Francisco Lloret Abrisqueta
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Francisco Lloret Abrisqueta has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Antonio Guerrero-González
Department of Automation, Electrical Engineering, and Electronic Technology, Polytechnic University of Cartagena, 30203 Cartagena, Spain
10 shared publications - Francisco García-Córdova
Department of Automation, Electrical Engineering, and Electronic Technology, Polytechnic University of Cartagena, 30203 Cartagena, Spain
4 shared publications - Carlos Torregrosa Bonet
Department of Automation, Electrical Engineering, and Electronic Technology, Polytechnic University of Cartagena, 30203 Cartagena, Spain
2 shared publications - Fernando Hidalgo-Castelo
Department of Automation, Electrical Engineering, and Electronic Technology, Polytechnic University of Cartagena, 30203 Cartagena, Spain
2 shared publications - Tomás Inglés Muñoz
Department of Automation, Electrical Engineering, and Electronic Technology, Polytechnic University of Cartagena, 30203 Cartagena, Spain
2 shared publications - Antonio Jesús Martínez-Espinosa
Department of Building and Urbanism, Area of Urban and Regional Planning, University of Alicante, 03690 Alicante, Spain
1 shared publication
Latest Publications
- Open Access
- 31 October 2026
- Published by MDPI AG in Electronics
- Vol. 15 (21) , 5053
Automatic Estimation of Manual Sorting Efficiency in Non-Ferrous Scrap Recycling Using Dual-Camera Computer Vision and Deep Learning
Manual picking is a critical refining stage in non-ferrous scrap recycling, yet it is rarely measured continuously. This study presents a dual-camera computer-vision system that estimates manual sorting efficiency by counting materials before and after picking. YOLO detectors trained on an in-plant dataset (4361 images, four classes) are combined with a Kalman-filter tracker and line-crossing counters to yield per-class and hourly efficiency indicators. YOLOv11m reached a higher maximum F1-score (0.82 vs. 0.79), and selected models attained mAP@50 values of 0.85–0.86. Image-level splitting may make detector metrics optimistic; stage comparisons are indicative only. In a six-hour test, 3753 input objects and 690 output objects were counted, yielding a count-derived global efficiency estimate of 81.61% (95% Wilson interval, sampling only: 80.34–82.82%). Estimated efficiency exceeded 90% for circuit boards and rubber but was only 75.95% and 73.75% for copper and brass, the most valuable fractions. This demonstrates end-to-end operation, not validated accuracy: no manual reference counts or real output-camera test images were available, so all efficiency values are conditional on the automatic counts. Sensitivity analysis quantifies error propagation into the indicator. The results show the feasibility of detection, tracking, and input–output comparison as a monitoring prototype for Industry 4.0 recycling lines.
- 31 October 2026
- Published by MDPI AG in Electronics
- Vol. 15 (21) , 5053
Open AccessAutomatic Estimation of Manual Sorting Efficiency in Non-Ferrous Scrap Recycling Using Dual-Camera Computer Vision and Deep Learning
Manual picking is a critical refining stage in non-ferrous scrap recycling, yet it is rarely measured continuously. This study presents a dual-camera computer-vision system that estimates manual sorting efficiency by counting materials before and after picking. YOLO detectors trained on an in-plant dataset (4361 images, four classes) are combined with a Kalman-filter tracker and line-crossing counters to yield per-class and hourly efficiency indicators. YOLOv11m reached a higher maximum F1-score (0.82 vs. 0.79), and selected models attained mAP@50 values of 0.85–0.86. Image-level splitting may make detector metrics optimistic; stage comparisons are indicative only. In a six-hour test, 3753 input objects and 690 output objects were counted, yielding a count-derived global efficiency estimate of 81.61% (95% Wilson interval, sampling only: 80.34–82.82%). Estimated efficiency exceeded 90% for circuit boards and rubber but was only 75.95% and 73.75% for copper and brass, the most valuable fractions. This demonstrates end-to-end operation, not validated accuracy: no manual reference counts or real output-camera test images were available, so all efficiency values are conditional on the automatic counts. Sensitivity analysis quantifies error propagation into the indicator. The results show the feasibility of detection, tracking, and input–output comparison as a monitoring prototype for Industry 4.0 recycling lines.
- Open Access
- 9 June 2026
- Published by MDPI AG in Electronics
- Vol. 15 (12) , 2547
Local LLMs for Industrial Supervision and Control: An Edge AI Event-Driven Architecture for Proactive Operational Context Management in Real Industrial Environments
Access to operational information in industrial plants forces operators to interrupt their tasks, walk to the human–machine interface (HMI) terminals, and navigate heterogeneous platforms—namely programmable logic controllers (PLC), supervisory control and data acquisition (SCADA) systems, manufacturing execution systems (MES), and enterprise resource planning (ERP) systems—consuming 15–30 min per query. Previous work integrated local large language models (LLMs) into a five-layer cognitive architecture deployed in a precast concrete plant, reducing that time to 14–23 s through voice-based conversational queries; however, model inference accounted for 55.3% of total latency and the system remained reactive. This work incorporates the event-driven paradigm as a non-intrusive augmentation layer that keeps the operational context permanently updated, continuously monitoring the process and refreshing knowledge only when significant changes occur. The architecture is fully local, cloud-independent, graphics processing unit (GPU)-free, and containerized via Docker Compose. Experimental results demonstrate a 26–31% reduction in response times (means of 9.84 s, 11.23 s, and 16.47 s for simple, moderate, and complex queries), an 8.4 °C reduction in peak hardware temperature (from 79.6 °C to 71.2 °C), a 41.6% decrease in thermal variability, and an expansion of the safety margin before central processing unit (CPU) throttling from 5.4 °C to 13.8 °C. The system achieved 100% success rate and availability over 30 min of autonomous operation, validated in a real industrial environment.
- 9 June 2026
- Published by MDPI AG in Electronics
- Vol. 15 (12) , 2547
Open AccessLocal LLMs for Industrial Supervision and Control: An Edge AI Event-Driven Architecture for Proactive Operational Context Management in Real Industrial Environments
Access to operational information in industrial plants forces operators to interrupt their tasks, walk to the human–machine interface (HMI) terminals, and navigate heterogeneous platforms—namely programmable logic controllers (PLC), supervisory control and data acquisition (SCADA) systems, manufacturing execution systems (MES), and enterprise resource planning (ERP) systems—consuming 15–30 min per query. Previous work integrated local large language models (LLMs) into a five-layer cognitive architecture deployed in a precast concrete plant, reducing that time to 14–23 s through voice-based conversational queries; however, model inference accounted for 55.3% of total latency and the system remained reactive. This work incorporates the event-driven paradigm as a non-intrusive augmentation layer that keeps the operational context permanently updated, continuously monitoring the process and refreshing knowledge only when significant changes occur. The architecture is fully local, cloud-independent, graphics processing unit (GPU)-free, and containerized via Docker Compose. Experimental results demonstrate a 26–31% reduction in response times (means of 9.84 s, 11.23 s, and 16.47 s for simple, moderate, and complex queries), an 8.4 °C reduction in peak hardware temperature (from 79.6 °C to 71.2 °C), a 41.6% decrease in thermal variability, and an expansion of the safety margin before central processing unit (CPU) throttling from 5.4 °C to 13.8 °C. The system achieved 100% success rate and availability over 30 min of autonomous operation, validated in a real industrial environment.
- Open Access
- 20 May 2026
- Published by MDPI AG in Electronics
- Vol. 15 (10) , 2204
Artificial Intelligence for Autonomous Vehicles: Robustness Analysis in Complex Urban Traffic Scenarios
Autonomous driving in complex urban environments remains challenging due to perception uncertainty, dynamic multi-agent interactions, and control instability under adverse conditions. Despite advances in individual components, systematic evaluations of fully integrated modular pipelines under compounded urban disturbances remain scarce. This work presents a modular autonomous driving framework in CARLA Town10HD, integrating Convolutional Neural Network (CNN)-based perception using ResNet-18, global path planning via A* algorithm, and two control strategies: a classical Proportional–Integral–Derivative (PID) controller and a Deep Q-Network (DQN) agent with adaptive geometric steering assistance. A structured protocol assessed robustness across five scenarios: Heavy Rain, Dense Fog, Nighttime Driving, Dense Traffic, and Combined Extreme Conditions. The perception module achieved F1-scores close to 0.99 for traffic-sign, pedestrian, and lane classification; results reflect synthetic CARLA data and should not be interpreted as real-world generalization. The PID controller produced smoother trajectories with lower steering oscillations, while the DQN agent achieved faster traversal times at the cost of higher control variability. Route efficiency remained around 0.96 under isolated disturbances and decreased to 0.52 under compounded conditions, confirming sensitivity to multi-factor complexity. This study contributes a reproducible multi-scenario benchmark quantifying stability–adaptability trade-offs between classical and learning-based control, identifying scenario generalization and simulation-to-reality transfer as key future directions.
- 20 May 2026
- Published by MDPI AG in Electronics
- Vol. 15 (10) , 2204
Open AccessArtificial Intelligence for Autonomous Vehicles: Robustness Analysis in Complex Urban Traffic Scenarios
Autonomous driving in complex urban environments remains challenging due to perception uncertainty, dynamic multi-agent interactions, and control instability under adverse conditions. Despite advances in individual components, systematic evaluations of fully integrated modular pipelines under compounded urban disturbances remain scarce. This work presents a modular autonomous driving framework in CARLA Town10HD, integrating Convolutional Neural Network (CNN)-based perception using ResNet-18, global path planning via A* algorithm, and two control strategies: a classical Proportional–Integral–Derivative (PID) controller and a Deep Q-Network (DQN) agent with adaptive geometric steering assistance. A structured protocol assessed robustness across five scenarios: Heavy Rain, Dense Fog, Nighttime Driving, Dense Traffic, and Combined Extreme Conditions. The perception module achieved F1-scores close to 0.99 for traffic-sign, pedestrian, and lane classification; results reflect synthetic CARLA data and should not be interpreted as real-world generalization. The PID controller produced smoother trajectories with lower steering oscillations, while the DQN agent achieved faster traversal times at the cost of higher control variability. Route efficiency remained around 0.96 under isolated disturbances and decreased to 0.52 under compounded conditions, confirming sensitivity to multi-factor complexity. This study contributes a reproducible multi-scenario benchmark quantifying stability–adaptability trade-offs between classical and learning-based control, identifying scenario generalization and simulation-to-reality transfer as key future directions.
- Open Access
Multimodal Cognitive Architecture with Local Generative AI for Industrial Control of Concrete Plants on Edge Devices
Accessing operational information across industrial systems (ERP, MES, SCADA, PLC) in concrete plants requires 15–30 min and specialized knowledge. This work addresses this accessibility gap by developing a conversational AI system that democratizes industrial information access through natural language. A five-layer cognitive architecture was implemented integrating the Mistral-7B model quantized in GGUF Q4_0 format (3.82 GB) on a Raspberry Pi 5, Spanish speech recognition/synthesis, and heterogeneous industrial protocols (OPC UA, MQTT, REST API) across all automation pyramid levels. Experimental validation at Frumecar S.L. (Murcia, Spain) characterized performance, thermal stability, and reliability. Results show response times of 14.19 s (simple queries, SD = 7.56 s), 16.45 s (moderate, SD = 6.40 s), and 23.24 s (complex multilevel, SD = 6.59 s), representing 26–77× improvement over manual methods. The system maintained average temperature of 69.3 °C (peak 79.6 °C), preserving 5.4 °C margin below throttling threshold. Communication latencies averaged 8.93 ms across 10,163 readings (<1% of total latency). During 30 min of autonomous operation, 100% reliability was achieved with 39 successful queries. These findings demonstrate the viability of deploying quantized LLMs on low-cost edge hardware, enabling cognitive democratization of industrial information while ensuring data privacy and cloud independence.
Open AccessMultimodal Cognitive Architecture with Local Generative AI for Industrial Control of Concrete Plants on Edge Devices
Accessing operational information across industrial systems (ERP, MES, SCADA, PLC) in concrete plants requires 15–30 min and specialized knowledge. This work addresses this accessibility gap by developing a conversational AI system that democratizes industrial information access through natural language. A five-layer cognitive architecture was implemented integrating the Mistral-7B model quantized in GGUF Q4_0 format (3.82 GB) on a Raspberry Pi 5, Spanish speech recognition/synthesis, and heterogeneous industrial protocols (OPC UA, MQTT, REST API) across all automation pyramid levels. Experimental validation at Frumecar S.L. (Murcia, Spain) characterized performance, thermal stability, and reliability. Results show response times of 14.19 s (simple queries, SD = 7.56 s), 16.45 s (moderate, SD = 6.40 s), and 23.24 s (complex multilevel, SD = 6.59 s), representing 26–77× improvement over manual methods. The system maintained average temperature of 69.3 °C (peak 79.6 °C), preserving 5.4 °C margin below throttling threshold. Communication latencies averaged 8.93 ms across 10,163 readings (<1% of total latency). During 30 min of autonomous operation, 100% reliability was achieved with 39 successful queries. These findings demonstrate the viability of deploying quantized LLMs on low-cost edge hardware, enabling cognitive democratization of industrial information while ensuring data privacy and cloud independence.
- Open Access
- 17 September 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (18) , 10147
Integration of Industry 5.0 Technologies in the Concrete Industry: An Analysis of the Impact of AI-Based Virtual Assistants
The construction industry, traditionally lagging behind in terms of digitalization, faces significant challenges in its transition to Industry 4.0, which is characterized by the use of advanced technologies such as artificial intelligence (AI), the Industrial Internet of Things (IIoT), and cloud computing. This article presents the development and implementation of an AI-based virtual assistant, designed to optimize the operation and maintenance of concrete production plants. The assistant helps reduce the margin of human error, improve operational efficiency, and facilitate continuous training for operators. These advancements foster a more collaborative and digitalized environment, while also generating environmental, economic, and social benefits: reduced material and energy waste, lower carbon footprint, increased workplace safety, and strengthened organizational resilience. The results show high accuracy in voice transcription (96%) and a 100% success rate in responding to technical queries, demonstrating its effectiveness as a support tool in industrial settings. Based on these findings, it is concluded that the incorporation of AI-based virtual assistants promotes a more sustainable and responsible production model, aligned with the Sustainable Development Goals of the 2030 Agenda, and anticipates the principles of Industry 5.0 by promoting symbiotic collaboration between humans and technology. This innovation represents a key advancement in transforming the concrete industry, contributing to productivity, environmental sustainability, and workplace well-being in the sector.
- 17 September 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (18) , 10147
Open AccessIntegration of Industry 5.0 Technologies in the Concrete Industry: An Analysis of the Impact of AI-Based Virtual Assistants
The construction industry, traditionally lagging behind in terms of digitalization, faces significant challenges in its transition to Industry 4.0, which is characterized by the use of advanced technologies such as artificial intelligence (AI), the Industrial Internet of Things (IIoT), and cloud computing. This article presents the development and implementation of an AI-based virtual assistant, designed to optimize the operation and maintenance of concrete production plants. The assistant helps reduce the margin of human error, improve operational efficiency, and facilitate continuous training for operators. These advancements foster a more collaborative and digitalized environment, while also generating environmental, economic, and social benefits: reduced material and energy waste, lower carbon footprint, increased workplace safety, and strengthened organizational resilience. The results show high accuracy in voice transcription (96%) and a 100% success rate in responding to technical queries, demonstrating its effectiveness as a support tool in industrial settings. Based on these findings, it is concluded that the incorporation of AI-based virtual assistants promotes a more sustainable and responsible production model, aligned with the Sustainable Development Goals of the 2030 Agenda, and anticipates the principles of Industry 5.0 by promoting symbiotic collaboration between humans and technology. This innovation represents a key advancement in transforming the concrete industry, contributing to productivity, environmental sustainability, and workplace well-being in the sector.
- 8 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Latin America Transactions
- Vol. 23 (8) , 729-735
Redefining Human-Machine Collaboration: Industry 5.0 to Improve Safety and Efficiency
This study presents an innovative implementation of Industry 5.0 principles in a window production line, integrating advanced robotics and artificial intelligence technologies to improve operational efficiency and worker well-being. A robotic cell was designed to automate the handling of heavy components in the final production stage, resulting in a 35% reduction in cycle times and a significant decrease in ergonomic risks. Additionally, an interactive voice assistant based on generative AI was implemented, allowing operators to access system data and technical information in real-time through cognitive interaction. The results show a substantial improvement in job satisfaction, with a 278% increase in the perception of occupational health. This approach not only optimizes productivity but also redefines workers' roles, aligning with the human-centered vision of Industry 5.0. The study demonstrates how the integration of advanced technologies can create safer, more efficient, and adaptable work environments in modern manufacturing.
- 8 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Latin America Transactions
- Vol. 23 (8) , 729-735
Redefining Human-Machine Collaboration: Industry 5.0 to Improve Safety and Efficiency
This study presents an innovative implementation of Industry 5.0 principles in a window production line, integrating advanced robotics and artificial intelligence technologies to improve operational efficiency and worker well-being. A robotic cell was designed to automate the handling of heavy components in the final production stage, resulting in a 35% reduction in cycle times and a significant decrease in ergonomic risks. Additionally, an interactive voice assistant based on generative AI was implemented, allowing operators to access system data and technical information in real-time through cognitive interaction. The results show a substantial improvement in job satisfaction, with a 278% increase in the perception of occupational health. This approach not only optimizes productivity but also redefines workers' roles, aligning with the human-centered vision of Industry 5.0. The study demonstrates how the integration of advanced technologies can create safer, more efficient, and adaptable work environments in modern manufacturing.
- Open Access
- 6 November 2024
- Published by MDPI AG in Preprints.org
Interactive Virtual Reality Application for 3D Disassembly and Assembly: Innovation in Industrial Technical Education
This study presents the development of a cutting-edge virtual reality (VR) application aimed at education in industrial and technical environments. Using the Meta Quest 3 system and the ShapesXR platform, the application allows users to interactively disassemble and assemble 3D models in an immersive environment. Detailed models were developed through parametric modeling tools such as Autodesk Fusion 360 and 3D optimization software like Blender, optimized for a high-performance VR environment. The feasibility of the platform as an innovative educational tool was evaluated, and areas for improvement for future iterations of the system were identified.
- 6 November 2024
- Published by MDPI AG in Preprints.org
Open AccessInteractive Virtual Reality Application for 3D Disassembly and Assembly: Innovation in Industrial Technical Education
This study presents the development of a cutting-edge virtual reality (VR) application aimed at education in industrial and technical environments. Using the Meta Quest 3 system and the ShapesXR platform, the application allows users to interactively disassemble and assemble 3D models in an immersive environment. Detailed models were developed through parametric modeling tools such as Autodesk Fusion 360 and 3D optimization software like Blender, optimized for a high-performance VR environment. The feasibility of the platform as an innovative educational tool was evaluated, and areas for improvement for future iterations of the system were identified.
- Open Access
- 23 September 2024
- Published by MDPI AG in Preprints.org
Monitoring and Remote Control of Solar Tracker Using MQTT Technologies
This study presents the development and implementation of a remote monitoring system for a dual-axis solar tracker, integrating Industry 4.0 technologies such as IoT, SCADA, and MQTT. The system, which combines a Siemens S7-1200 PLC, an IoT gateway, and a SCADA platform based on Ignition, demonstrated significant increases in solar capture efficiency, with production gains of 25-30% compared to fixed systems, reaching up to 67.65% under ideal conditions. In addition to improving operational management through predictive monitoring and early fault detection, the study identified areas for improvement, such as the need for real-world testing and the integration of weather predictions. In conclusion, the research validates the feasibility and effectiveness of automated IoT and SCADA-based systems to optimize solar trackers, significantly contributing to improved energy efficiency in photovoltaic installations.
- 23 September 2024
- Published by MDPI AG in Preprints.org
Open AccessMonitoring and Remote Control of Solar Tracker Using MQTT Technologies
This study presents the development and implementation of a remote monitoring system for a dual-axis solar tracker, integrating Industry 4.0 technologies such as IoT, SCADA, and MQTT. The system, which combines a Siemens S7-1200 PLC, an IoT gateway, and a SCADA platform based on Ignition, demonstrated significant increases in solar capture efficiency, with production gains of 25-30% compared to fixed systems, reaching up to 67.65% under ideal conditions. In addition to improving operational management through predictive monitoring and early fault detection, the study identified areas for improvement, such as the need for real-world testing and the integration of weather predictions. In conclusion, the research validates the feasibility and effectiveness of automated IoT and SCADA-based systems to optimize solar trackers, significantly contributing to improved energy efficiency in photovoltaic installations.
- Open Access
- 19 July 2024
- Published by MDPI AG in Preprints.org
Evaluating the Technical and Economic Impact of 4.0 Technologies in Photovoltaic Installations: A Case Study in the Residential and Industrial Sectors of Murcia
The integration of Industry 4.0 technologies in photovoltaic (PV) installations offers significant potential to enhance efficiency, reliability, and economic viability. This study evaluates the technical and economic impacts of implementing the Internet of Things (IoT), artificial intelligence (AI), and advanced data analytics in PV systems within the residential and industrial sectors in the Region of Murcia. Real-time monitoring technologies based on IoT sensors were analyzed to collect data on the operational performance of pilot PV installations. Advanced data analysis techniques, including machine learning, were analyzed to process the collected data, enabling predictive maintenance, performance optimization, and future production estimation. The study also explored the use of drones and computer vision for automated inspection of solar panels, identifying issues such as hotspots and dirt accumulation. The results demonstrate significant improvements in energy efficiency, system availability, and reduction of failures and downtime. Economic analyses indicate cost savings in operation and maintenance and increased overall system reliability. This research identifies key barriers and opportunities for adopting 4.0 technologies in the PV sector and proposes strategies to overcome challenges and leverage benefits. The findings contribute to the advancement of knowledge and the promotion of sustainable and efficient energy systems in the solar industry.
- 19 July 2024
- Published by MDPI AG in Preprints.org
Open AccessEvaluating the Technical and Economic Impact of 4.0 Technologies in Photovoltaic Installations: A Case Study in the Residential and Industrial Sectors of Murcia
The integration of Industry 4.0 technologies in photovoltaic (PV) installations offers significant potential to enhance efficiency, reliability, and economic viability. This study evaluates the technical and economic impacts of implementing the Internet of Things (IoT), artificial intelligence (AI), and advanced data analytics in PV systems within the residential and industrial sectors in the Region of Murcia. Real-time monitoring technologies based on IoT sensors were analyzed to collect data on the operational performance of pilot PV installations. Advanced data analysis techniques, including machine learning, were analyzed to process the collected data, enabling predictive maintenance, performance optimization, and future production estimation. The study also explored the use of drones and computer vision for automated inspection of solar panels, identifying issues such as hotspots and dirt accumulation. The results demonstrate significant improvements in energy efficiency, system availability, and reduction of failures and downtime. Economic analyses indicate cost savings in operation and maintenance and increased overall system reliability. This research identifies key barriers and opportunities for adopting 4.0 technologies in the PV sector and proposes strategies to overcome challenges and leverage benefits. The findings contribute to the advancement of knowledge and the promotion of sustainable and efficient energy systems in the solar industry.
- Open Access
- 11 July 2024
- Published by Universitas Ahmad Dahlan in Buletin Ilmiah Sarjana Teknik Elektro
Precision Agriculture 4.0: Implementation of IoT, AI, and Sensor Networks for Tomato Crop Prediction
Precision agriculture introduces an innovative approach to farm management by involving the use of technologies such as the Internet of Things (IoT), Artificial Intelligence (AI), and sensor networks to optimize resources and increase crop yields. In this context, the present study aimed to develop a tomato crop prediction system using IoT, AI, and sensor networks. A system architecture was designed, including distributed sensors, IoT gateways, and a cloud platform running AI models based on recurrent neural networks. These AI models were trained with environmental data and validated using actual harvest data. The results showed up that the model could predict weekly harvest volumes with an average error of 3.2% during the best 4-week period. The integration of IoT, AI, and sensor networks proved to be effective for accurate crop prediction and has potential for other applications in precision agriculture.
- 11 July 2024
- Published by Universitas Ahmad Dahlan in Buletin Ilmiah Sarjana Teknik Elektro
Open AccessPrecision Agriculture 4.0: Implementation of IoT, AI, and Sensor Networks for Tomato Crop Prediction
Precision agriculture introduces an innovative approach to farm management by involving the use of technologies such as the Internet of Things (IoT), Artificial Intelligence (AI), and sensor networks to optimize resources and increase crop yields. In this context, the present study aimed to develop a tomato crop prediction system using IoT, AI, and sensor networks. A system architecture was designed, including distributed sensors, IoT gateways, and a cloud platform running AI models based on recurrent neural networks. These AI models were trained with environmental data and validated using actual harvest data. The results showed up that the model could predict weekly harvest volumes with an average error of 3.2% during the best 4-week period. The integration of IoT, AI, and sensor networks proved to be effective for accurate crop prediction and has potential for other applications in precision agriculture.