Due to the sharp increase in global industrial production, as well as the over-exploitation of land and sea resources, the quality of drinking water has deteriorated considerably. Furthermore, nowadays, many water supply systems serving growing human populations suffer from shortages since many rivers, lakes, and aquifers are drying up because of global climate change. To cope with these serious threats, smart water management systems are in great demand to ensure vigorous control of the quality and quantity of drinking water. Indeed, water monitoring is essential today since it allows to ensure the real-time control of water quality indicators and the appropriate management of resources in cities to provide an adequate water supply to citizens. In this context, a novel IoT-based framework is proposed to support smart water monitoring and management. The proposed framework, named SmartWater, combines cutting-edge technologies in the field of sensor clouds, deep learning, knowledge reasoning, and data processing and analytics. First, knowledge graphs are exploited to model the water network in a semantic and multi-relational manner. Then, incremental network embedding is performed to learn rich representations of water entities, in particular the affected water zones. Finally, a decision mechanism is defined to generate a water management plan depending on the water zones’ current states. A real-world dataset has been used in this study to experimentally validate the major features of the proposed smart water monitoring framework.

Having access to safe water and using it properly is crucial for human well-being, sustainable development, and environmental conservation. Nonetheless, the increasing disparity between human demands and natural freshwater resources is causing water scarcity, negatively impacting agricultural and industrial efficiency, and giving rise to numerous social and economic issues. Understanding and managing the causes of water scarcity and water quality degradation are essential steps toward more sustainable water management and use. In this context, continuous Internet of Things (IoT)-based water measurements are becoming increasingly crucial in environmental monitoring. However, these measurements are plagued by uncertainty issues that, if not handled correctly, can introduce bias and inaccuracy into our analysis, decision-making processes, and results. To cope with uncertainty issues related to sensed water data, we propose combining network representation learning with uncertainty handling methods to ensure rigorous and efficient modeling management of water resources. The proposed approach involves accounting for uncertainties in the water information system by leveraging probabilistic techniques and network representation learning. It creates a probabilistic embedding of the network, enabling the classification of uncertain representations of water information entities, and applies evidence theory to enable decision making that is aware of uncertainties, ultimately choosing appropriate management strategies for affected water areas.

The remarkable progress of federated learning (FL) has enhancing a range of tasks within computer vision, graph learning and natural language processing fields. and the existing frameworks such as FGL, TFF, and FATE facilitating its application in real-world scenarios. Formal Concept Analysis (FCA) is one of the most known unsupervised knowledge discovery techniques with sound and mathematical foundation theories. Formal concept analysis (FCA) has proved helpful in the resolution of practical problems from fields such software engineering, knowledge engineering and data mining. Nevertheless, the adoption of federated FCA learning (FedFCA) remains limited, as its integration faces hurdles owing to the characteristics nature of lattice structures and formal context representation, which are central to the FCA foundations, even though these elements are widely prevalent. Inspired by the evident demand for such a framework, we begin by identifying the hurdles in crafting an intuitive FedFCA framework. Following this exploration, in this paper, we unveil our contribution: FedFCA , a federated framework designed to provide a Federated Formal Concept Analysis, which is a new approach that uses differential privacy to ensure data protection from local parties. First, each parties generates and encrypts the noisy local lattice, which contains the local data. Afterwards, a global server combines the encrypted noisy lattices from multiple untrusted parties, preserving the privacy of each party's data. We conceptualize the comprehensive framework (FedFCA) as an autonomic micro-service network of loosely integrated services, harmonizing with the principles of autonomy and decentralized management intrinsic to self-* systems. This approach facilitates synchronous or asynchronous communication strategies between servers and participants, encompassing both local lattice and global lattice mining processes. Thorough testing has validated the effectiveness of FedFCA, shedding light on its valuable insights, showcasing its diverse applications, and demonstrating shorter running times and superior applicability when compared with the most advanced benchmark. FedFCA is made available publicly as part of the FedFCA Framework suite on GitHub, encouraging further FCA research and the expansion of applications previously hindered by the absence of specialized tools.