Intelligent Environments require perception systems capable of adapting to evolving tasks, heterogeneous sensing conditions, and the resource constraints of large-scale IoT deployments. This work shows an edge-centric pipeline in which a highcapacity model, specifically YOLO12n, operates at the gateway to automatically label visual data and guide the specialization of TinyML models deployed on low-power devices. Focusing on two representative mobility-related classes, cat (present in COCO) and scooter (absent from COCO), we analyze the behavior of YOLO models under zero-shot conditions, during finetuning, and when incrementally integrating new classes. Results show that YOLO12n consistently outperforms YOLO11n in zeroshot evaluation and reaches near-perfect detection accuracy (mAP@50 up to 0.995) after only a few epochs of fine-tuning, with inference times below 5 ms on GPU-equipped edge nodes. When adding the new scooter class, the model rapidly adapts, yet subsequent fine-tuning on cats reveals strong catastrophic forgetting. Rehearsal-based retraining effectively mitigates this degradation, even when using replay buffers as small as$\mathbf{1 0 - 2 0 o r i g i n a l}$dataset. These findings demonstrate that lightweight edge auto-labeling combined with efficient replay mechanisms enables sustainable, privacy-preserving, and continuously adaptive perception pipelines for next-generation Intelligent Environments and IoT monitoring infrastructures.

Stream Processing Systems (SPSs) are designed to process continuous streams of events, often under highly variable input rates. Although prior work has explored dynamic operator replication, many existing approaches lack generalizability and perform suboptimally across diverse scenarios. In this article, we present MMP-SPS, a predictive self-adaptive framework that extends extends our prior PA-SPS system by introducing a multi-window control loop, support for multiple prediction models, and online model selection via RMSE-based evaluation and multi-armed bandits. Targeting environments with high-volume and fluctuating data streams, such as social media analytics and network traffic monitoring, the framework dynamically selects the most suitable model based on real-time workload characteristics using a reinforcement learning (RL) strategy. To prove the validity of our system, we deployed an implementation of MMP-SPS based on Apache Storm, and we evaluated it on Google Cloud Platform against real-world datasets. Experimental results show substantial improvements in latency, throughput, and resource utilization compared to static and single-model baselines. These findings underscore the potential of multi-model predictive adaptation for scalable and robust stream processing under dynamic conditions.

Monitoring invasive species is essential for protecting biodiversity in sensitive ecosystems. In the natural park of Torrevieja (Alicante, Spain), domestic cats threaten local bird populations, including endangered species. To address this issue, we developed a system leveraging deep-learning models, including YOLO (You Only Look Once), to detect cats in real-time automatically. Our solution involves deploying edge-AI cameras equipped with LoRa communication technology to efficiently transmit detection data to the cloud. This infrastructure enables continuous monitoring, accurate detection, and prompt invasive species reporting while optimizing power consumption and network bandwidth. In this paper, we present the development and evaluation of multiple deep-learning models, assess their prediction accuracy, and discuss the integration of LoRa technology to enhance data transmission in remote areas. Our findings demonstrate the feasibility and effectiveness of using edge-AI and IoT technologies for biodiversity conservation in protected natural environments.

Measuring ephemeral stream flows is essential for ecological and hydrological studies. However, their intermittent nature and remote locations pose challenges for conventional monitoring methods, which often consume excessive energy to capture rare events. We address this with BODOQUE (Bimodal Observational Device for Optimizing Quantification of Ephemeral streams), a dual-mode system that leverages Tiny Machine Learning (TinyML) on low-power microcontrollers. The system remains in an energy-saving sensing state and activates high-precision measurements only when water flow is detected. We present a model selection methodology that balances detection accuracy with inference cost, enabling reliable operation within hardware constraints. To enhance adaptability in diverse environments, we developed a specialized component that facilitates dataset expansion through new field samples. This supports ongoing retraining to maintain model performance under changing conditions. A comprehensive evaluation using real-world data demonstrates that our system can achieve up to 97% annual energy savings compared to traditional continuous monitoring approaches.

Efficient long-range communication is critical for environmental monitoring, especially when dealing with large data transfers in remote areas. We present an AI-driven dynamic RF configuration mode, which combines the advanced capabilities of a novel AI*LoRa model with an enhanced RF configuration request mechanism. By leveraging TinyML, AI*LoRa dynamically adjusts key parameters of the physical layer, based on real-time environmental data, ensuring robust and energy-efficient communication. We conducted extensive real-world testing across distances ranging from a few meters to over 100 kilometers to collect the dataset necessary for training our model. The results demonstrate that our approach achieved over 90% accuracy in predicting optimal settings, leading to an average improvement of over 170% in communication efficiency. These findings underscore AI*LoRa's significant potential to enhance long-range IoT deployments.

Environmental intelligence aims to improve the decision-making process for high social and environmental value ecosystems. To this end, data are collected using different sensors to allow monitoring of different variables of interest. Typically, these ecosystems cover a large geographical area, with spots of low or no connectivity, preventing their monitoring in real time. In this work, we propose AlLoRa (Advanced Layer LoRa), a modular, low-power, long-range communication protocol based on LoRa, that allows monitoring of remote natural areas. AlLoRa has been evaluated and tested in an operational oceanographic buoy that has been deployed to address the specific environmental crisis of the Mar Menor lagoon in southeastern Spain - a region spanning 135 Km2 currently undergoing severe eutrophication process. Our results reveal that AlLoRa offers good performance regarding transfer time, power consumption, and range. The throughput ranged from around 2 kbps with SF7 to approximately 300 bps with SF11; the power consumption per kilobyte transmitted varied from 395μWh to 428μWh depending on the specific device used. The Mesh mode test successfully maintained communication between nodes over 20.33 km. Further tests in various configurations under challenging conditions validated the mesh forwarding approach. Despite tripling the distance, the system maintained reliable data transfer, improving speeds from the original point-to-point setup.

On post disaster scenarios, communication infrastructure can be seriously compromised, generating intermittent or null Internet access. Delay Tolerant Networks (DTNs) are a promising communication mechanism able to deal with connection disruptions enabling communication for affected people. DTNs forward messages through untrusted devices, which have better probability to reach destination. However, they are susceptible to attacks where participants forge their metrics in order for them to appear as a better alternative to route messages, thus most traffic is attracted to them. This problem is known as the blackhole attack. In this work we propose a routing protocol that verifies participants' interactions using the Guy Fawkes protocol for an encounter-based routing protocol which routes messages based on the interactions of nodes. We propose a transmission ticket in order to achieve accountability in the actions of nodes. Routing decisions are based on the past tickets collected by the nodes. Our protocol creates a more reliable routing path by preventing the creation of fake interactions, and therefore blackhole attacks. Results show that our protocol reduces the number of messages attracted by malicious peers performing a blackhole attack, maintaining good delivery rates and low overhead for different network scenarios.

Nowadays, the overwhelming amount of data generated on Internet have boosted the development of new solutions to process data on time windows closer to real time. Such solutions are known as Distributed Stream Processing Engines (DSPEs). DSPEs were specially designed to process data streams over cluster infrastructure, however the great massification of mobile devices opens new opportunities to process data closer to the source in order to reduce latency and traffic over the network. In this paper we propose Symbiosis, an architecture oriented to process data streams over mobile clients such as tablets and smartphones. Symbiosis model aims to exploit mobile devices resources to pre-process data streams generated on neighbors clients. Implementing data processing on mobile nodes is challenging due to their mobility and the limited battery power. In order to cope with such a requirements, Symbiosis proposes a data processing method based on checkpoints which consider both mobility and available energy in the device.

Distributed Hash Tables (DHTs) provide the substrate to build scalable and efficient Peer-to-Peer (P2P) networks: distributed systems with the potential to handle massive amounts of data on a very large scale. However, traditional DHTs provide very poor support for range queries. In this article we present a search mechanism that efficiently supports range queries over a ring-like DHT structure using a prefix tree index. Load balancing is improved by delegating the routing of queries to the nodes that store data, and by updating neighbor information through an optimistic approach. Our solution reduces latency and message traffic in environments where queries are more frequent than data insertion operations. We evaluate the performance of the system through simulations and show that our solution in not affected by data skewness.

This paper proposes a two-level caching strategy for Web search queries which is devised to operate on P2P networks. The aim is to significantly reduce query traffic going from a large community of users to commercial search engines by placing between them a P2P caching service capable of storing and efficiently distributing frequent queries among users. The proposed design takes into consideration the highly dynamic nature of user queries both in traffic intensity and drastic shifts in user interest which are both usually driven by unpredictable world-wide events. Each peer maintains a LRU result cache (RCache) used to keep the answers for queries originated in the peer itself and queries for which the peer is responsible for by contacting on-demand a Web search engine to get the query answers. When query traffic is predominantly routed to a few responsible peers our strategy replicates the role of ``being responsible for" to neighboring peers so that they can absorb part of the traffic to restore load balance. This is a fairly slow and adaptive process that we call mid-term load balancing. To achieve a short-term fair distribution of queries we introduce in each peer a location cache (LCache) which keeps pointers to peers that have already requested the same queries in the very recent past. This lets these peers share their query answers with newly requesting peers. This process is fast as these popular queries are usually cached in the first DHT hop of a requesting peer which quickly tends to redistribute load among more and more peers. A comparative study shows that the proposed strategy achieves better load balance, significantly smaller communication volume among peers, and larger cache hit ratios than previous strategies.

Building trust is a major concern in Peer-to-Peer networks as several kinds of applications rely on the presence of trusted services. Traditional techniques do not scale, produce very high overheads or rely on unrealistic assumptions. In this paper, we propose a new membership algorithm (Community Of Reputable PeerS, CORPS) for Distributed Hash Tables which builds a community of reputable nodes and thus enables the implementation of pseudo-trusted services. CORPS uses a reputation-based approach to decide whether a node can be a member of the group or not. We demonstrate the benefits of this approach and evaluate how much it improves the reliability of a trusted routing service.