This study investigates the potential of machine learning techniques for detecting Equatorial Plasma Bubbles (EPBs) using nighttime airglow imagery from the Global-scale Observations of the Limb and Disk (GOLD) mission. EPBs are ionospheric irregularities characterized by significant plasma density depletions that disrupt trans-ionospheric radio wave propagation, affecting satellite navigation and communication systems. We propose and implement a convolutional encoder-decoder neural network specifically designed for precise pixel-level segmentation of EPB structures within GOLD’s 135.6 nm radiance images. The convolutional neural network demonstrated remarkable performance, achieving high precision and recall, successfully detecting prominent EPBs as well as subtle features overlooked in manual annotations. Results also reveal the network’s capability to generalize beyond explicitly labeled data, indicating its robustness in capturing intricate EPB morphologies. Additionally, a preliminary cross-validation was conducted using GNSS Radio Occultation (RO) data, which showed promising correspondence with the EPB locations identified by the machine learning algorithm. This supports the value of integrating deep learning methods with GNSS-RO techniques to achieve comprehensive global detection and validation of EPBs.

The ability to make decisions according to environmental factors is crucial for Situational Awareness (SA). In the maritime sector, a variety of tools have been introduced to provide operators with situational awareness, such as radars and Automatic Identification Systems (AIS). However, enhancing these tools using assistant systems is important to make the information more concise and reliable for the operators. This paper presents a situational awareness enhancement system for categorizing airborne targets using data collected from a radar system onboard a vessel. The targets are ranked from low to high priority, which would increase the situational awareness of naval operators. To do so, a set of attributes is extracted from the radar data to describe airborne targets. Then, two methods of fuzzy c-means clustering and artificial neural networks are investigated for this task. The experimental results show promising performance for both models, with the neural networks and the fuzzy c-means clustering reaching the accuracy of 92.6% and 80.3%, respectively. This indicates that the proposed system can be utilized to increase situational awareness by ranking the targets effectively.

This letter introduces a novel regression model structure for the inflated Rayleigh distribution, which effectively models high dynamic amplitude pixel values in synthetic aperture radar (SAR) images. The proposed model estimates the mean of inflated Rayleigh distribution signals by a structure that includes a set of regressors and a link function. The inflated Rayleigh distribution combines the Rayleigh and a degenerate distribution, assigning non-null probability specifically for observed values equal to zero. Null pixel values in amplitude SAR images can be randomly distributed within the image, especially in low-intensity areas; a model capable of incorporating these values is essential to avoid changes in image statistics. Extensive evaluations are conducted using simulated and real SAR images to validate the proposed model, specifically focusing on ground-type detection in high dynamic amplitude pixel values scenarios. The performance of the proposed inflated Rayleigh regression model is compared with traditional Gaussian-based regression models, excelling in terms of ground-type detection in a SAR image obtained from the ICEYE radar. 

This paper presents a crucial multispectral image registration and sensor calibration method for an agricultural application. The multispectral images are obtained using a special drone equipped with multiple cameras flying at low altitudes. However, the distance between lenses, the lens distortions and the low-altitude flights lead to a lack of alignment in the built-in normalized difference vegetation index (NDVI). This lack of alignment results in a very poor performance in further analysis, especially for image segmentation and target detection to distinguish crops from invasive plants. In this work, we point out the importance of reducing this misalignment. To do so, the near-infrared and red sensors are first calibrated to remove the lens distortions. Then, the corresponding keypoints are utilized to calculate the transformation matrix and to minimize the back-projection error. The registered near-infrared and red images are then used to compute NDVI. The experimental results show higher alignment and F1-score of 0.73 which is a significant improvement in the performance of a trained deep neural network using NDVI in the detection of invasive plants. This is particularly a challenging task as the invasive plants resemble the desired crops.

The process of internationalising higher education brings about numerous benefits f or t eaching a nd l earning activities. It fosters an extensive exchange of information that extends beyond national borders. Nonetheless, achieving an acceptable standard of quality to meet the expectations of international students necessitates diligent feedback and inquiry to comprehend and address their experiences effectively. This work's primary objective is to investigate international students experiences, focusing on factors that can influence t h eir a c ademic pursuits, including learning activities, learning environment, academic collaboration and social integration at a higher education institute in Sweden. This study employs a quantitative analysis methodology to examine anonymous surveys completed by a group of international students at our university. The gathered data were classified i n to t h ree d i stinct c a tegories a n d subjected to separate analyses within each category. The findings suggest that the expectations of international students are met mainly regarding learning activities, receiving the highest score. However, challenges were observed in the learning environment, especially with regard to academic collaboration and social integration with domestic students. Recommendations for improvement include promoting social integration, enhancing academic collaboration, improving information dissemination, and establishing partnerships with the municipality to ensure better accommodation. These findings offer valuable insights for our university and other institutions striving to enhance international students' educational quality and overall experience. © 2024 IEEE.

Generating precise saliency maps from eye tracker fixation points is a challenging task influenced by environmen-tal factors and the choice of evaluation metrics. This paper presents a novel, sustainable, scale-invariant, and sampling-independent method for converting fixation points into saliency maps. Leveraging the inherent predictability of human behavior, the proposed method ensures the highest compatibility with the chosen evaluation metric. Moreover, it introduces a mechanism to calculate the maximum achievable similarity score for each conversion. In addition, it offers crucial insights for both saliency map evaluation and the training of machine learning systems dedicated to saliency map generation. Experimental results demonstrate the method's efficacy in producing saliency maps that align seamlessly with diverse evaluation metrics, showcasing its adaptability and predictive capabilities. This approach con-tributes not only to the refinement of saliency map generation but also to the broader understanding of the intricacies involved in converting eye tracker data into meaningful ground truths. © 2024 IEEE.

Synthetic aperture radar (SAR) data are widely used for remote sensing applications, such as change detection and environmental monitoring. This paper presents a recent measurement campaign for SAR images using the LORA system and investigates the applicability of the collected data for change detection. The region of interest in this study is a busy commercial harbour area in the south of Sweden. During the measurements, there were significant changes on the ground in the parking lot as trucks were disembarking a ship. The obtained SAR images were first filtered to have similar regions of interest in the Fourier domain to increase the coherence magnitude. Then, a constant false alarm rate (CFAR) algorithm was employed to detect changes with respect to trucks. In addition, optical aerial images were collected during this measurement campaign and were utilized to adjust the CFAR detection threshold. As a result, all the changed and unchanged regions corresponding to the selected targets were detected successfully. Moreover, a pattern of trucks’ utilization of the harbour’s parking lot during this peak time was obtained. The results demonstrate the applicability of the data from the ongoing measurement campaign and the possibility of further algorithm development for target detection and classification.

This paper describes a new measurement campaign for SAR images. The data consists of images collected by the Swedish LORA system associated with VHF-band (19-90 MHz). Due to the system frequency, detecting targets concealed in a forest is possible. Thus, this paper aims to share with the community the results of utilizing new VHF-band SAR data that allows the development of new methods for target and other change detection. In particular, to show the applicability of the new data set, a simple change detection method was performed to detect targets in a forest, resulting in 100% of detection, associated with no false alarm in a particular region of interest.

It is no secret that the engagement of the students in any course is necessary for their learning process. Therefore, it is worth focusing on increasing their motivation and engagement during their studies. In addition, it may be more crucial in distance courses to increase engagement where in-person interactions are minimized. Needless to say that different courses may require different approaches to reach this common goal. In my experience in teaching both in-person and distance courses, I noticed two simple ways to enhance students’ engagement: giving examples from real-world applications and providing constructive feedback.

Synthetic aperture radars (SAR) data plays an important role in remote sensing applications. It is common knowledge that SAR image amplitude pixels can be approximately modeled by the Rayleigh distribution. However, this model is contin-uous and does not accommodate points with non-zero prob-ability, such as a null pixel amplitude value. Thus, in this paper, we propose an inflated Rayleigh distribution for SAR image modeling that is based on a mixed continuous-discrete distribution and can be used to fit signals with observed values on [0, infty). The maximum likelihood approach is considered to estimate the parameters of the proposed distribution. An empirical experiment with a SAR image is also presented and discussed. © 2022 IEEE.