Low-power embedded systems have been widely used in a variety of applications, allowing devices to efficiently collect and exchange data while minimizing energy consumption. However, the lack of extensive maintenance procedures designed specifically for low-power systems, coupled with constraints on anticipating faults and monitoring capacities, presents notable difficulties and intricacies in identifying failures and customized reaction mechanisms. The proposed approach seeks to address the gaps in current resource management frameworks and maintenance protocols for low-power embedded systems. Furthermore, this paper offers a trilateral framework that provides periodic prescriptions to stakeholders, a periodic control mechanism for automated actions and messages to prevent breakdowns, and a backup AI malfunction detection module to prevent the system from accessing any stress points. To evaluate the AI malfunction detection module approach, three novel autonomous embedded systems based on different ARM Cortex cores have been specifically designed and developed. Real-life results obtained from the testing of the proposed AI malfunction detection module in the developed embedded systems demonstrated outstanding performance, with metrics consistently exceeding 98%. This affirms the efficacy and reliability of the developed approach in enhancing the fault tolerance and maintenance capabilities of low-power embedded systems.

Fire incidents in residential and industrial areas are often the cause of human casualties and property damage. Although there are existing systems that detect fire and monitor the presence of people in indoor areas, research on their implementation in embedded platforms is limited. This article introduces an ultra-low-power embedded system for fire detection and crowd counting using efficient deep learning methods. For the prediction of fire occurrences, environmental and gas sensor along with multilayer perceptron nodes are used. For crowd counting, a custom lightweight version of YOLOv5 is introduced, using an architecture based on ShuffleNetV2, resulting in a model with low memory requirements, high accuracy predictions, and fast inference on an embedded platform. The accuracy, power consumption, and memory requirements of the proposed system are evaluated using public datasets and datasets acquired by the environmental and image sensors, and its performance is compared to that of existing approaches.

Harvesting energy for IoT nodes in places that are permanently poorly lit is important, as many such places exist in buildings and other locations. The need for energy-autonomous devices working in such environments has so far received little attention. This work reports the design and test results of an energy-autonomous sensor node powered solely by solar cells. The system can cold-start and run in low light conditions (in this case 20 lux and below, using white LEDs as light sources). Four solar cells of 1 cm² each are used, yielding a total active surface of 4 cm². The system includes a capacitive sensor that acts as a touch detector, a crystal-accurate real-time clock (RTC), and a Cortex-M3-compatible microcontroller integrating a Bluetooth Low Energy radio (BLE) and the necessary stack for communication. A capacitor of 100 μF is used as energy storage. A low-power comparator monitors the level of the energy storage and powers up the system. The combination of the RTC and touch sensor enables the MCU load to be powered up periodically or using an asynchronous user touch activity. First tests have shown that the system can perform the basic work of cold-starting, sensing, and transmitting frames at +0 dBm, at illuminances as low as 5 lux. Harvesting starts earlier, meaning that the potential for full function below 5 lux is present. The system has also been tested with other light sources. The comparator is a test chip developed for energy harvesting. Other elements are off-the-shelf components. The use of commercially available devices, the reduced number of parts, and the absence of complex storage elements enable a small node to be built in the future, for use in constantly or intermittently poorly lit places.

Citizen science reinforces the development of emergent tools for the surveillance, monitoring, and early detection of biological invasions, enhancing biosecurity resilience. The contribution of farmers and farm citizens is vital, as volunteers can strengthen the effectiveness and efficiency of environmental observations, improve surveillance efforts, and aid in delimiting areas affected by plant-spread diseases and pests. This study presents a robust, user-friendly, and cost-effective smart module for citizen science that incorporates a cutting-edge developed hyperspectral imaging (HI) module, integrated in a single, energy-independent device and paired with a smartphone. The proposed module can empower farmers, farming communities, and citizens to easily capture and transmit data on crop conditions, plant disease symptoms (biotic and abiotic), and pest attacks. The developed HI-based module is interconnected with a smart embedded system (SES), which allows for the capture of hyperspectral images. Simultaneously, it enables multimodal analysis using the integrated environmental sensors on the module. These data are processed at the edge using lightweight Deep Learning algorithms for the detection and identification of Tuta absoluta (Meyrick), the most important invaded alien and devastating pest of tomato. The innovative Artificial Intelligence (AI)-based module offers open interfaces to passive surveillance platforms, Decision Support Systems (DSSs), and early warning surveillance systems, establishing a seamless environment where innovation and utility converge to enhance crop health and productivity and biodiversity protection.