Using Mobile Edge AI to Detect and Map Diseases in Citrus Orchards.

Deep Learning models have presented promising results when applied to Agriculture 4.0. Among other applications, these models can be used in disease detection and fruit counting. Deep Learning models usually have many layers in the architecture and millions of parameters. This aspect hinders the use of Deep Learning on mobile devices as they require a large amount of processing power for inference. In addition, the lack of high-quality Internet connectivity in the field impedes the usage of cloud computing, pushing the processing towards edge devices. This work describes the proposal of an edge AI application to detect and map diseases in citrus orchards. The proposed system has low computational demand, enabling the use of low-footprint models for both detection and classification tasks. We initially compared AI algorithms to detect fruits on trees. Specifically, we analyzed and compared YOLO and Faster R-CNN. Then, we studied lean AI models to perform the classification task. In this context, we tested and compared the performance of MobileNetV2, EfficientNetV2-B0, and NASNet-Mobile. In the detection task, YOLO and Faster R-CNN had similar AI performance metrics, but YOLO was significantly faster. In the image classification task, MobileNetMobileV2 and EfficientNetV2-B0 obtained an accuracy of 100%, while NASNet-Mobile had a 98% performance. As for the timing performance, MobileNetV2 and EfficientNetV2-B0 were the best candidates, while NASNet-Mobile was significantly worse. Furthermore, MobileNetV2 had a 10% better performance than EfficientNetV2-B0. Finally, we provide a method to evaluate the results from these algorithms towards describing the disease spread using statistical parametric models and a genetic algorithm to perform the parameters' regression. With these results, we validated the proposed pipeline, enabling the usage of adequate AI models to develop a mobile edge AI solution.

Wearable Edge AI Applications for Ecological Environments.

Ecological environments research helps to assess the impacts on forests and managing forests. The usage of novel software and hardware technologies enforces the solution of tasks related to this problem. In addition, the lack of connectivity for large data throughput raises the demand for edge-computing-based solutions towards this goal. Therefore, in this work, we evaluate the opportunity of using a Wearable edge AI concept in a forest environment. For this matter, we propose a new approach to the hardware/software co-design process. We also address the possibility of creating wearable edge AI, where the wireless personal and body area networks are platforms for building applications using edge AI. Finally, we evaluate a case study to test the possibility of performing an edge AI task in a wearable-based environment. Thus, in this work, we evaluate the system to achieve the desired task, the hardware resource and performance, and the network latency associated with each part of the process. Through this work, we validated both the design pattern review and case study. In the case study, the developed algorithms could classify diseased leaves with a circa 90% accuracy with the proposed technique in the field. This results can be reviewed in the laboratory with more modern models that reached up to 96% global accuracy. The system could also perform the desired tasks with a quality factor of 0.95, considering the usage of three devices. Finally, it detected a disease epicenter with an offset of circa 0.5 m in a 6 m × 6 m × 12 m space. These results enforce the usage of the proposed methods in the targeted environment and the proposed changes in the co-design pattern.

A UAV-Based Framework for Semi-Automated Thermographic Inspection of Belt Conveyors in the Mining Industry.

Frequent and accurate inspections of industrial components and equipment are essential because failures can cause unscheduled downtimes, massive material, and financial losses or even endanger workers. In the mining industry, belt idlers or rollers are examples of such critical components. Although there are many precise laboratory techniques to assess the condition of a roller, companies still have trouble implementing a reliable and scalable procedure to inspect their field assets. This article enumerates and discusses the existing roller inspection techniques and presents a novel approach based on an Unmanned Aerial Vehicle (UAV) integrated with a thermal imaging camera. Our preliminary results indicate that using a signal processing technique, we are able to identify roller failures automatically. We also proposed and implemented a back-end platform that enables field and cloud connectivity with enterprise systems. Finally, we have also cataloged the anomalies detected during the extensive field tests in order to build a structured dataset that will allow for future experimentation.

Field Research Cooperative Wearable Systems: Challenges in Requirements, Design and Validation.

The widespread availability of wearable devices is evolving them into cooperative systems. Communication and distribution aspects such as the Internet of Things, Wireless Body Area Networks, and Local Wireless Networks provide the means to develop multi-device platforms. Nevertheless, the field research environment presents a specific feature set, which increases the difficulty in the adoption of this technology. In this text, we review the main aspects of Field Research Gears and Wearable Devices. This review is made aiming to understand how to create cooperative systems based on wearable devices directed to the Field Research Context. For a better understanding, we developed a case study in which we propose a cooperative system architecture and provide validation aspects. For this matter, we provide an overview of a previous device architecture and study an integration proposal.

Vehicle Driver Monitoring through the Statistical Process Control.

This paper proposes the use of the Statistical Process Control (SPC), more specifically, the Exponentially Weighted Moving Average method, for the monitoring of drivers using approaches based on the vehicle and the driver's behavior. Based on the SPC, we propose a method for the lane departure detection; a method for detecting sudden driver movements; and a method combined with computer vision to detect driver fatigue. All methods consider information from sensors scattered by the vehicle. The results showed the efficiency of the methods in the identification and detection of unwanted driver actions, such as sudden movements, lane departure, and driver fatigue. Lane departure detection obtained results of up to 76.92% (without constant speed) and 84.16% (speed maintained at ≈60). Furthermore, sudden movements detection obtained results of up to 91.66% (steering wheel) and 94.44% (brake). The driver fatigue has been detected in up to 94.46% situations.