Future Internet

This work investigates the deployment of Deep Learning (DL) models for network intrusion detection on resource-constrained IoT devices, using the public CICIoT2023 dataset. In particular, we consider the following DL models: Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), Temporal Convolutional Network (TCN), Multi-Layer Perceptron (MLP). Bayesian optimization is employed to fine-tune the models’ hyperparameters and ensure reliable performance evaluation across both binary (2-class) and multi-class (8-class, 34-class) intrusion detection. Then, the computational complexity of each DL model is analyzed—in terms of the number of Multiply–ACCumulate operations (MACCs), RAM usage, and inference time—through the STMicroelectronics Cube.AI Analyzer tool, with models being deployed on an STM32H7S78-DK board. To assess the practical deployability of the considered DL models, a trade-off score (balancing classification accuracy and computational efficiency) is introduced: according to this score, our experimental results indicate that MLP and TCN outperform the other models. Furthermore, Post-Training Quantization (PTQ) to 8-bit integer precision is applied, allowing the model size to be reduced by more than $90\%$ with negligible performance degradation. This demonstrates the effectiveness of quantization in optimizing DL models for real-world deployment on resource-constrained IoT devices.

Applications of smart cities, smart buildings, smart agriculture systems, smart grids, and other smart systems benefit from Internet of Things (IoT) protocols, networks, and architecture. Wireless Sensor Networks (WSNs) in smart systems that employ IoT use wireless communication technologies between sensors in the Things layer and the Fog layer hub. Such wireless protocols and networks include WiFi, Bluetooth, and Zigbee, among others. However, the payload formats of these protocols are heterogeneous, and thus, they lack a unified frame format that ensures interoperability. In this paper, a lightweight, interoperable frame format for low–rate, small–size Wireless Sensor Networks (WSNs) in IoT–based systems is designed, implemented, and tested. The practicality of this system is underscored by the development of a gateway that transfers collected data from sensors that use the unified frame to online servers via message queuing and telemetry transport (MQTT) secured with transport layer security (TLS), ensuring interoperability using the JavaScript Object Notation (JSON) format. The proposed frame is tested using market–available technologies such as Bluetooth and Zigbee, and then applied to smart home applications. The smart home scenario is chosen because it encompasses various smart subsystems, such as healthcare monitoring systems, energy monitoring systems, and entertainment systems, among others. The proposed system offers several advantages, including a low–cost architecture, ease of setup, improved interoperability, high flexibility, and a lightweight frame that can be applied to other wireless–based smart systems and applications.

Knowledge graphs (KGs) offer a structured and collaborative approach to integrating diverse knowledge from various domains. However, constructing knowledge graphs typically requires significant manual effort and heavily relies on pretrained models, limiting their adaptability to specific sub-domains. This paper proposes an innovative, efficient, and locally deployable knowledge graph construction framework that leverages low-rank adaptation (LoRA) to fine-tune large language models (LLMs) in order to reduce noise. By integrating iterative optimization, consistency-guided filtering, and prompt-based extraction, the proposed method achieves a balance between precision and coverage, enabling the robust extraction of standardized subject–predicate–object triples from raw long texts. This makes it highly effective for knowledge graph construction and downstream reasoning tasks. We applied the parameter-efficient open-source model Qwen3-14B, and experimental results on the SciERC dataset show that, under strict matching (i.e., ensuring the exact matching of all components), our method achieved an F1 score of 0.358, outperforming the baseline model’s F1 score of 0.349. Under fuzzy matching (allowing some parts of the triples to be unmatched), the F1 score reached 0.447, outperforming the baseline model’s F1 score of 0.392, demonstrating the effectiveness of our approach. Ablation studies validate the robustness and generalization potential of our method, highlighting the contribution of each component to the overall performance.