Logistics is significantly impacted by quality/quantity issues associated with data collection and data sharing restrictions. Nonetheless, public data from national entities and internet-of-things (IoT) solutions enable the development of integrated tools for performance analysis and real-time optimization of logistics networks. This study proposes a three-module data-driven system architecture that covers (a) logistics data collection tools, (b) logistics services performance evaluation, and (c) the transition to synchromodal systems. Module 1 integrates multisource data from national logistics platforms and embedded devices placed within intermodal containers. A multigraph representation of the problem is conceived. Environmental, economic, and operational data are generated and injected into a digital twin. Thus, key performance indicators (KPIs) are computed by simulation or direct transformation of the collected data. Module 2 uses Multi-directional Efficiency Analysis, an optimization algorithm that benchmarks multimodal transportation routes of containers using prior KPIs. Outputs are a technical performance index relevant to logistics clients and improvement measures for logistics service providers. A real case study application of the solution proposed for Module 2 is presented. Module 3 provides real-time scheduling and assignment models using CP-sat solvers, accommodating varying system dynamics and resource availability, minimizing makespan and operational costs.

Increasing digitalization and automation have elevated the importance of data analysis in reducing waste and costs, optimizing resources, and enhancing sustainability. However, as processes approach their optimization limits, traditional analytics become insufficient. This study introduces ImproveXpert4.0, a big data-driven platform designed to uncover actionable insights from process data through six algorithmic modules. These modules employ Machine Learning, Explainable AI, Operational Research, and Statistical methods for root cause analysis, bottleneck detection, simulation, prediction, human performance assessment, and variation prediction. ImproveXpert4.0 was developed using Design Science Research Methodology, and its algorithms were validated in real-world Manufacturing and Logistics settings. Its conceptual foundation is presented through two key artifacts: (1) the DMAIC-PDCA Structural Flowchart, which outlines its operating logic and algorithmic integration, and (2) a High-Level Architecture that details the technological infrastructure. Insights from a Narrative Literature Review and semi-structured interviews with Kaizen experts from award-winning organizations helped define the practical requirements for the system’s design. The platform contributes to both theory and practice by promoting a structured, data-driven approach to Continuous Improvement in digital organizations.

Detecting water leakage represents a significant and pervasive challenge in water supply systems due to the complexity of network behavior, and the diversity of leakage manifestations, which may remain undetected. The magnitude of leakage varies considerably, from 3% to over 50%, depending on the level of maintenance undertaken. The global volume of water loss per year is estimated to be 126 billion cubic meters, equivalent to a financial loss of over 30 billion USD. To address this problem, leakage management strategies have been developed, including preventive measures, systematic assessment protocols, regulatory frameworks, stringent control measures, detection and localization techniques, and prompt repair initiatives. The detection and localization phase is particularly important due to its inherent complexity and critical role, where various techniques are used, including hardware- and software-based, and hybrid methods. These techniques include the implementation of Machine Learning models that provide an advantage in automated data analysis, leading to faster detection and localization of leakage in water supply systems. Moreover, commercial solutions and patented technologies are continuing to converge into more integrated and scalable monitoring strategies. This paper presents a state-of-the-art review of scientific, commercial, and industrial developments in water leakage management for water supply systems. The scientific review provides a critical and integrative comparison of existing methodologies, highlighting the trade-offs regarding practical applicability, including scalability, data dependency, uncertainty propagation, and localization accuracy. Additionally, Machine Learning applications to this field, as well as leak detection and localization performance indicators, are presented. A focused analysis of the BattLeDIM competition highlights leading methodologies and underlines the potential of hybrid approaches that merge hydraulic modeling with advanced analytics. Furthermore, the commercial and industrial analysis provides valuable insights into the main technologies and techniques employed by leading companies, and the current status of registered patents regarding water leakage detection and localization, highlighting interesting trends. Overall, this review bridges scientific, commercial, and industrial knowledge across sectors and highlights key priorities for advancing scalable and operationally robust leakage detection strategies.

Problem-solving based, as much as possible, on real data, expert knowledge, and on-field observation are quite desired objectives. However, it creates several difficulties on deployment in real situations. In this work, a data-driven version of the well-known PDCA cycle is proposed for continuous improvement within a general class of problems represented by key performance indicators (KPI). Such class is wide enough to accommodate several real problems but still has a controlled level of complexity that allows defining a general data-driven protocol that covers all the (sub)steps of the cycle. New approaches and alternatives in the literature are discussed. A brief example of one of the steps of the protocol is given with real data from a company that adopts many of the new Industry 4.0 technologies.