Pre-Earthquake Ionospheric Perturbation Identification Using CSES Data via Transfer Learning

Integrating near-infrared hyperspectral imaging with machine learning and feature selection: Detecting adulteration of extra-virgin olive oil with lower-grade olive oils and hazelnut oil

It is important to identify which proteins can interact with RNA for the purpose of protein annotation, since interactions between RNA and proteins influence the structure of the ribosome and play important roles in gene expression. This paper tries to identify proteins that can interact with RNA using voting systems. Firstly through Weka, 34 learning algorithms are chosen for investigation. Then simple majority voting system (SMVS) is used for the prediction of RNA-binding proteins, achieving average ACC (overall prediction accuracy) value of 79.72% and MCC (Matthew's correlation coefficient) value of 59.77% for the independent testing dataset. Then mRMR (minimum redundancy maximum relevance) strategy is used, which is transferred into algorithm selection. In addition, the MCC value of each classifier is assigned to be the weight of the classifier's vote. As a result, best average MCC values are attained when 22 algorithms are selected and integrated through weighted votes, which are 64.70% for the independent testing dataset, and ACC value is 82.04% at this moment.

Anemia is one of the common adverse reactions after hip fracture surgery. The traditional method to solve anemia is allogeneic transfusion. However, the transfusion may lead to some complications such as septicemia and fever. So far, few studies have reported roles of machine learning in predicting whether blood transfusion is needed or not after hip fracture surgery. Therefore, the purpose of this study is to develop machine learning models to predict the likelihood of postoperative blood transfusion in patients undergoing hip fracture surgery. This study enrolled 1355 patients who underwent hip fracture surgery at the Affiliated Hospital of Qingdao University from January 2016 to December 2021. Among all patients, 210 cases received postoperative blood transfusion. All patients were randomly divided into a training group and a testing group at a ratio of 7:3. In the training group, univariate and multivariate logistic regression analyses were used to determine independent risk factors for the postoperative transfusion. Then, based on these independent risk factors, tenfold cross-validation method was utilized to develop five machine learning models, including logistic, multilayer perceptron (MLP), extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM). The receiver operating characteristic (ROC) curve, area under ROC curve (AUC), and Matthews correlation coefficient (MCC) were generated to evaluate the performance of the models. Calibration plot and decision curve analysis (DCA) were used to test the performance, stability, and clinical applicability of the models. The models were validated using the testing group; and the ROC curve, MCC, calibration plot, and DCA curves were also generated to validate the performance, stability, and clinical applicability of the models. To further verify the robustness of the model, we randomly grabbed 70% of the samples in the testing set, performed 1000 iterations, and calculated the AUC and confidence interval of the five models. Finally, we used SHapley Additive exPlanations (SHAP) to explain these models. Multivariate logistic regression analysis showed that there were 8 independent risk factors, including age, blood transfusion history, albumin (ALB), globulin (GLO), total bilirubin (TBIL), indirect bilirubin (IBIL), hemoglobin (HB), and blood loss > 200ml. We finally selected five independent risk factors including HB, GLO, age, IBIL, and blood loss > 200ml. Based on these five independent risk factors, we generated six characteristic variables, namely HB, HB × HB, HB × blood loss, GLO × HB, age, age × IBIL, and established five machine learning models using a tenfold cross-validation method. In the training group, the AUC values of logistic, RF, MLP, SVM, and XGB were 0.9320, 0.8911, 0.9327, 0.9225, and 0.8825, respectively, and the average AUC was 0.9122 ± 0.0212. The MCC values were 0.65, 0.77, 0.65, 0.66, and 0.68, respectively, and the calibration plot and DCA performed well. In the testing group the AUC values of logistic, RF, MLP, SVM, and XGB were 0.8483, 0.7978, 0.8576, 0.8598, and 0.8216, respectively. The average AUC was 0.8370 ± 0.0238, and the MCC values were 0.41, 0.35, 0.40, 0.41, and 0.41, respectively. The calibration plot and DCA in the testing group also showed good performance. The AUC values and confidence intervals of the 1000-iteration model were: logistic (AUC, min confidence interval [CI]-max confidence interval [CI] 0.848, 0.804-0.903), RF (AUC, minCI-maxCI 0.797, 0.734-0.857), MLP (AUC, minCI-maxCI 0.858, 0.812-0.902), SVM (AUC, minCI-maxCI 0.859, 0.819-0.910), and XGB (AUC, minCI-maxCI 0.821, 0.764-0.894). The model performed well. Finally, according to SHAP, among all five models, HB played the most important role in model prediction and interpretation. The five models we developed all performed well in predicting the likelihood of blood transfusion after hip fracture surgery. Therefore, we believed that the prediction model based on machine learning had great application prospects in clinical practice, which could help clinicians better predict the risk of blood transfusion after hip fracture surgery.

Enzymes play an important role in metabolism that helps in catalyzing bio-chemical reactions. Predicting functions of enzymes by experiments is costly and time consuming. Hence a computational method is required to predict the function of enzymes. This paper presents a supervised machine learning approach to predict the functional classes and subclass of protein sequences including enzymes and non-enzymes based on 857 sequence derived features. This paper used seven sequence derived properties including amino acid composition, dipeptide composition, correlation feature, composition, transition, distribution and pseudo amino acid composition. We have used recursive feature elimination technique (RFE), in order to select optimal number of features. The support vector machine (SVM) has been used to construct a three level model with optimal number of features selected by SVM-RFE, where top (first) level distinguish a query protein as an enzyme or nonenzyme, the next (second) level predicts the enzyme functional class and the last (third) level predict the subfunctional class. The proposed model reported overall accuracy of 97.6%, precision of 97.8%and Matthew Correlation Coefficient (MCC) value of 0.93 for the first level, whereas accuracy of 87.3%, precision of 87.7% and MCC value of 0.84 for second level and accuracy of 85.6%, precision of 87.9% and MCC value of 0.86 for the third level.

The article considers the problem of detecting anomalies in the video stream from traffic surveillance cameras, which is an important element of modern intelligent transport systems. An object-centric approach “detector-tracker-analyzer of anomalies” is proposed, which provides increased reliability of automatic detection of anomalous events, in particular, driving at a prohibitory traffic light signal, speeding, emergency braking and prolonged stay in the intersection zone. The method is based on the modern object detector YOLOv8n, which is characterized by high processing speed and acceptable accuracy for real-time tasks, as well as the OC-SORT tracker, which demonstrates increased resistance to short-term occlusions and reduces the number of false associations in a dense traffic flow. To determine the speed characteristics of vehicles, a homographic transformation was used taking into account the camera calibration, which made it possible to correctly translate the coordinates of objects into the world system. To test the efficiency of the approach, the proprietary dataset based on open source videos (Friant Roulette channel, California) was generated, containing both normal and abnormal situations. A total of 160 video fragments were used. The experiments demonstrated that the use of the combination of YOLOv8n + OC-SORT provides higher accuracy compared to the basic combination of YOLOv8n + SORT, which is confirmed by the increase in the Matthews correlation coefficient (MCC) values. The best results were obtained for anomalies such as “running a red light” (MCC = 0.909) and “being in the intersection zone” (MCC = 0.881). The results for “speeding” (MCC = 0.815) and “emergency braking” (MCC = 0.505) were somewhat worse, which is explained by the sensitivity to the quality of the video stream, viewing angle and camera stability. The developed approach is promising for the integration into intelligent traffic monitoring systems, as it allows automating the process of detecting violations and reducing the workload on operators. Further development directions include the optimization of the detector model architecture, using re-identification modules to reduce the number of false associations, improving speed estimation algorithms, and expanding the list of anomalies, such as pedestrians on the roadway or prohibited parking.

Recent studies have successfully reported the accuracy of using artificial neural networks to predict grip force in controlled settings. However, only relying on accuracy to evaluate the machine learning models may lead to overoptimistic results, especially on imbalanced datasets. The Matthews correlation coefficient (MCC) showed an advantage in capturing all the data characteristics in the confusion matrix. Therefore, a binary classification approach and the MCC value were introduced to assess the performance of previously proposed machine learning models. Our results show that the overall correlations ranging between 0.48 and 0.59 indicate a strong relationship between predictions and actual scenarios. The binary classification approach and the MCC values could be used for future performance comparison with other machine learning models.

CMSENN: Computational Modification Sites with Ensemble Neural Network

Ornamental pumpkin (Cucurbita pepo L. var. ovifera) seeds are highly morphologically variable, and their classification is hence a complex task for the seed industry. Efficient and accurate classification is critical for agricultural production, breeding programs, and seed sorting for commerce. This study employs machine learning models-Random Forest (RF), LightGBM, and k-Nearest Neighbors (KNN)-to classify ornamental pumpkin seeds based on their morphological (mass, elongation, width, thickness) and colorimetric characteristics (L*, a*, b* values from CIELAB color space). Prior to model training, the data set was preprocessed through normalization and balancing to enhance classification performance. In this study, six different types of ornamental pumpkin seeds were used, with a total of 900 (150 each of SDE0619, SDE1020, SDE1620, SDE2621, SDE4521, and SDE7721). The classification performance of the models was evaluated using different metrics, such as Accuracy, Balanced Accuracy, Precision, Recall, F1 Score, Matthews Correlation Coefficient (MCC), and Cohen's Kappa. Among the tested models, the RF model performed best, with Accuracy of 0.959, Balanced Accuracy of 0.961, Precision (Macro) of 0.962, Recall (Macro) of 0.961, F1 Score (Macro) of 0.961, MCC of 0.951, and Cohen's Kappa of 0.951. In contrast, the worst classification performance of the tested models was with the KNN model across all the evaluation metrics. These outcomes reflect the potential of machine learning-based approaches for seed classification automation, error minimization in seed classification, and maximization of efficiency in the seed industry. The high classification performance of the Random Forest model with 95.9% accuracy and 0.951 MCC value shows that artificial intelligence-based automatic classification of ornamental pumpkin seeds according to their morphological and colorimetric characteristics can make significant contributions to the seed industry, while the integration of this approach into seed sorting and quality determination processes can enable the creation of effective breeding schemes for optimum seed selection by maximizing the accuracy of agricultural processes.

This study investigates the linguistic competence of modern language models. Artificial neural networks demonstrate high quality in many natural language processing tasks. However, their implicit grammar knowledge remains unstudied. The ability to judge a sentence as grammatical or ungrammatical is regarded as key property of human’s linguistic competence. We suppose that language models’ grammar knowledge also occurs in their ability to judge the grammaticality of a sentence. In order to test neural networks’ linguistic competence, we probe their acquisition of number predicate agreement in Russian. A dataset consisted of artificially generated grammatical and ungrammatical sentences was created to train the language models. Automatic sentence generation allows us to test the acquisition of particular language phenomenon, to detach from vocabulary and pragmatic differences. We use transfer learning of pre-trained neural networks. The results show that all the considered models demonstrate high accuracy and Matthew's correlation coefficient values which can be attributed to successful acquisition of predicate agreement rules. The classification quality is reduced for sentences with inanimate nouns which show nominative-accusative case syncretism. The complexity of the syntactic structure turns out to be significant for Russian models and a model for Slavic languages, but it does not affect the errors distribution of multilingual models.

The leather industry plays a crucial role in the production of high-quality leather products to remain competitive in the market. Due to various reasons such as material handling and turning, leather defects can appear at different stages of the production process. This paper proposed deep learning techniques, specifically transfer learning, deep convolutional neural networks (D-CNN), and ensemble learning for automating leather defect detection and classification. The dataset was taken from the open source Kaggle. The dataset was preprocessed from the beginning. However, we performed Error Level Analysis (ELA) to detect possible changes or fraud in the image. We also used data augmentation techniques (resizing, rescaling, flipping, rotation, zooming, and contrasting) on the dataset to improve the model performance. This study investigated deep learning architectures for automatic leather defect detection, comparing them with seven deep convolutional neural networks (D-CNN) models and transfer learning architectures. Furthermore, we introduce and evaluate two novel ensemble models: MER built on transfer learning architecture (MobileNetV2, EfficientNetB0, and ResNet50) and AZL built on D-CNN architecture (AlexNet, ZfNet, and LeNet). A key contribution of this study is the demonstration of significant performance improvements achieved by strategically integrating squeeze and excitation and label smoothing techniques into transfer learning, D-CNN, and ensemble frameworks. Our proposed MER ensemble method achieves a state-of-the-art of 96.39% for leather defect detection. The proposed model was evaluated using performance metrics including precision, recall, F1-score, AUC, ROC, and Matthews Correlation Coefficient (MCC). Additionally, Grad-CAM was employed for explainable AI to visualize and interpret the model’s decision-making process. Comparative analysis against separate transfer learning and D-CNN models fails to establish the superior performance of our MER ensemble, which highlights the potential to significantly advance automated quality inspection in leather production. This study provides insights into evaluating the best deep learning techniques for leather defect classification, paving the way for more accurate, efficient, and reliable industrial applications. Proposes a robust deep learning-based framework for automated leather defect detection using transfer learning, deep CNNs, and two novel ensemble models (MER and AZL), enhanced with squeeze-and-excitation and label smoothing techniques. Achieves state-of-the-art performance with the proposed MER ensemble model, achieve 96.39% accuracy, and demonstrates superior results across precision, recall, F1-score, AUC–ROC, and MCC. Integrates Error Level Analysis (ELA), extensive data augmentation, and Grad-CAM–based explainable AI to ensure data reliability, improve generalization, and provide transparent visual interpretation of defect regions for industrial quality inspection.

Intensive-care units (ICUs) treat the most critically ill patients, which is complicated by the heterogeneity of the diseases that they encounter. Severity scores based mainly on acute physiology measures collected at ICU admission are used to predict mortality, but are non-specific, and predictions for individual patients can be inaccurate. We investigated whether inclusion of long-term disease history before ICU admission improves mortality predictions. Registry data for long-term disease histories for more than 230 000 Danish ICU patients were used in a neural network to develop an ICU mortality prediction model. Long-term disease histories and acute physiology measures were aggregated to predict mortality risk for patients for whom both registry and ICU electronic patient record data were available. We compared mortality predictions with admission scores on the Simplified Acute Physiology Score (SAPS) II, the Acute Physiologic Assessment and Chronic Health Evaluation (APACHE) II, and the best available multimorbidity score, the Multimorbidity Index. An external validation set from an additional hospital was acquired after model construction to confirm the validity of our model. During initial model development data were split into a training set (85%) and an independent test set (15%), and a five-fold cross-validation was done during training to avoid overfitting. Neural networks were trained for datasets with disease history of 1 month, 3 months, 6 months, 1 year, 2·5 years, 5 years, 7·5 years, 10 years, and 23 years before ICU admission. Mortality predictions with a model based solely on disease history outperformed the Multimorbidity Index (Matthews correlation coefficient 0·265 vs 0·065), and performed similarly to SAPS II and APACHE II (Matthews correlation coefficient with disease history, age, and sex 0·326 vs 0·347 and 0·300 for SAPS II and APACHE II, respectively). Diagnoses up to 10 years before ICU admission affected current mortality prediction. Aggregation of previous disease history and acute physiology measures in a neural network yielded the most precise predictions of in-hospital mortality (Matthews correlation coefficient 0·391 for in-hospital mortality compared with 0·347 with SAPS II and 0·300 with APACHE II). These results for the aggregated model were validated in an external independent dataset of 1528 patients (Matthews correlation coefficient for prediction of in-hospital mortality 0·341). Longitudinal disease-spectrum-wide data available before ICU admission are useful for mortality prediction. Disease history can be used to differentiate mortality risk between patients with similar vital signs with more precision than SAPS II and APACHE II scores. Machine learning models can be deconvoluted to generate novel understandings of how ICU patient features from long-term and short-term events interact with each other. Explainable machine learning models are key in clinical settings, and our results emphasise how to progress towards the transformation of advanced models into actionable, transparent, and trustworthy clinical tools. Novo Nordisk Foundation and Innovation Fund Denmark.

Adaptor proteins, also known as signal transduction adaptor proteins, are important proteins in signal transduction pathways, and play a role in connecting signal proteins for signal transduction between cells. Studies have shown that adaptor proteins are closely related to some diseases, such as tumors and diabetes. Therefore, it is very meaningful to construct a relevant model to accurately identify adaptor proteins. In recent years, many studies have used a position-specific scoring matrix (PSSM) and neural network methods to identify adaptor proteins. However, ordinary neural network models cannot correlate the contextual information in PSSM profiles well, so these studies usually process 20×N (N>20) PSSM into 20×20 dimensions, which results in the loss of a large amount of protein information; This research proposes an efficient method that combines one-dimensional convolution (1-D CNN) and a bidirectional long short-term memory network (biLSTM) to identify adaptor proteins. The complete PSSM profiles are the input of the model, and the complete information of the protein is retained during the training process. We perform cross-validation during model training and test the performance of the model on an independent test set; in the data set with 1224 adaptor proteins and 11,078 non-adaptor proteins, five indicators including specificity, sensitivity, accuracy, area under the receiver operating characteristic curve (AUC) metric and Matthews correlation coefficient (MCC), were employed to evaluate model performance. On the independent test set, the specificity, sensitivity, accuracy and MCC were 0.817, 0.865, 0.823 and 0.465, respectively. Those results show that our method is better than the state-of-the art methods. This study is committed to improve the accuracy of adaptor protein identification, and laid a foundation for further research on diseases related to adaptor protein. This research provided a new idea for the application of deep learning related models in bioinformatics and computational biology.

Ionospheric disturbances (such as electromagnetic emissions) in connection to strong earthquakes have been reported in literature for over two decades. In order to be reliable, the identification of such disturbances requires a preliminary robust definition of the ionospheric background in the absence of both seismic activity and any other possible input (e.g., transient change in solar activity).In this work, we present a new technique for the assessment of the electromagnetic (EM) background in the ionosphere over seismic regions. The background is estimated via a multiscale statistical analysis that makes use of most of the electric- and magnetic-field datasets (2019–2021) from the China Seismo-Electromagnetic Satellite (CSES-01).The result is a map of the average relative energy in a 6° x 6° LAT-LON cell centered at the earthquake epicenter (EE). Only EM signals that statistically differ from the background should be considered as events suitable for investigation.The method is tested against two strong seismic events, the 14 August 2021 Haitian earthquake (7.2 MW) and the 27 September 2021 Cretan earthquake (6.0 MW). In the former case, a signal (with characteristic frequency of 250 Hz) can be identified, which emerges from the background. In the latter one, the concurrent strong geomagnetic activity does not allow to tell any distinct signal apart from the background.

In recent times, the detection of brain tumour is a common fatality in the field of the health community. Generally, the brain tumor is an abnormal mass of tissue where the cells grow up and increase uncontrollably, apparently unregulated by mechanisms that control cells. A number of techniques have been developed so far; however, the time consumption in detecting brain tumor is still a challenge in the field of image processing. This paper intends to propose a new detection model even accurately. The model includes certain processes like Preprocessing, Segmentation, Feature Extraction and Classification. Particularly, two extreme processes like contrast enhancement and skull stripping are processed under initial phase, in the segmentation process, this paper uses Fuzzy Means Clustering (FCM) algorithm. Both Gray Level Co-occurrence Matrix (GLCM) as well as Gray-Level Run-Length Matrix (GRLM) features are extracted in feature extraction phase. Moreover, this paper uses Deep Belief Network (DBN) for classification. The DBN is integrated with the optimization approach, and hence this paper introduces the optimized DBN, for which Grey Wolf Optimization (GWO) is used here. The proposed model is termed as GW-DBN model. The proposed model compares its performance over other conventional methods in terms of Accuracy, Specificity, Sensitivity, Precision, Negative Predictive Value (NPV), F 1 Score and Matthews Correlation Coefficient (MCC), False negative rate (FNR), False positive rate (FPR) and False Discovery Rate (FDR), and proven the superiority of proposed work.

Identifying protein arginine methylation sites using global features of protein sequence coupled with support vector machine optimized by particle swarm optimization algorithm