventricle 18F-FDG uptake were used to predict ACEs using seven different ML algorithms (namely, decision tree, random forest [RF], neural network, k-nearest neighbors, Naïve Bayes, logistic regression, and support vector machine [SVM]) with tenfold cross-validation and the synthetic minority over-sampling technique. The ML models were constructed using the top four features ranked by the decrease in Gini impurity. The AUCs and accuracies were used to compare predictive performances. Patients who developed ACEs presented with a significantly higher surface area and gray level run length matrix run length non-uniformity (GLRLM_RLNU), and lower neighborhood gray-tone difference matrix_coarseness and sphericity than those without ACEs (each, p < 0.05). In the training cohort, all seven ML algorithms had a good classification performance with AUC values of > 0.80 (range: 0.841-0.944). In the testing cohort, the RF algorithm had the highest AUC and accuracy (88.9% [8/9]) with a similar classification performance between training and testing cohorts (AUC: 0.945 vs 0.889). GLRLM_RLNU was the most important feature of the modeling process of this RF algorithm. ML analyses using 18F-FDG-PET-based radiomic features may be useful for predicting ACEs in patients with CS.

Survival risk prediction of gastric cardia cancer-based on a dynamic modular neural network

Gastric cardia cancer is a high-incidence malignant tumour, which seriously endangers human health and life safety. The patient prognosis of gastric cardia cancer is affected by diet, physical condition, regional environment, medical history and other factors. Traditional prediction methods cannot fully reflect the prognosis characteristics and survival risks of all patients. Therefore, this paper proposes a data-driven method for the survival risk of cardiac cancer based on an adaptive particle swarm optimization algorithm (APSO) and a dynamic modular neural network (DMNN). First, the article uses density clustering to cluster 293 patients’ blood characteristics and generate different sub-networks. Second, the weight is calculated through the APSO algorithm and the sub-network output is obtained by the integration algorithm. At last, the effectiveness of this network is verified through a 50% cross-validation of training sets and test sets. The results show that the survival prediction based on the APSO-DMNN data-driven method shows good classification performance and accuracy.

Simple Methods for Improving the Forensic Classification between Computer-Graphics Images and Natural Images

From the information forensics point of view, it is important to correctly classify between natural images (outputs of digital cameras) and computer-graphics images (outputs of advanced graphics rendering engines), so as to know the source of the images and the authenticity of the scenes described in the images. It is challenging to achieve good classification performance when the forensic classifier is tested on computer-graphics images generated by unknown rendering engines and when we have a limited number of training samples. In this paper, we propose two simple yet effective methods to improve the classification performance under such challenging situations, respectively based on data augmentation and the combination of local and global prediction results. Compared with existing methods, our methods are conceptually simple and computationally efficient, while achieving satisfying classification accuracy. Experimental results on datasets comprising computer-graphics images generated by four popular and advanced graphics rendering engines demonstrate the effectiveness of the proposed methods.