Tiny Machine Learning (TinyML) is an emerging technology proposed by the scientific community for developing autonomous and secure devices that can gather, process, and provide results without transferring data to external entities. The technology aims to democratize AI by making it available to more sectors and contribute to the digital revolution of intelligent devices. In this work, a classification of the most common optimization techniques for Neural Network compression is conducted. Additionally, a review of the development boards and TinyML software is presented. Furthermore, the work provides educational resources, a classification of the technology applications, and future directions and concludes with the challenges and considerations.

The use of action cameras for photogrammetry purposes is not widespread due to the fact that until recently the images provided by the sensors, using either still or video capture mode, were not big enough to perform and provide the appropriate analysis with the necessary photogrammetric accuracy. However, several manufacturers have recently produced and released new lightweight devices which are: (a) easy to handle, (b) capable of performing under extreme conditions and more importantly (c) able to provide both still images and video sequences of high resolution. In order to be able to use the sensor of action cameras we must apply a careful and reliable self-calibration prior to the use of any photogrammetric procedure, a relatively difficult scenario because of the short focal length of the camera and its wide angle lens that is used to obtain the maximum possible resolution of images. Special software, using functions of the OpenCV library, has been created to perform both the calibration and the production of undistorted scenes for each one of the still and video image capturing mode of a novel action camera, the GoPro Hero 3 camera that can provide still images up to 12 Mp and video up 8 Mp resolution.

Food safety is a fundamental right in modern societies. One of the most pressing problems nowadays is the provenance of food and food-related products that citizens consume, mainly due to several food scares and the globalization of food markets, which has resulted in food supply chains that extend beyond nations or even continent boundaries. Food supply networks are characterized by high complexity and a lack of openness. There is a critical requirement for applying novel techniques to verify and authenticate the origin, quality parameters, and transfer/storage details associated with food. This study portrays an end-to-end approach to enhance the security of the food supply chain and thus increase the trustfulness of the food industry. The system aims at increasing the transparency of food supply chain monitoring systems through securing all components that those consist of. A universal information monitoring scheme based on blockchain technology ensures the integrity of collected data, a self-sovereign identity approach for all supply chain actors ensures the minimization of single points of failure, and finally, a security mechanism, that is based on the use of TinyML’s nascent technology, is embedded in monitoring devices to mitigate a significant portion of malicious behavior from actors in the supply chain.

Internet of Things devices are frequently used as consumer devices to provide digital solutions, such as smart lighting and digital voice-activated assistants, but they are also employed to alert residents in the instance of an emergency. Given the increasingly costly nature of present neural network systems, it is necessary to transport information to the cloud for intelligent machine analysis. TinyML is a potential technology that has been presented by the research world for building fully independent and safe devices that can gather, analyze, and produce data, without transferring it to distant organizations. This paper describes a gas leakage detection system based on TinyML. The proposed solution can be programmed to identify anomalies and warn occupants via the utilization of the BLE technology, in addition to an incorporated LCD screen. Experiments have been employed to show and assess two distinct test situations. For the first occasion, the smoke detection test case, the system earned an F1-Score of 0.77, whereas the F1-Score for the ammonia test case was 0.70.

Unmanned aerial vehicles (UAVs) have increasingly proven to be flexible tools for mapping mine terrain, offering expedient and precise data compared to alternatives. Photogrammetric outputs are particularly beneficial in open pit operations and waste dump areas, since they enable cost-effective and reproducible digital terrain models. Meanwhile, UAV-based LiDAR has proven invaluable in situations where uniform ground surfaces, dense vegetation, or steep slopes challenge purely photogrammetric solutions. Recent advances in machine learning and deep learning have further enhanced the capacity to distinguish critical features, such as vegetation and fractured rock surfaces, thereby reducing the likelihood of accidents and ecological damage. Nevertheless, scientific gaps remain to be researched. Standardization around flight practices, sensor selection, and data verification persists as elusive, and most mining sites still rely on limited, multi-temporal surveys that may not capture sudden changes in slope conditions. Complexity lies in devising strategies for rehabilitated dumps, where post-mining restoration efforts involve vegetation regrowth, erosion mitigation, and altered land use. Through expanded sensor integration and refined automated analysis, approaches could shift from information gathering to ongoing hazard assessment and environmental surveillance. This evolution would improve both safety and environmental stewardship, reflecting the emerging role of UAVs in advancing a more sustainable future for mining.