Artificial Intelligence

This figure shows the accuracy and loss curves generated during the training process. We trained different neural networks on the CIFAR-100 dataset. For each network, the same training strategy was applied to every image in the dataset. The blue curve represents the accuracy after replacing the convolution layers, which achieves a higher accuracy compared to other networks.In the figure, the green curve represents the network after replacing standard convolution with the SCT module. We can see that the red and green curves converge towards the end.

The Theory of Integrated Language Learning (ToILL) supports many complementary schools of educational thought. The constructivism, pragmatism, humanism, and sociocultural theory are combined in one process to produce an integrated and successful method of language acquisition. The approach promotes the complete person development in a continuously changing environment that is global in nature but does not stop at cognitive components but also concerns the social and emotional experiences of the students.

The DRIVE dataset, developed by Staal et al. (2004), utilizes the elongated structure of vessel ridges for automatic vessel classification in the Utrecht database. It consists of 40 images (565 × 584 pixels) in JPEG format, captured at a 45° field of view, divided into 20 training and 20 testing images.

This dataset originates from a longitudinal study examining the factors contributing to the progression of cardiovascular disease. P This particular research employs the unprocessed sequential actigraph recordings collected from an actigraph device. We evaluate sleep quality based on the two indicators as proposed in our previous study [3] which are weekly sleep quality ‘SleepQualWeek’, and sleep consistency ‘SleepCons’. SleepQualWeek and SleepCons are calculated using the pre-processed attribute set derived from the MESA dataset. 

The increasing prevalence of encrypted traffic in

modern networks poses significant challenges for network security,

particularly in detecting and classifying malicious activities

and application signatures. To overcome this issue, deep learning

has turned out to be a promising candidate owing to its ability

to learn complex data patterns. In this work, we present a

deep learning-based novel and robust framework for encrypted

traffic analysis (ETA) which leverages the power of Bidirectional

This dataset is from "One-Stage Cascade Refinement Networks for Infrared Small Target Detection." It includes 427 infrared images and 480 targets (due to the lack of infrared sequences, SIRST also contains infrared images at a wavelength of 950 nm, in addition to shortwave and midwave infrared images). Approximately 90% of the images contain only one target, while about 10% have multiple targets (which may be overlooked in sparse/significant methods due to global unique assumptions).

This custom dataset was created to support gait recognition research using Inertial Measurement Units (IMUs), which capture acceleration, angular velocity, and orientation data from key body locations (e.g., ankles, waist, wrists). It includes recordings from [insert number] participants performing various walking tasks under different conditions, such as normal and fast walking or navigating obstacles. The dataset provides time-series data suitable for both traditional feature-based analysis and deep learning approaches.

When training supervised deep learning models for despeckling SAR images, it is necessary to have a labeled dataset with pairs of images to be able to assess the quality of the filtering process. These pairs of images must be noisy and ground truth. The noisy images contain the speckle generated during the backscatter of the microwave signal, while the ground truth is generated through multitemporal fusion operations. In this paper, two operations are performed: mean and median.

In the domain of gait recognition, the scarcity of non-simulated, real-world data significantly hampers the performance and applicability of recognition systems. To address this limitation, we present a comprehensive gait recognition dataset - GaitMotion- collected using built-in sensors of Android smartphones in an uncontrolled, real-world environment. This dataset captures the walking activity of 24 subjects (14 females and 10 males) above 18 years old and weighing at least 50 kg.

This dataset is utilized for adversarial camouflage generation. We collect vehicle datasets in the CARLA simulation environment under 16 weather conditions. These weather conditions are generated by combining four sun altitude angles (-90°, 10°, 45°, 90°) with four fog densities (0, 25, 50, 90). Within each weather scenario,  we randomly choose 16 locations for texture generation. Camera transformation values are randomly selected within specified intervals at each car location.