Fig 1.
System architecture diagram illustrating the integration of sensing, AI-driven classification, servo-based actuation, laser marking, and FSM control for adaptive cut-shape placement on coconut shells.
Fig 2.
Finite-state machine (FSM) logic flow of the proposed automation process, depicting sequential state transitions from shell detection and measurement to classification, marking, and actuation.
Fig 3.
3D CAD rendering of the proposed embedded automation system. The model illustrates key mechanical components including the coconut shell holder, dual servo-driven rotating plate, conveyor assembly, and laser marking rail.
Fig 4.
Electrical circuit schematic showing Raspberry Pi GPIO and I²C-based interfacing with sensors, actuators, and output modules.
Fig 5.
Modular software architecture illustrating interactions between sensing, inference, actuation, and FSM logic.
Table 1.
Core hardware components and specifications of the proposed embedded automation system, detailing the controller, sensors, actuators, and structural materials used.
Fig 6.
Assembled prototype of the embedded automation system for coconut shell marking, showing (a) the mechanical shell holder for stable positioning, (b) the camera mount for overhead imaging and classification, (c) the Time-of-Flight (ToF) module for non-contact surface profiling, and (d) the servo–laser subsystem for adaptive orientation and marking indication.
Fig 7.
2D technical drawing of the prototype, showing (a) isometric view, (b) top view, (c) front view, and (d) side view with dimensional specifications (in mm).
Fig 8.
Software pipeline showing modular interactions between image capture, inference, actuation, and laser control under FSM orchestration.
Table 2.
Average execution time per system module of the proposed embedded automation system, benchmarked over 50 trials.
Table 3.
Evaluation metrics and their definitions used to assess the performance of the proposed embedded automation system for coconut shell marking.
Table 4.
Average marking time per shell for manual and automated methods, showing a significant reduction in cycle duration achieved by the proposed embedded automation system.
Fig 9.
Comparison of marking time between automated and manual methods across 20 coconut shell samples, showing consistently lower cycle times with the proposed embedded automation system.
Table 5.
Average deviation from the optimal cut center for manual and automated marking methods, showing significantly higher accuracy achieved with the proposed embedded automation system.
Fig 10.
Comparison of cut placement accuracy between automated and manual marking methods across 20 coconut shell samples, showing consistently higher accuracy with the proposed system.
Table 6.
Average material utilization for manual and automated marking methods, showing a substantial improvement in usable shell surface area with the proposed embedded automation system.
Table 7.
Average number of successful cuts per shell obtained through manual and automated marking methods, showing higher productive yield and consistency with the proposed embedded automation system.
Fig 11.
Comparison of usable cut yield per coconut shell across 20 samples, showing consistently higher productive output with the automated method compared to manual marking.
Table 8.
Summary of performance improvements achieved by the proposed embedded automation system over manual marking, showing gains in speed, accuracy, material utilization, and productive yield.
Table 9.
Summary of the key contributions and innovations of the proposed embedded automation system, highlighting its advances in sustainability, automation, affordability, deployability, scalability, and adaptive intelligence.