Explore the vast range of titles available.

Brain-computer interfaces (BCIs) based on motor imagery (MI) offer a transformative pathway for rehabilitation, communication, and control by translating imagined movements into actionable commands. However, accurately decoding motor imagery from electroencephalography (EEG) signals remains a significant challenge in BCI research. In this paper, we propose TCFormer, a temporal convolutional Transformer designed to improve the performance of EEG-based motor imagery decoding. TCFormer integrates a multi-kernel convolutional neural network (MK-CNN) for spatial-temporal feature extraction with a Transformer encoder enhanced by grouped query attention to capture global contextual dependencies. A temporal convolutional network (TCN) head follows, utilizing dilated causal convolutions to enable the model to learn long-range temporal patterns and generate final class predictions. The architecture is evaluated on three benchmark motor imagery and motor execution EEG datasets: BCIC IV-2a, BCIC IV-2b, and HGD, achieving average accuracies of 84.79, 87.71, and 96.27%, respectively, outperforming current methods. These results demonstrate the effectiveness of the integrated design in addressing the inherent complexity of EEG signals. The code is publicly available at https://github.com/altaheri/TCFormer .

According to the World Meteorological Organization, since 2000, there has been an increase in global flood-related disasters by 134 percent compared to the previous decades. Efficient flood risk management strategies necessitate a holistic approach to evaluating flood vulnerabilities and risks. Catastrophic losses can occur when the peak flow values in the rivers in a basin coincide. Therefore, estimating the joint flood risks in a region is vital, especially when frequent occurrences of extreme events are experienced. This study focuses on estimating the joint flood risks due to river flow extremes in the Grand River watershed in Canada. For this purpose, the study uses copula analysis to investigate the joint occurrence of extreme river flow events in the Speed and Grand Rivers in the Grand River Watershed in Ontario, Canada. By estimating the joint return period for extreme flows in both rivers, we demonstrate the interdependence of the two river flows and how this interdependence influences the behavior of river flow extreme patterns. Our findings suggest that the interdependence between the two river flows leads to changes in the river flow extreme pattern. Determining the interdependence of floods at multiple locations using state-of-the-art tools will benefit various stakeholders, such as the insurance industry, the disaster management sector, and most importantly, the public.

A decade ago, the crowdsourcing term was first coined and used to represent a method for expressing the wisdom of the crowd in accomplishing two types of tasks. One type includes tasks that need human intelligence rather than machines, and the other type covers those tasks that can be accomplished with a higher time and cost efficiency using the crowd rather than employing experts. The crowdsourcing process contains five modules: The first is designing incentives to mobilize the crowd to do the required task. This step is followed by four modules for collecting and assuring quality and then verifying and aggregating the received information. The verification and quality control can be done for the tasks, collected data and the participants by having more participants answer the same question or accepting answers only from experts to avoid errors from unreliable participants. Methods of discovering topic experts are utilized to discover reliable candidates in the crowd who have relevant experience in the discussed topic. Expert discovery reduces the number of needed participants per question which reduces the overall cost. This work summarizes and reviews the methods used to accomplish each processing step. Yet, choosing a specific method remains application dependent.

Breast cancer is a current problem that causes the death of many women. In this work, we test meta-heuristics applied to the segmentation of mammographic images. Traditionally, the application of these algorithms has a direct relationship with optimization problems; however, in this study, its implementation is oriented to the segmentation of mammograms using the Dunn index as an optimization function, and the grey levels to represent each individual. The update of grey levels during the process results in the maximization of the Dunn’s index function; the higher the index, the better the segmentation will be. The results showed a lower error rate using these meta-heuristics for segmentation compared to a well-adopted classical approach known as the Otsu method.

A thorough understanding of the impact of climatic factors on agricultural production is crucial for improving crop models and enhancing predictability of crop prices and yields. Fluctuations in crop yield and price can have significant implications for the market sector and farming community. Given the projected increase in frequency and intensity of extreme events, reliable modelling of cropping patterns becomes essential. Temperature anomalies are expected to play a prominent role in future extreme events, emphasizing the need to comprehend their influence on crop yield. Forecasting extreme yield, which encompasses both the highest and lowest levels of agricultural production within a given time period, along with peak crop prices representing the highest market values, poses greater challenges in forecasting compared to other values. Probability-based predictions, accounting for uncertainty and variability, offer a more accurate approach for extreme value estimation and risk assessment. In this study, we employ a multivariate analysis based on vine copula to explore the interdependencies between temperature anomalies and daily strawberry yield in Santa Maria, California. By considering the maximum and minimum daily yields each month, we observe an increased probability of yield loss with rising temperature anomalies. While we do not explicitly consider the specific impacts of temperature anomalies under individual Representative Concentration Pathway (RCP) scenarios, our analysis is conducted within the broader context of the current global warming scenario. This allows us to capture the overall anticipated effects of regional temperature anomalies on agriculture. The findings of this study have potential impacts and consequences for understanding the vulnerability of agricultural systems and improving crop model predictions. By enhancing our understanding of the relationships between temperature anomalies and crop yield, we can inform decision-making processes related to the impact of climate change on agriculture. This research contributes to the ongoing efforts in improving agricultural sustainability and resilience in the face of changing climatic conditions.

Convolutional Recurrent architectures are currently preferred for spatio-temporal learning tasks in videos to the 3D convolutional networks which accompany a huge computational burden and it is imperative to understand the working of different architectural configurations. But most of the current works on visual learning, especially for video anomaly detection, predominantly employ ConvLSTM networks and focus less on other possible variants of Convolutional Recurrent configurations for temporal learning which warrants a need to study the different possible variants to make informed, optimal design choices according to the nature of the application at hand. We explore a variety of Convolutional Recurrent architectures and the influence of hyper-parameters on their performance for the task of anomaly detection. Through this work, we also intend to quantify the efficiency of the architectures based on the trade-off between their performance and computational complexity. With comprehensive quantitative and visual evidence, we establish that the ConvGRU based configurations are the most effective and perform better than the popular ConvLSTM configurations on video anomaly detection tasks, in contrast to what is seen from the literature.

One of the major problems in testing software code and assuring its quality is deriving test oracles. This problem becomes more evident when testing machine learning models. To overcome such problems, metamorphic testing is introduced. Metamorphic testing is built to test the presence of metamorphic relations; required relations that should hold for the program to be valid. Those metamorphic requirements are usually articulated by domain experts since they are application dependent which is a costly, complex, and error prone process. Therefore, the automatic detection of such relations can be more efficient for code verification. The novelty of this work is first emphasizing the two-way relationship between metamorphic testing and machine learning; where metamorphic testing is used to assess the effectiveness of machine learning models, while machine learning is used to automatically detect the main metamorphic relations in software code. Secondly, literature metamorphic relations are categorized into the eight main categories defined in literature, and three new metamorphic relations are introduced for the first time. Finally, all literature metamorphic relations are customized to fit the time series forecasting domain. An application is proposed consisting of a deep learning model for forecasting fresh produce yields along with a generalization framework to enable the proposed models to forecast other similar fresh produce yields. The interactive role played by metamorphic testing and machine learning is investigated through the quality assurance of the forecasting application. The datasets used to train and test the deep learning forecasting models as well as the forecasting models are verified using metamorphic tests and the metamorphic relations in the generalization code are automatically detected using support vector machine (SVM) models. Testing revealed the unmatched requirements that are fixed to have a valid application with sound data, effective models, and valid generalization code.

The optic disc (OD) is an important anatomical feature in retinal images, and its detection is vital for developing automated screening programs. Currently, there is no algorithm designed to automatically detect the OD in fundus images captured from Asians which are larger and have thicker vessels compared to Caucasians. In this paper, we propose such a method to complement current algorithms using two steps: OD vessel candidate detection and OD vessel candidate matching. The first step is achieved with multiscale Gaussian filtering, scale production, and double thresholding to initially extract the vessels' directional map of various thicknesses. The map is then thinned before another threshold is applied to remove pixels with low intensities. This result forms the OD vessel candidates. In the second step, a Vessels' Directional Matched Filter (VDMF) of various dimensions is applied to the candidates to be matched, and the pixel with the smallest difference designated the OD center. We tested the proposed method on a new database consisting of 402 images from a diabetic retinopathy (DR) screening programme consisting of Asians. The OD center was successfully detected with an accuracy of 99.25% (399/402).

Continual learning models are known to suffer from catastrophic forgetting . Existing regularization methods to countering forgetting operate by penalizing large changes to learned parameters. A significant downside to these methods, however, is that, by effectively freezing model parameters, they gradually suspend the capacity of a model to learn new tasks. In this paper, we explore an alternative approach to the continual learning problem that aims to circumvent this downside. In particular, we ask the question: instead of forcing continual learning models to remember the past, can we modify the learning process from the start, such that the learned representations are less susceptible to forgetting? To this end, we explore multiple methods that could potentially encourage durable representations. We demonstrate empirically that the use of unsupervised auxiliary tasks achieves significant reduction in parameter re-optimization across tasks, and consequently reduces forgetting, without explicitly penalizing forgetting. Moreover, we propose a distance metric to track internal model dynamics across tasks, and use it to gain insight into the workings of our proposed approach, as well as other recently proposed methods.

Detecting topics from Twitter streams has become an important task as it is used in various fields including natural disaster warning, users opinion assessment, and traffic prediction. In this article, we outline different types of topic detection techniques and evaluate their performance. We categorize the topic detection techniques into five categories which are clustering, frequent pattern mining, Exemplar-based, matrix factorization, and probabilistic models. For clustering techniques, we discuss and evaluate nine different techniques which are sequential k-means, spherical k-means, Kernel k-means, scalable Kernel k-means, incremental batch k-means, DBSCAN, spectral clustering, document pivot clustering, and Bngram. Moreover, for matrix factorization techniques, we analyze five different techniques which are sequential Latent Semantic Indexing (LSI), stochastic LSI, Alternating Least Squares (ALS), Rank-one Downdate (R1D), and Column Subset Selection (CSS). Additionally, we evaluate several other techniques in the frequent pattern mining, Exemplar-based, and probabilistic model categories. Results on three Twitter datasets show that Soft Frequent Pattern Mining (SFM) and Bngram achieve the best term precision, while CSS achieves the best term recall and topic recall in most of the cases. Moreover, Exemplar-based topic detection obtains a good balance between the term recall and term precision, while achieving a good topic recall and running time.