Metric learning aims to measure the similarity among samples while using an optimal distance metric for learning tasks. Metric learning methods, which generally use a linear projection, are limited in solving real-world problems demonstrating non-linear characteristics. Kernel approaches are utilized in metric learning to address this problem. In recent years, deep metric learning, which provides a better solution for nonlinear data through activation functions, has attracted researchers’ attention in many different areas. This article aims to reveal the importance of deep metric learning and the problems dealt with in this field in the light of recent studies. As far as the research conducted in this field are concerned, most existing studies that are inspired by Siamese and Triplet networks are commonly used to correlate among samples while using shared weights in deep metric learning. The success of these networks is based on their capacity to understand the similarity relationship among samples. Moreover, sampling strategy, appropriate distance metric, and the structure of the network are the challenging factors for researchers to improve the performance of the network model. This article is considered to be important, as it is the first comprehensive study in which these factors are systematically analyzed and evaluated as a whole and supported by comparing the quantitative results of the methods.

Declared a pandemic disease, COVID-19 has affected the lives of millions of people and had significant effects on public health. Despite the development of effective vaccines against COVID-19, cases continue to increase worldwide. According to studies in the literature, artificial intelligence methods are used effectively for the detection of COVID-19. In particular, deep-learning-based approaches have achieved very good results in clinical diagnostic studies and other fields. In this study, a new approach using x-ray images is proposed to detect COVID-19. In the proposed method, the angle transform (AT) method is first applied to the x-ray images. The AT method proposed in this study is an important novelty in the literature, as there is no such approach in previous studies. This transformation uses the angle information created by each pixel on the image with the surrounding pixels. Using the AT approach, eight different images are obtained for each image in the dataset. These images are trained with a hybrid deep learning model, which combines GoogleNet and long short-term memory (LSTM) models, and COVID-19 disease detection is carried out. A dataset from the Mendeley database is used to test the proposed approach. A high classification accuracy of 98.97% is achieved with the AT + GoogleNet + LSTM approach. The results obtained were also compared with other studies in the literature. The presented results reveal that the proposed method is successful for COVID-19 detection using chest x-ray images. Direct transfer methods were also applied to the data set used in the study. However, worse results were observed according to the proposed approach. The proposed approach has the flexibility to be applied effectively to different medical images.

This study utilizes a robust dataset provided by Energy Exchange Istanbul (EXIST), a leading authority in energy data, which contains hourly energy consumption and production data from 01/01/2018 to 31/12/2023 across Turkey. Various machine learning and deep learning methods such as linear regression (LR), random forest (RF), support vector machines (SVR), convolutional neural networks (CNN), long short-term memory networks (LSTM), and the proposed hybrid CNN-LSTM model are applied to predict energy consumption and production more accurately. This study transforms time series data into a regression problem using the sliding window method. The experimental results show that the hybrid CNN-LSTM model outperforms the other models in forecasting total energy consumption and natural gas, hydro dam, lignite, hydro river, wind, and fuel oil production. The CNN-LSTM model achieved the lowest RMSE and MAE values and the highest R² scores. The success of the proposed hybrid approach is due to the combination of CNN's ability to identify local patterns and LSTM's ability to learn long-term dependencies. This study demonstrates the hybrid CNN-LSTM model's effectiveness in accurately forecasting energy consumption and production. It makes an important contribution to more efficient use of energy resources.

Spam messages have emerged as a significant issue in digital communication, adversely affecting users’ mental health, personal safety, and network resources. Traditional spam detection methods often suffer from low detection rates and high false positives, underscoring the need for more effective solutions. This paper proposes the EGMA model, an ensemble learning-based hybrid approach for spam detection in SMS messages, which integrates gated recurrent unit (GRU), multilayer perceptron (MLP), and hybrid autoencoder models utilizing a majority voting algorithm. The EGMA model enhances performance by incorporating additional statistical features extracted from message content and employing text vectorization techniques, such as Term Frequency–Inverse Document Frequency (TF-IDF) and CountVectorizer. The proposed model achieved impressive classification accuracies of 99.28% on the SMS Spam Collection dataset, 99.24% on the Email Spam dataset, 99.00% on the Enron-Spam dataset, 98.71% on the Super SMS dataset, and 95.09% on UtkMl’s Twitter Spam dataset. These results demonstrate that the EGMA model outperforms individual models and existing methods in the literature, providing a robust solution for enhancing spam detection performance and effectively mitigating the threats that spam messages pose in digital communication.

This study proposes a novel hybrid convolution and vision transformer model (ConvViT) designed to detect harmful insect species that adversely affect agricultural production and play a critical role in global food security. By utilizing a dataset comprising images of 15 distinct insect species, the suggested approach combines the strengths of traditional convolutional neural networks (CNNs) with vision transformer (ViT) architectures. This integration aims to capture local-level morphological features effectively while analyzing global spatial relationships more comprehensively. While the CNN structure excels at discerning fine morphological details of insects, the ViT’s self-attention mechanism enables a holistic evaluation of their overall configurations. Several data preprocessing steps were implemented to enhance the model’s performance, including data augmentation techniques and strategies to ensure class balance. In addition, hyperparameter optimization contributed to more stable and robust model training. Experimental results indicate that the ConvViT model outperforms commonly used benchmark architectures such as EfficientNetB0, DenseNet201, ResNet-50, VGG-16, and standalone ViT, achieving a classification accuracy of 93.61%. This hybrid approach improves accuracy and strengthens generalization capabilities, delivering steady performance during training and testing phases, thereby increasing its reliability for field applications. The findings highlight that the ConvViT model achieves high efficiency in pest detection by integrating local and global feature learning. Consequently, this scalable artificial intelligence solution can support sustainable agricultural practices by enabling the early and accurate identification of pests and reducing the need for intensive pesticide use.

Stream clustering has emerged as a vital area for processing streaming data in real-time, facilitating the extraction of meaningful information. While efficient approaches for defining and updating clusters based on similarity criteria have been proposed, outliers and noisy data within stream clustering areas pose a significant threat to the overall performance of clustering algorithms. Moreover, the limitation of existing methods in generating non-spherical clusters underscores the need for improved clustering quality. As a new methodology, we propose a new stream clustering approach, MCMSTStream, to overcome the abovementioned challenges. The algorithm applies MST to micro-clusters defined by using the KD-Tree data structure to define macro-clusters. MCMSTStream is robust against outliers and noisy data and has the ability to define clusters with arbitrary shapes. Furthermore, the proposed algorithm exhibits notable speed and can handling high-dimensional data. ARI and Purity indices are used to prove the clustering success of the MCMSTStream. The evaluation results reveal the superior performance of MCMSTStream compared to state-of-the-art stream clustering algorithms such as DenStream, DBSTREAM, and KD-AR Stream. The proposed method obtained a Purity value of 0.9780 and an ARI value of 0.7509, the highest scores for the KDD dataset. In the other 11 datasets, it obtained much higher results than its competitors. As a result, the proposed method is an effective stream clustering algorithm on datasets with outliers, high-dimensional, and arbitrary-shaped clusters. In addition, its runtime performance is also quite reasonable.