1,066 research outputs found
Incremental firmware update over-the-air for low-power IoT devices over LoRaWAN
No full textRemote firmware updates in Internet of Things (IoT) devices remain a major challenge due to the constraints of many IoT communication protocols. In particular, transmitting full firmware images over low-bandwidth links such as Long Range Wide Area Network (LoRaWAN) is often impractical. Existing techniques, such as firmware partitioning, can alleviate the problem but are often insufficient, especially for battery-powered devices where time and energy are critical constraints. Consequently, physical maintenance is still frequently required, which is costly and impractical in large-scale deployments. In this work, we introduce bpatch, a lightweight method for generating highly compact delta patches that enable on-device firmware reconstruction. The algorithm is explicitly designed for low-power devices, minimizing memory requirements and computational overhead during the update process. We evaluate bpatch on 173 firmware images across three architectures. Results show that it reduces update payloads by up to 39,000x for near-identical updates and by 9–18x for typical minor revisions, eliminating the need to transmit full firmware images. Experimental results further demonstrate significant time and energy savings, with performance comparable to more complex alternatives. bpatch is released as open-source and, although demonstrated on LoRaWAN, the approach is flexible and can be adapted to other IoT communication technologies
Audio-Based Identification of Queen Bee Presence Inside Beehives
No full textHoneybees are essential for the health of people and the planet. They play a key role in the pollination of most crops. The high mortality observed in the last decade, caused by stress factors among which the climate change, have raised the necessity of remote sensing the beehives to help monitor the health of honeybees and better understand this phenomenon. Several solutions have been proposed in the literature, and some of them include the analysis of in-hive sounds. In this scenario, we explore the potential of machine learning methods for queen bee detection using only the audio signal, being a good indicator of the colony state of health. In particular, we experiment support vector machines and neural network classifiers. We consider the effect of varying the audio chunk duration and the adoption of different hyperparameters
A Machine Learning Approach for Queen Bee Detection Through Remote Audio Sensing to Safeguard Honeybee Colonies
No full textHoneybees play a pivotal role in maintaining global ecosystems and agricultural productivity through their indispensable contribution to crop pollination. However, the alarming rise in honeybee mortality, attributed to various stress factors including climate change, has highlighted the urgency of implementing effective monitoring strategies. Remote sensing of beehives emerges as a promising solution, with a focus on understanding and mitigating the impacts of these stressors. Differently from other approaches proposed in the literature, this study specifically explores the potential of lightweight machine learning models and the extraction of compressed feature to enable future deployment on microcontroller devices. The experimentation involves the application of support vector machines and neural network classifiers, considering the influence of variable audio chunk durations, the utilization of different hyperparameters and combining the audio recorded in several hives and available in different datasets
A quantitative approach to testing in Quantum dot Cellular Automata: NanoMagnet Logic case
No full textWith the approaching of CMOS scaling limits the interest on emerging technologies is rapidly growing. Among emerging technologies, Quantum dot Cellular Automata (QCA) is one of the most studied. Particularly the magnetic implementation, NanoMagnet Logic (NML), offers very low power consumption and it combines logic and memory on a unique device. Despite the advantages of these technologies, QCA and NML working principle relies on the electric or magnetic interaction among neighbor cells, so it is very sensitive to process variations. The behavior of circuits is therefore largely affected by defects and fabrication variations. To effectively design circuits with these technologies, proper tools for testing circuits are necessary. In this work we present an innovative test environment for NML technology. The test algorithm is integrated in ToPoliNano, our design and simulation tool for emerging technologies, and it is specifically tailored to support the analysis of faults in large complexity circuits. Thanks to this tool it is possible to design and test complex NML circuits considering the effect of process variations in terms of Yield and Output Error Rate. The approach gives then feedback to the technologists, remarkably helping the future development of this technology. Moreover, notwithstanding the methodology is applied here to NML circuits only, it can also be successfully applied to QCA technology in general, greatly enhancing the value of the work we proposed her
Domain Wall Interconnections for NML
No full textNanoMagnet Logic is one of the most novel solutions studied as complementary technology to CMOS transistors. Information propagation involves only a change in spin orientation, no charge movement is present. Since the basic element is a nanomagnet, NML circuits have no stand-by power consumption and the ability to mix logic and memory in the same device. While CMOS is a multilayer technology, until now NML is confined to one single physical layer. The consequence is that circuit area grows exponentially due to interconnections overhead. In this paper we present an innovative solution that drastically reduces the area wasted for interconnection wires relying on the properties of Domain Walls (DWs). We mix DWs and NML technologies in a unique Doman Wall Logic (DWL) solution that exploits the advantages of both technologies. The proposed solution is technologically compatible with up-to-date fabrication processes. All the results here presented for the NML logic blocks and the DWs interconnections and their combination are obtained through rigorous micromagnetic simulations. Moreover, we implemented as a case study an high performance adder (Pentium-4 Adder) and evaluated its features with increasing parallelism and compared to the simple NML implementation in order to explore the potential of DWL technology at circuit and architectural level. The reduction in circuit area corresponds to a notable reduction in both latency and power consumption. The improvements in NML technology are shown by both the remarkable performance improvement and new possibilities offered by this novel solution
Custom Memory Design for Logic-in-Memory: Drawbacks and Improvements over Conventional Memories
No full textThe speed of modern digital systems is severely limited by memory latency (the “Memory Wall” problem). Data exchange between Logic and Memory is also responsible for a large part of the system energy consumption. Logic-in-Memory (LiM) represents an attractive solution to this problem. By performing part of the computations directly inside the memory the system speed can be improved while reducing its energy consumption. LiM solutions that offer the major boost in performance are based on the modification of the memory cell. However, what is the cost of such modifications? How do these impact the memory array performance? In this work, this question is addressed by analysing a LiM memory array implementing an algorithm for the maximum/minimum value computation. The memory array is designed at physical level using the FreePDK 45nm CMOS process, with three memory cell variants, and its performance is compared to SRAM and CAM memories. Results highlight that read and write operations performance is worsened but in-memory operations result to be very efficient: a 55.26% reduction in the energy-delay product is measured for the AND operation with respect to the SRAM read one. Therefore, the LiM approach represents a very promising solution for low-density and high-performance memories
Device for Data Storage and Processing, and Method Thereof
No full textA device for data storage and processing includes: at least two input racetrack elements having a plurality of first magnetization regions; at least one output racetrack element having a plurality of second magnetization regions, wherein a magnetization vector is adapted to switch from a first direction to the opposite one, or vice versa, by way of a magnetic field of reduced intensity compared with a magnetic field required to produce a similar switching of a magnetization vector of the first magnetization region, wherein the input racetrack elements and output racetrack element are configured in such a way as to constitute at least one elementary logic gate, wherein at least two of the first magnetization regions are magnetically coupled to at least one of the second magnetization regions
Advancing Beekeeping: IoT and TinyML for Queen Bee Monitoring Using Audio Signals
No full textBeekeeping plays an essential role in maintaining ecosystems through pollination and enhancing biodiversity. The presence of the queen bee inside the hive is an important indicator for the health of the bee colony. Monitoring the health of honeybees and their hives is crucial not only for bees but also for the entire ecosystem. This article introduces a tiny machine learning (ML) application for edge computing in the Internet-of-Things (IoT) systems, designed to predict the queen bee's presence. The solution, implemented on a low-power microcontroller (MCU), listens to the sound produced by honeybees and aids beekeepers by automating health assessments of the colony. The system utilizes audio recordings of honeybees combined with artificial intelligence (AI) techniques, while the second focuses on optimizing a feature extraction algorithm from these recordings to minimize latency and energy use in the IoT setup. The findings show that despite the implementation of a simpler ML model and audio preprocessing with lower computational precision, the final metrics remain comparable to those analyzed, with only a limited reduction
An Integrated Multi-Sensor System for Remote Bee Health Monitoring
No full textOver 75% of the world's food crops depends on pollination and in particular by the inestimable value of the service provided by bees. Besides, the bee colony health is a good indicator of the quality of the environment and it is strongly affected by many aspects such as beekeepers' management practices, policies adopted for cropping and land use. However, the climate change, the intensive agriculture, pesticides, biodiversity loss, Varroa mites and pollution are the leading cause of bees death world wide. The role of beekeepers is of extremely importance to mitigate this damage. Apiaries are usually located in remote environment an require frequent visit by the beekeepers. Indeed, the beekeeping sector lacks of suitable tools for risk assessment and decision making that can be used by stakeholders. Smart monitoring systems assessing the health of the colony and the honey production would be beneficial for such community. In this work, we present a prototype of an embedded multi-sensor system for beehive monitoring with the aim of providing a simple solution to beekeepers. Indeed, the proposed system do not require modification of the beehive and it is compact enough to be simply inserted in the brood box. It measures the vital parameters of the beehive, such as temperature, weight, humidity and CO2 concentration. It exploits the low power communication protocol LoRaWAN for the data transmission. The collected data are made available to the beekeeper through a web application. We show the effectiveness of such compact, non-invasive embedded system with its installation in an apiary
- …
