Search

Facial expression recognition (FER) plays a crucial role in understanding human emotions and is becoming increasingly relevant in educational contexts, where personalized and empathetic interactions are essential. The problems with existing approaches are typically solved using a single deep learning method, which is not robust with complex datasets, such as FER data, which have a characteristic imbalance and multi-class labels. In this research paper, an innovative approach to FER using a homogeneous ensemble convolutional neural network, called HoE-CNN, is presented for future online learning education. This paper aims to transfer the knowledge of models and FER classification using ensembled homogeneous conventional neural network architectures. FER is challenging to research because there are many real-world applications to consider, such as adaptive user interfaces, games, education, and robot integration. HoE-CNN is used to improve the classification performance on an FER dataset, encompassing seven main multi-classes (Angry, Disgust, Fear, Happy, Sad, Surprise, Neutral). The experiment shows that the proposed framework, which uses an ensemble of deep learning models, performs better than a single deep learning model. In summary, the proposed model will increase the efficiency of FER classification results and solve FER2013 at a accuracy of 75.51%, addressing both imbalanced datasets and multi-class classification to transfer the application of the model to online learning applications. [ABSTRACT FROM AUTHOR]

This paper presents a signal generation architecture for simulating arbitrarily intercepted low-probability-of-intercept (LPI) signals in a battlefield environment. Additionally, the performances of deep learning models in classifying the generated signals are compared in terms of the classification time, GPU memory usage, and accuracy. Previous studies have utilized ensemble learning to minimize signal classification time and enhance accuracy; however, an explicit criteria for the adoption of deep learning models have been lacking. This paper presents the analysis of the performances of 11 deep learning models on the basis of simulation results and proposes an ensemble model that utilizes MobileNet V3 Small as the main model and Densenet-169 as the sub-model. [ABSTRACT FROM AUTHOR]

As the deployment of Autonomous Vehicles (AVs) gains momentum, ensuring both security and accountability becomes paramount. This paper proposes a comprehensive approach to address these concerns. With the increasing importance of speaker identification, our first contribution lies in implementing a robust mechanism for identifying authorized users within AVs, enhancing security. To counter the threat of voice spoofing, an ensemble-based approach leveraging speaker verification techniques is presented, ensuring the authenticity of user commands. Furthermore, in scenarios of accidents involving AVs, the need for accurate accountability and liability allocation arises. To address this, we introduce a novel application of blockchain technology, enabling an event recording system that ensures transparent and tamper-proof records. The proposed system enhances AV security and establishes a framework for reliable accident investigation using speakers' records. In addition, this paper presents an innovative concept where vehicles act as impartial judges during accidents, utilizing location-based identification. Results show the viability of the proposed solution for accident investigation and analysis. [ABSTRACT FROM AUTHOR]

This paper explores the potential of using the SAM (Segment-Anything Model) segmentator to enhance the segmentation capability of known methods. SAM is a promptable segmentation system that offers zero-shot generalization to unfamiliar objects and images, eliminating the need for additional training. The open-source nature of SAM allows for easy access and implementation. In our experiments, we aim to improve the segmentation performance by providing SAM with checkpoints extracted from the masks produced by mainstream segmentators, and then merging the segmentation masks provided by these two networks. We examine the "oracle" method (as upper bound baseline performance), where segmentation masks are inferred only by SAM with checkpoints extracted from the ground truth. One of the main contributions of this work is the combination (fusion) of the logit segmentation masks produced by the SAM model with the ones provided by specialized segmentation models such as DeepLabv3+ and PVTv2. This combination allows for a consistent improvement in segmentation performance in most of the tested datasets. We exhaustively tested our approach on seven heterogeneous public datasets, obtaining state-of-the-art results in two of them (CAMO and Butterfly) with respect to the current best-performing method with a combination of an ensemble of mainstream segmentator transformers and the SAM segmentator. The results of our study provide valuable insights into the potential of incorporating the SAM segmentator into existing segmentation techniques. We release with this paper the open-source implementation of our method. [ABSTRACT FROM AUTHOR]

Customer churn remains a critical concern for businesses, highlighting the significance of retaining existing customers over acquiring new ones. Effective prediction of potential churners aids in devising robust retention policies and efficient customer management strategies. This study dives into the realm of machine learning algorithms for predictive analysis in churn prediction, addressing the inherent challenge posed by diverse and imbalanced customer churn data distributions. This paper introduces a novel approach—the Ratio-based data balancing technique, which addresses data skewness as a pre-processing step, ensuring improved accuracy in predictive modelling. This study fills gaps in existing literature by highlighting the effectiveness of ensemble algorithms and the critical role of data balancing techniques in optimizing churn prediction models. While our research contributes a novel approach, there remain avenues for further exploration. This work evaluates several machine learning algorithms—Perceptron, Multi-Layer Perceptron, Naive Bayes, Logistic Regression, K-Nearest Neighbour, Decision Tree, alongside Ensemble techniques such as Gradient Boosting and Extreme Gradient Boosting (XGBoost)—on balanced datasets achieved through our proposed Ratio-based data balancing technique and the commonly used Data Resampling. Results reveal that our proposed Ratio-based data balancing technique notably outperforms traditional Over-Sampling and Under-Sampling methods in churn prediction accuracy. Additionally, using combined algorithms like Gradient Boosting and XGBoost showed better results than using single methods. Our study looked at different aspects like Accuracy, Precision, Recall, and F-Score, finding that these combined methods are better for predicting customer churn. Specifically, when we used a 75:25 ratio with the XGBoost method, we got the most promising results for our analysis which are presented in this work. [ABSTRACT FROM AUTHOR]

Cardiovascular disease (CVD) is a prominent contributor to global mortality rates. The principal aim of this research is to employ machine learning techniques to anticipate the early actions needed to prevent the disease from progressing. The timely identification of individuals with a heightened risk of developing CVD plays an important role in implementing early interventions to impede disease progression. Machine learning techniques have shown promise in predicting CVD risk. For this paper, we propose a comprehensive CVD prediction model using ML techniques. Our approach utilizes a substantial dataset of electronic health records (EHRs) for training and validating our model. Through the incorporation of feature engineering, feature selection, and model optimization techniques, we have reached a high level of accuracy and interpretability. To evaluate the prediction of cardiovascular disease (CVD) threats, we compare the performance of various popular ML algorithms, such as logistic regression, random forest, and Support Vector Machine. Our findings point towards that our proposed model improve on existing approaches in regard of both accuracy and efficiency. This model can efficiently recognize individuals with an elevated risk of developing CVD, enabling early interventions to prevent the onset and progression of the disease. Additionally, we perform a acatalectic analysis of the features that contribute most to the assessment of CVD risk, providing insights into the underlying mechanisms of the disease. We also evaluate the robustness of our model by testing its performance on a separate dataset. Furthermore, we discuss the clinical implications of our proposed model, highlighting the potential benefits of using ML techniques in identifying individuals at high risk of developing CVD. Our model can aid in personalized medicine and facilitate the delivery of targeted interventions to high-risk individuals, thereby improving patient outcomes and reducing healthcare costs. When it comes to treating severe stages of cardiovascular disease, preventive treatments are typically more economical. Our approach can assist in lessening the financial burden related to CVD by lowering hospital stays, ER visits, and long-term care expenses via early detection of high-risk individuals and implementation of focused therapies. In summary, our model presents a robust solution for utilizing machine learning techniques to envisage the risk of cardiovascular disease (CVD). Our study targets to provide the expanding field of research regarding the application of machine learning in healthcare. The insights extended from our findings hold significant potential for enhancing the anticipation and treatment of CVD. [ABSTRACT FROM AUTHOR]

The paper reports three new ensembles of supervised learning predictors for managing medical insurance costs. The open dataset is used for data analysis methods development. The usage of artificial intelligence in the management of financial risks will facilitate economic wear time and money and protect patients' health. Machine learning is associated withmany expectations, but its quality is determined by choosing a good algorithm and the proper steps to plan, develop, and implement the model. The paper aims to develop three new ensembles for individual insurance costs prediction to provide high prediction accuracy. Pierson coefficient and Boruta algorithm are used for feature selection. The boosting, stacking, and bagging ensembles are built. A comparison with existing machine learning algorithms is given. Boosting modes based on regression tree and stochastic gradient descent is built. Bagged CART and Random Forest algorithms are proposed. The boosting and stacking ensembles shown better accuracy than bagging. The tuning parameters for boosting do not allow to decrease the RMSE too. So, bagging shows its weakness in generalizing the prediction. The stacking is developed using K Nearest Neighbors (KNN), Support Vector Machine (SVM), Regression Tree, Linear Regression, Stochastic Gradient Boosting. The random forest (RF) algorithm is used to combine the predictions. One hundred trees are built forRF.RootMean Square Error (RMSE) has lifted the to 3173.213 in comparison with other predictors. The quality of the developed ensemble for RootMean Squared Error metric is 1.47 better than for the best weak predictor (SVR). [ABSTRACT FROM AUTHOR]

Recognizing aircraft automatically by using satellite images has different applications in both the civil and military sectors. However, due to the complexity and variety of the foreground and background of the analyzed images, it remains challenging to obtain a suitable representation of aircraft for identification. Many studies and solutions have been presented in the literature, but only a few studies have suggested handling the issue using semantic image segmentation techniques due to the lack of publicly labeled datasets. With the advancement of CNNs, researchers have presented some CNN architectures, such as U-Net, which has the ability to obtain very good performance using a small training dataset. The U-Net architecture has received much attention for segmenting 2D and 3D biomedical images and has been recognized to be highly successful for pixel-wise satellite image classification. In this paper, we propose a binary image segmentation model to recognize aircraft by exploiting and adopting the U-Net architecture for remote sensing satellite images. The proposed model does not require a significant amount of labeled data and alleviates the need for manual aircraft feature extraction. The public dense labeling remote sensing dataset is used to perform the experiments and measure the robustness and performance of the proposed model. The mean IoU and pixel accuracy are adopted as metrics to assess the obtained results. The results in the testing dataset indicate that the proposed model can achieve a 95.08% mean IoU and a pixel accuracy of 98.24%. [ABSTRACT FROM AUTHOR]

The world recently has faced the COVID-19 pandemic, a disease caused by the severe acute respiratory syndrome. The main features of this disease are the rapid spread and high-level mortality. The illness led to the rapid development of a vaccine that we know can fight against the virus; however, we do not know the actual vaccine's effectiveness. Thus, the early detection of the disease is still necessary to provide a suitable course of action. To help with early detection, intelligent methods such as machine learning and computational intelligence associated with computer vision algorithms can be used in a fast and efficient classification process, especially using ensemble methods that present similar efficiency to traditional machine learning algorithms in the worst-case scenario. In this context, this review aims to answer four questions: (i) the most used ensemble technique, (ii) the accuracy those methods reached, (iii) the classes involved in the classification task, (iv) the main machine learning algorithms and models, and (v) the dataset used in the experiments. [ABSTRACT FROM AUTHOR]