Remote fruit fly detection using computer vision and machine learning-based electronic trap

Introduction

Intelligent monitoring systems must be put in place to practice precision agriculture. In this context, computer vision and artificial intelligence techniques can be applied to monitor and prevent pests, such as that of the olive fly. These techniques are a tool to discover patterns and abnormalities in the data, which helps the early detection of pests and the prompt administration of corrective measures. However, there are significant challenges due to the lack of data to apply state of the art Deep Learning techniques.

Methods

This article examines the detection and classification of the olive fly using the Random Forest and Support Vector Machine algorithms, as well as their application in an electronic trap version based on a Raspberry Pi B+ board.

Results

The combination of the two methods is suggested to increase the accuracy of the classification results while working with a small training data set. Combining both techniques for olive fly detection yields an accuracy of 89.1%, which increases to 94.5% for SVM and 91.9% for RF when comparing all fly species to other insects.

Discussion

This research results reports a successful implementation of ML in an electronic trap system for olive fly detection, providing valuable insights and benefits. The opportunities of using small IoT devices for image classification opens new possibilities, emphasizing the significance of ML in optimizing resource usage and enhancing privacy protection. As the system grows by increasing the number of electronic traps, more data will be available. Therefore, it holds the potential to further enhance accuracy by learning from multiple trap systems, making it a promising tool for effective and sustainable fly population management.

Ambient Hot Box: An Instrument for Thermal Characterization of Building Elements and Constructive Materials

In assessing the energy performance of buildings, the thermal performance of the structural components and building materials is crucial. Although reference catalogs are used to determine the thermal properties of construction materials, the use of novel materials or non-homogeneous mixtures, particularly with biomaterials, demands the development of new instruments that are capable of performing rapid, accurate and cost-effective thermal characterization. This study introduces the ambient hot-box, a new tool for measuring the thermal properties of construction components and heterogeneous materials. The paper provides a methodology for measuring a sample's benchmark and fresh materials using a streamlined hot-box-based instrument. Utilizing samples as a benchmark material, the new instrument is assessed, yielding transmittance values with errors below 4%. The electronic circuits, measurements techniques and instrument implementation are all described.

Thermolabile drug storage in an ambulatory setting

More thermolabile drugs are becoming available, and in most cases, these medications are dispensed to ambulatory patients. However, there is no regulation once medications are dispensed to patients and little is known with regard to what happens during transport and home storage. Previous studies suggest that these drugs are improperly stored. The present study was designed to determine the storage conditions of thermolabile drugs once they are dispensed to the patient in the Hospital Pharmacy Department. This is a prospective observational study to assess the temperature profile of 7 thermolabile drugs once they are dispensed to ambulatory patients at a tertiary care hospital. A data logger was added to the medication packaging. Temperature was considered inappropriate if one of the following circumstances were met: any temperature record less than or equal to 0 °C or over 25 °C; temperatures between 0-2 or 8-25 °C for a continuous period over 30 min. The time series of temperature measurements obtained from each data logger were analyzed as statistically independent variables. The data shown did not undergo any statistical treatment and must be considered directly related to thermal measurements. One hundred and fourteen patients were included and 107 patients were available for the analysis. On the whole, a mean of 50.6 days (SD 18.3) were measured and the mean temperature was 6.88 °C (SD 2.93). Three data loggers (2.8%) maintained all the measurements between 2 and 8 °C with less than 3 continuous data (< 30 min) out of this range but no data over 25 °C or below or equal to 0 °C. 28 (26.2%) data loggers had at least one measurement below zero, 1 data logger had a measurement greater than 25 °C and 75 (70.1%) were between 0 and 2 °C and/or between 8 and 25 °C for more than 30 min. In conclusion, once dispensed to patients, most thermolabile drugs are improperly stored. Future studies should focus on clinical consequences and possible solutions.