This work presents a real-time video-based fire and smoke detection using YOLOv2 Convolutional Neural Network (CNN) in antifire surveillance systems. YOLOv2 is designed with light-weight neural network architecture to account the requirements of embedded platforms. The training stage is processed off-line with indoor and outdoor fire and smoke image sets in different indoor and outdoor scenarios. Ground truth labeler app is used to generate the ground truth data from the training set. The trained model was tested and compared to the other state-of-the-art methods. We used a large scale of fire/smoke and negative videos in different environments, both indoor (e.g., a railway carriage, container, bus wagon, or home/office) or outdoor (e.g., storage or parking area). YOLOv2 is a better option compared to the other approaches for real-time fire/smoke detection. This work has been deployed in a low-cost embedded device (Jetson Nano), which is composed of a single, fixed camera per scene, working in the visible spectral range. There are not specific requirements for the video camera. Hence, when the proposed solution is applied for safety on-board vehicles, or in transport infrastructures, or smart cities, the camera installed in closed-circuit television surveillance systems can be reused. The achieved experimental results show that the proposed solution is suitable for creating a smart and real-time video-surveillance system for fire/smoke detection.

The Intrusion Detection System (IDS) is an effective tool utilized in cybersecurity systems to detect and identify intrusion attacks. With the increasing volume of data generation, the possibility of various forms of intrusion attacks also increases. Feature selection is crucial and often necessary to enhance performance. The structure of the dataset can impact the efficiency of the machine learning model. Furthermore, data imbalance can pose a problem, but sampling approaches can help mitigate it. This research aims to explore machine learning (ML) approaches for IDS, specifically focusing on datasets, machine algorithms, and metrics. Three datasets were utilized in this study: KDD 99, UNSW-NB15, and CSE-CIC-IDS 2018. Various machine learning algorithms were chosen and examined to assess IDS performance. The primary objective was to provide a taxonomy for interconnected intrusion detection systems and supervised machine learning algorithms. The selection of datasets is crucial to ensure the suitability of the model construction for IDS usage. The evaluation was conducted for both binary and multi-class classification to ensure the consistency of the selected ML algorithms for the given dataset. The experimental results demonstrated accuracy rates of 100% for binary classification and 99.4In conclusion, it can be stated that supervised machine learning algorithms exhibit high and promising classification performance based on the study of three popular datasets.

Nowadays, automatic modulation classification (AMC) has become a key component of next-generation drone communication systems, which are crucial for improving communication efficiency in non-cooperative environments. The contradiction between the accuracy and efficiency of current methods hinders the practical application of AMC in drone communication systems. In this paper, we propose a real-time AMC method based on the lightweight mobile radio transformer (MobileRaT). The constructed radio transformer is trained iteratively, accompanied by pruning redundant weights based on information entropy, so it can learn robust modulation knowledge from multimodal signal representations for the AMC task. To the best of our knowledge, this is the first attempt in which the pruning technique and a lightweight transformer model are integrated and applied to processing temporal signals, ensuring AMC accuracy while also improving its inference efficiency. Finally, the experimental results—by comparing MobileRaT with a series of state-of-the-art methods based on two public datasets—have verified its superiority. Two models, MobileRaT-A and MobileRaT-B, were used to process RadioML 2018.01A and RadioML 2016.10A to achieve average AMC accuracies of 65.9% and 62.3% and the highest AMC accuracies of 98.4% and 99.2% at +18 dB and +14 dB, respectively. Ablation studies were conducted to demonstrate the robustness of MobileRaT to hyper-parameters and signal representations. All the experimental results indicate the adaptability of MobileRaT to communication conditions and that MobileRaT can be deployed on the receivers of drones to achieve air-to-air and air-to-ground cognitive communication in less demanding communication scenarios.

Automatic modulation classification (AMC) plays a critical role in both civilian and military applications. In this letter, we propose a multi-scale radio transformer (Ms-RaT) with dual-channel representation for fine-grained modulation classification (FMC). In Ms-RaT, a dual-channel representation (DcR) of radio signals is designed to help the model learn discriminative features by converging the multi-modality information, including frequency, amplitude, and phase. During the learning process, multi-scale analysis is introduced into the model to form the tighter decision boundary. Finally, extensive simulation results demonstrate that Ms-RaT achieves superior modulation classification accuracy with similar or lower computational complexity than existing state-of-the-art deep learning methods. Through ablation studies, we also validate the effectiveness of DcR and multi-scale analysis in Ms-RaT.

Artificial Intelligence (AI) and Machine Learning (ML) have experienced rapid growth in both industry and academia. However, the current ML and AI models demand significant computing and processing power to achieve desired accuracy and results, often restricting their use to high-capability devices. With advancements in embedded system technology and the substantial development in the Internet of Things (IoT) industry, there is a growing desire to integrate ML techniques into resource-constrained embedded systems for ubiquitous intelligence. This aspiration has led to the emergence of TinyML, a specialized approach that enables the deployment of ML models on resource-constrained, power-efficient, and low-cost devices. Despite its potential, the implementation of ML on such devices presents challenges, including optimization, processing capacity, reliability, and maintenance. This article delves into the TinyML model, exploring its background, the tools that support it, and its applications in advanced technologies. By understanding these aspects, we can better appreciate how TinyML is transforming the landscape of AI and ML in embedded and IoT systems.