Object detection models often struggle with class imbalance, where rare categories appear significantly less frequently than common ones. Existing sampling-based rebalancing strategies, such as Repeat Factor Sampling (RFS) and Instance-Aware Repeat Factor Sampling (IRFS), mitigate this issue by adjusting sample frequencies based on image and instance counts. However, these methods are based on linear adjustments, which limit their effectiveness in long-tailed distributions. This work introduces Exponentially Weighted Instance-Aware Repeat Factor Sampling (E-IRFS), an extension of IRFS that applies exponential scaling to better differentiate between rare and frequent classes. E-IRFS adjusts sampling probabilities using an exponential function applied to the geometric mean of image and instance frequencies, ensuring a more adaptive rebalancing strategy. We evaluate E-IRFS on a dataset derived from the Fireman-UAV-RGBT Dataset and four additional public datasets, using YOLOv11 object detection models to identify fire, smoke, people and lakes in emergency scenarios. The results show that E-IRFS improves detection performance by 22% over the baseline and outperforms RFS and IRFS, particularly for rare categories. The analysis also highlights that E-IRFS has a stronger effect on lightweight models with limited capacity, as these models rely more on data sampling strategies to address class imbalance. The findings demonstrate that E-IRFS improves rare object detection in resource-constrained environments, making it a suitable solution for real-time applications such as UAV-based emergency monitoring. The code is available at: https://github.com/futurians/E-IRFS.

Wildfire detection in the densely forested and remote regions of Finland presents substantial challenges. This paper introduces a new publicly available dataset, FireMan-UAV-RGBT, comprising UAV-captured RGB and thermal video data to advance wildfire detection methodologies. The dataset includes high-resolution images of boreal forests that have been carefully annotated both manually and using a semi-automatic method that leverages thermal information for improved RGB image segmentation. The utility of the dataset is assessed by applying established deep learning models (ResN et50 and YOLOv8), and comparing their performance in unimodal and multimodal detection approaches. The performance is evaluated using both intra-set validation on the novel dataset and inter-set evaluation through cross-validation with the Flame-1 and Flame-2 datasets, demonstrating the usability of our dataset in wildfire detection scenarios. The FireMan-UAV-RGBT dataset represents a step forward in wildfire management, offering a resource that may contribute to cost-effective and environmentally sensitive solutions in remote sensing and emergency response strategies.

Smart spaces, physical spaces that are integrated with sensor-enabled IoT devices, are a powerful paradigm for optimizing the operations of the space and improving its quality for the occupants. Managing the applications and services running in the space is a complex task as the operations of the devices and services are dependent on the physical characteristics of the space, the occupants of the space, and the technologies that are being integrated. Digital twinning, the combination of physical representations with a virtual counterpart, is a potential technology for facilitating the management of smart space devices and services. While digital twins are increasingly adopted in industry, their use in everyday environments remains low due to difficulties in creating and linking the virtual representation with the physical environment. In this paper, we propose our vision for the adoption of digital twinning as a pathway to improve the functions of smart spaces. We derive a generic reference architecture that comprises four layers, covering the physical space, the sensing infrastructure, the network interfaces, and the underlying computational infrastructure. Next, we identify and address key requirements for the uptake of digital twins in smart space and assess their benefits using the ascendancy model of business analytics. Finally, to demonstrate the practicality of digital twinning, we present a proof-of-concept digital twin for the TellUs smart space at the University of Oulu in Finland and use it to highlight the potential benefits of different ascendancy levels.

During the past years, the LoRaWAN technology took a prominent position among the wireless connectivity solutions for the Internet of Things (IoT) and has attracted substantial attention. The LoRaWAN technology has become popular for collecting the data from the sensors, which traditionally have periodic communication patterns. Meanwhile, recent studies have shown that the LoRaWAN procedures, such as the over-the-air activation, may also compromise the uniformity of data traffic distribution. Therefore, in this study, we investigate how the communication pattern of LoRaWAN devices during activation and data communication affects the overall network performance with respect to speed of activation and overall packet delivery probability. We show that the periodic communication patterns, widely employed by commercial LoRaWAN devices today, are less efficient than the patterns featuring random delays between the packets. Also, we find that introduction of a random delay between uplink data packets helps randomizing the channel access and enables network performance boost both for the application data transfer and during the activation. Finally, we show that implementation of the suggested communication patterns modification is feasible for the state-of-the-art LoRaWAN transceivers with no hardware modifications.

Efficiency and flexibility are among the key requirements for Wireless Sensor and Actuator Networks (WSAN) of Internet of Things (IoT) era. In this work we present and demonstrate a novel WSAN and IoT platform. The new nodes are constructed by stacking together the different hardware modules encapsulating power sources, processing units, wired and wireless transceivers, sensors and actuators, or sets of those. Once a node is built, its processing unit can automatically identify all the connected hardware modules, obtain required software modules and tune node's operation accounting for its structure, available resources and active applications.

In the paper we present and demonstrate the modular prototyping platform designed for trialing the Internet of Things (IoT) applications. The new devices are constructed by stacking together the various hardware modules encapsulating power sources, processing units, wired and wireless transceivers, sensors and actuators, or sets of those. The main processing unit automatically identifies all the attached modules and adjusts own operation accordingly. The demo will showcase how the platform can be used for building up multi-radio technology enabled wireless devices which will automatically form a heterogeneous wireless sensor and actuator network (WSAN). The possible use case scenarios and the ongoing research activities around the platform will be highlighted as well.

A co-primary spectrum sharing trial is presented in this paper. It is presenting a flexible way to share resources between multiple operators in order to increase spectral efficiency. In this trial the differences in traffic patterns of the mobile network operators are exploited to ease up the peak traffic demands of particular operator. This shared recourse is also usable for inter-operator D2D communication, when two users of different operators want to communicate and operators need to negotiate resource allocation for this communication link. We will also introduce Wireless Open Access Research Platform as our choice for the implementation of this trial.