Machine Learning-Based Classification of Mango Pulp Weevil Activity Utilizing an Acoustic Sensor

The mango pulp weevil (MPW) is an aggressive pest that mates seasonally according to the cycle of the mango fruit. After discovering the existence of the mango pulp weevil in Palawan, the island has been under quarantine for exporting mangoes. Detection of the pest proves difficult as the pest does not leave a physical sign that the mango has been damaged. Infested mangoes are wasted as they cannot be sold due to damage. This study serves as a base study for non-invasive mango pulp weevil detection using MATLAB machine learning and audio feature extraction tools. Acoustic sensors were evaluated for best-fit use in the study. The rationale for selecting the acoustic sensors includes local availability and accessibility. Among the three sensors tested, the MEMS sensor had the best result. The data for acoustic frequency are acquired using the selected sensor, which is placed inside a soundproof chamber to minimize the noise and isolate the sound produced by each activity. The identified activity of the adult mango pulp weevil includes walking, resting, and mating. The Mel-frequency cepstral coefficient (MFCC) was used for feature extraction of the recorded audio and training of the SVM classifier. The study achieved 89.81% overall accuracy in characterizing mango pulp weevil activity.

Boosting precision crop protection towards agriculture 5.0 via machine learning and emerging technologies: A contextual review

Crop protection is a key activity for the sustainability and feasibility of agriculture in a current context of climate change, which is causing the destabilization of agricultural practices and an increase in the incidence of current or invasive pests, and a growing world population that requires guaranteeing the food supply chain and ensuring food security. In view of these events, this article provides a contextual review in six sections on the role of artificial intelligence (AI), machine learning (ML) and other emerging technologies to solve current and future challenges of crop protection. Over time, crop protection has progressed from a primitive agriculture 1.0 (Ag1.0) through various technological developments to reach a level of maturity closelyin line with Ag5.0 (section 1), which is characterized by successfully leveraging ML capacity and modern agricultural devices and machines that perceive, analyze and actuate following the main stages of precision crop protection (section 2). Section 3 presents a taxonomy of ML algorithms that support the development and implementation of precision crop protection, while section 4 analyses the scientific impact of ML on the basis of an extensive bibliometric study of >120 algorithms, outlining the most widely used ML and deep learning (DL) techniques currently applied in relevant case studies on the detection and control of crop diseases, weeds and plagues. Section 5 describes 39 emerging technologies in the fields of smart sensors and other advanced hardware devices, telecommunications, proximal and remote sensing, and AI-based robotics that will foreseeably lead the next generation of perception-based, decision-making and actuation systems for digitized, smart and real-time crop protection in a realistic Ag5.0. Finally, section 6 highlights the main conclusions and final remarks.

A Novel Method for the Classification of Butterfly Species Using Pre-Trained CNN Models

In comparison to the competitors, engineers must provide quick, low-cost, and dependable solutions. The advancement of intelligence generated by machines and its application in almost every field has created a need to reduce the human role in image processing while also making time and labor profit. Lepidopterology is the discipline of entomology dedicated to the scientific analysis of caterpillars and the three butterfly superfamilies. Students studying lepidopterology must generally capture butterflies with nets and dissect them to discover the insect’s family types and shape. This research work aims to assist science students in correctly recognizing butterflies without harming the insects during their analysis. This paper discusses transfer-learning-based neural network models to identify butterfly species. The datasets are collected from the Kaggle website, which contains 10,035 images of 75 different species of butterflies. From the available dataset, 15 unusual species were selected, including various butterfly orientations, photography angles, butterfly lengths, occlusion, and backdrop complexity. When we analyzed the dataset, we found an imbalanced class distribution among the 15 identified classes, leading to overfitting. The proposed system performs data augmentation to prevent data scarcity and reduce overfitting. The augmented dataset is also used to improve the accuracy of the data models. This research work utilizes transfer learning based on various convolutional neural network architectures such as VGG16, VGG19, MobileNet, Xception, ResNet50, and InceptionV3 to classify the butterfly species into various categories. All the proposed models are evaluated using precision, recall, F-Measure, and accuracy. The investigation findings reveal that the InceptionV3 architecture provides an accuracy of 94.66%, superior to all other architectures.

Automatic Crop Pest Detection Oriented Multiscale Feature Fusion Approach

Specialized pest control for agriculture is a high-priority agricultural issue. There are multiple categories of tiny pests, which pose significant challenges to monitoring. Previous work mainly relied on manual monitoring of pests, which was labor-intensive and time-consuming. Recently, deep-learning-based pest detection methods have achieved remarkable improvements and can be used for automatic pest monitoring. However, there are two main obstacles in the task of pest detection. (1) Small pests often go undetected because much information is lost during the network training process. (2) The highly similar physical appearances of some categories of pests make it difficult to distinguish the specific categories for networks. To alleviate the above problems, we proposed the multi-category pest detection network (MCPD-net), which includes a multiscale feature pyramid network (MFPN) and a novel adaptive feature region proposal network (AFRPN). MFPN can fuse the pest information in multiscale features, which significantly improves detection accuracy. AFRPN solves the problem of anchor and feature misalignment during RPN iterating, especially for small pest objects. In extensive experiments on the multi-category pests dataset 2021 (MPD2021), the proposed method achieved 67.3% mean average precision (mAP) and 89.3% average recall (AR), outperforming other deep learning-based models.

Classification of Fruit Flies by Gender in Images Using Smartphones and the YOLOv4-Tiny Neural Network

The fruit fly Drosophila melanogaster is a classic research object in genetics and systems biology. In the genetic analysis of flies, a routine task is to determine the offspring size and gender ratio in their populations. Currently, these estimates are made manually, which is a very time-consuming process. The counting and gender determination of flies can be automated by using image analysis with deep learning neural networks on mobile devices. We proposed an algorithm based on the YOLOv4-tiny network to identify Drosophila flies and determine their gender based on the protocol of taking pictures of insects on a white sheet of paper with a cell phone camera. Three strategies with different types of augmentation were used to train the network. The best performance (F1 = 0.838) was achieved using synthetic images with mosaic generation. Females gender determination is worse than that one of males. Among the factors that most strongly influencing the accuracy of fly gender recognition, the fly’s position on the paper was the most important. Increased light intensity and higher quality of the device cameras have a positive effect on the recognition accuracy. We implement our method in the FlyCounter Android app for mobile devices, which performs all the image processing steps using the device processors only. The time that the YOLOv4-tiny algorithm takes to process one image is less than 4 s.

Development of an Optical System Based on Spectral Imaging Used for a Slug Control Robot

The state-of-the-art technique to control slug pests in agriculture is the spreading of slug pellets. This method has some downsides, because slug pellets also harm beneficials and often fail because their efficiency depends on the prevailing weather conditions. This study is part of a research project which is developing a pest control robot to monitor the field, detect slugs, and eliminate them. Robots represent a promising alternative to slug pellets. They work independent of weather conditions and can distinguish between pests and beneficials. As a prerequisite, a robot must be able to reliably identify slugs irrespective of the characteristics of the surrounding conditions. In this context, the utilization of computer vision and image analysis methods are challenging, because slugs look very similar to the soil, particularly in color images. Therefore, the goal of this study was to develop an optical filter-based system that distinguishes between slugs and soil. In this context, the spectral characteristics of both slugs and soil in the visible and visible near-infrared (VNIR) wavebands were measured. Conspicuous maxima followed by conspicuous local minima were found for the reflection spectra of slugs in the near infrared range from 850 nm to 990 nm]. Thus, this enabled differentiation between slugs and soils; soils showed a monotonic increase in the intensity of the relative reflection for this wavelength. The extrema determined in the reflection spectra of slugs were used to develop and set up a slug detector device consisting of a monochromatic camera, a filter changer and two narrow bandpass filters with nominal wavelengths of 925 nm and 975 nm. The developed optical system takes two photographs of the target area at night. By subtracting the pixel values of the images, the slugs are highlighted, and the soil is removed in the image due to the properties of the reflection spectra of soils and slugs. In the resulting image, the pixels of slugs were, on average, 12.4 times brighter than pixels of soil. This enabled the detection of slugs by a threshold method.

Early Detection of Aphid Infestation and Insect-Plant Interaction Assessment in Wheat Using a Low-Cost Electronic Nose (E-Nose), Near-Infrared Spectroscopy and Machine Learning Modeling

Advances in early insect detection have been reported using digital technologies through camera systems, sensor networks, and remote sensing coupled with machine learning (ML) modeling. However, up to date, there is no cost-effective system to monitor insect presence accurately and insect-plant interactions. This paper presents results on the implementation of near-infrared spectroscopy (NIR) and a low-cost electronic nose (e-nose) coupled with machine learning. Several artificial neural network (ANN) models were developed based on classification to detect the level of infestation and regression to predict insect numbers for both e-nose and NIR inputs, and plant physiological response based on e-nose to predict photosynthesis rate (A), transpiration (E) and stomatal conductance (gs). Results showed high accuracy for classification models ranging within 96.5-99.3% for NIR and between 94.2-99.2% using e-nose data as inputs. For regression models, high correlation coefficients were obtained for physiological parameters (gs, E and A) using e-nose data from all samples as inputs (R = 0.86) and R = 0.94 considering only control plants (no insect presence). Finally, R = 0.97 for NIR and R = 0.99 for e-nose data as inputs were obtained to predict number of insects. Performances for all models developed showed no signs of overfitting. In this paper, a field-based system using unmanned aerial vehicles with the e-nose as payload was proposed and described for deployment of ML models to aid growers in pest management practices.

Prediction of Pest Insect Appearance Using Sensors and Machine Learning

The appearance of pest insects can lead to a loss in yield if farmers do not respond in a timely manner to suppress their spread. Occurrences and numbers of insects can be monitored through insect traps, which include their permanent touring and checking of their condition. Another more efficient way is to set up sensor devices with a camera at the traps that will photograph the traps and forward the images to the Internet, where the pest insect’s appearance will be predicted by image analysis. Weather conditions, temperature and relative humidity are the parameters that affect the appearance of some pests, such as Helicoverpa armigera. This paper presents a model of machine learning that can predict the appearance of insects during a season on a daily basis, taking into account the air temperature and relative humidity. Several machine learning algorithms for classification were applied and their accuracy for the prediction of insect occurrence was presented (up to 76.5%). Since the data used for testing were given in chronological order according to the days when the measurement was performed, the existing model was expanded to take into account the periods of three and five days. The extended method showed better accuracy of prediction and a lower percentage of false detections. In the case of a period of five days, the accuracy of the affected detections was 86.3%, while the percentage of false detections was 11%. The proposed model of machine learning can help farmers to detect the occurrence of pests and save the time and resources needed to check the fields.