Classification Of Insects Research Articles

Exploring multiple optimization algorithms in transfer learning with EfficientNet models for agricultural insect classification

Dangerous insects are a significant risk to the global agricultural industry, threatening food security, economic stability, and crop quality. This study investigates the impact of multiple optimization algorithms within transfer learning, employing EfficientNet models for the classification of agricultural insects. The explored optimization algorithms include Adam, Adamax, AdamW, RMSprop, and SGD, while utilizing the EfficientNetB0, EfficientNetB3, EfficientNetB5, and EfficientNetB7 architectures. Experimental results show notable performance differences between optimization algorithms across all EfficiencyNet models in the study. Among the measured metrics are precision, recall, f1-score, accuracy, and loss, the AdamW optimizer consistently demonstrates superior performance compared to other algorithms. The findings underscore the critical influence of optimization algorithms in enhancing classification accuracy and convergence within transfer learning scenarios. Additionally, the study employs various visualization techniques, such as Gradient-weighted Class Activation Mapping (Grad-CAM) to enhance the interpretation of the image classification model’s results. By focusing on these methodologies, this research aims to improve the model’s performance, optimize its capabilities, and ultimately contribute to effective pest management strategies in agriculture, safeguarding crop yields, farmer livelihoods, and global food security.

Revisions, new taxa, and venation transformations of the sawfly family Blasticotomidae sensu lato (Hymenoptera: Tenthredinoidea) highlight the evolution of the basal Hymenoptera

Abstract Wing venation pattern is particularly important in the taxonomy and classification of insects, especially for fossil material. There are recognized transformation series that apparently often represent a mainstream in the evolutionary trend of the wing venation of Hymenoptera. One notable instance is the gradual reduction of the subcosta veins from multiple branches to their total absence. Herein, we place four new genera and six new species in the family Blasticotomidae (=Xyelotomidae) of Hymenoptera. They are Xyelocerus abruptus sp. nov., Liberitoma tenella gen et sp. nov., Liberitoma compta sp. nov., Liberitoma incompleta sp. nov., Aduantoma insolita gen. et sp. nov., and Apertoma gen. nov. from the Middle Jurassic of China, and Enspeletoma oligocaenica gen. et sp. nov. from the Upper Oligocene of Germany. The newly discovered species of Liberitoma from China possessed a supernumerary hind branch of vein Sc in its forewing, which has apparently never been recorded before in other hymenopterans, and the unique venation pattern of Aduantoma suggests the possibility of two additional steps of vein Sc transformation before its complete loss. Based on the new findings, Blasticotomidae are proposed to be divided into four subfamilies: Blasticotominae Thomson 1871, Dahurotominae subfam. nov., Pseudoxyelocerinae subfam. nov., and Undatominae subfam. nov.

Towards a standardized framework for AI-assisted, image-based monitoring of nocturnal insects.

Automated sensors have potential to standardize and expand the monitoring of insects across the globe. As one of the most scalable and fastest developing sensor technologies, we describe a framework for automated, image-based monitoring of nocturnal insects-from sensor development and field deployment to workflows for data processing and publishing. Sensors comprise a light to attract insects, a camera for collecting images and a computer for scheduling, data storage and processing. Metadata is important to describe sampling schedules that balance the capture of relevant ecological information against power and data storage limitations. Large data volumes of images from automated systems necessitate scalable and effective data processing. We describe computer vision approaches for the detection, tracking and classification of insects, including models built from existing aggregations of labelled insect images. Data from automated camera systems necessitate approaches that account for inherent biases. We advocate models that explicitly correct for bias in species occurrence or abundance estimates resulting from the imperfect detection of species or individuals present during sampling occasions. We propose ten priorities towards a step-change in automated monitoring of nocturnal insects, a vital task in the face of rapid biodiversity loss from global threats. This article is part of the theme issue 'Towards a toolkit for global insect biodiversity monitoring'.

BEETLES IDENTIFIED IN THE SCORNICESTI ORCHARD ECOSYSTEM, OLT COUNTY

The work is a general classification of insects, starting from the large systematic units, the orders and suborders, and further treating the main families and subfamilies. Following the experiments carried out in 2023, in the North-Eastern area of Olt County, Scornicești locality, the coleoptera species collected in the analyzed fruit-growing ecosystem were classified into 4 families: Scarabeidae, Carabidae, Staphilinidae, Coccinellidae.Thus, in 2023, out of a total of 1214 beetles, the Scarabidae family was present in a proportion of 21.17%, the Carabidae family represented 22.16%, the Staphilinidae family was 7.58%, and the Coccinelidae family represented 49, 09%.

Classification of insects' acoustic signals using a hybrid approach: Mel-frequency Hilbert-Huang transformation

Classification of insects' acoustic signals using a hybrid approach: Mel-frequency Hilbert-Huang transformation

Use of Machine Learning and Deep Learning along with NPK Sensor for Intelligent Farming Solutions

The increased human population increases the demand for food. Traditional farming leads to inefficiencies and difficulty in fertilizer usage, crop selection, and insect detection. This research project eliminates all these problems by developing an advanced farming web application to evaluate crop production efficiency. This research evaluates the soil nutrients needed by different plants and thereby generates a recommendation system to recommend the most suitable crop based on sensor values, thus reducing risk, nutritional imbalance and environmental pollution. It consists of an NPK sensor with a combination of machine learning models to monitor soil health and increase yields, reduce costs and match fertilizer supply with demand. It also helps to analyze various insects and provides descriptions of insects and recommends solutions to those insects in Nepali language helping farmers. The integration of ML and DL models such as random forest for fertilizer prediction, light GBM (Gradient Boosting Machine) for crop prediction and Conv2D for the classification of insects will help to maximize the production yield.

Relevance of molecular systematics in insect pest management

Relevance of molecular systematics in insect pest management

Improved Artificial Ecosystem Optimizer with Deep-Learning-Based Insect Detection and Classification for Agricultural Sector

The agricultural industry has the potential to meet the increasing food production requirements and supply nutritious and healthy food products. Since the Internet of Things (IoT) phenomenon has achieved considerable growth in recent years, IoT-based systems have been established for pest detection so as to mitigate the loss of crops and reduce serious damage by employing pesticides. In the event of pest attack, the detection of crop insects is a tedious process for farmers since a considerable proportion of crop yield is affected and the quality of pest detection is diminished. Based on morphological features, conventional insect detection is an option, although the process has a disadvantage, i.e., it necessitates highly trained taxonomists to accurately recognize the insects. In recent times, automated detection of insect categories has become a complex problem and has gained considerable interest since it is mainly carried out by agriculture specialists. Advanced technologies in deep learning (DL) and machine learning (ML) domains have effectively reached optimum performance in terms of pest detection and classification. Therefore, the current research article focuses on the design of the improved artificial-ecosystem-based optimizer with deep-learning-based insect detection and classification (IAEODL-IDC) technique in IoT-based agricultural sector. The purpose of the proposed IAEODL-IDC technique lies in the effectual identification and classification of different types of insects. In order to accomplish this objective, IoT-based sensors are used to capture the images from the agricultural environment. In addition to this, the proposed IAEODL-IDC method applies the median filtering (MF)-based noise removal process. The IAEODL-IDC technique uses the MobileNetv2 approach as well as for feature vector generation. The IAEO system is utilized for optimal hyperparameter tuning of the MobileNetv2 approach. Furthermore, the gated recurrent unit (GRU) methodology is exploited for effective recognition and classification of insects. An extensive range of simulations were conducted to exhibit the improved performance of the proposed IAEODL-IDC methodology. The simulation results validated the remarkable results of the IAEODL-IDC algorithm with recent systems.

Based on the multi-scale information sharing network of fine-grained attention for agricultural pest detection.

It is of great significance to identify the pest species accurately and control it effectively to reduce the loss of agricultural products. The research results of this project will provide theoretical basis for preventing and controlling the spread of pests and reducing the loss of agricultural products, and have important practical significance for improving the quality of agricultural products and increasing the output of agricultural products. At the same time, it provides a kind of effective prevention and control measures for farmers, so as to ensure the safety and health of crops. Because of the slow speed and high cost of manual identification, it is necessary to establish a set of automatic pest identification system. The traditional image-based insect classifier is mainly realized by machine vision technology, but because of its high complexity, the classification efficiency is low and it is difficult to meet the needs of applications. Therefore, it is necessary to develop a new automatic insect recognition system to improve the accuracy of insect classification. There are many species and forms of insects, and the field living environment is complex. The morphological similarity between species is high, which brings difficulties to the classification of insects. In recent years, with the rapid development of deep learning technology, using artificial neural network to classify pests is an important method to establish a fast and accurate classification model. In this work, we propose a novel convolutional neural network-based model (MSSN), which includes attention mechanism, feature pyramid, and fine-grained model. The model has good scalability, can better capture the semantic information in the image, and achieve more accurate classification. We evaluated our approach on a common data set: large-scale pest data set, PlantVillage benchmark data set, and evaluated model performance using a variety of evaluation indicators, namely, macro mean accuracy (MPre), macro mean recall rate (MRec), macro mean F1-score (MF1), Accuracy (Acc) and geometric mean (GM). Experimental results show that the proposed algorithm has better performance and universality ability than the existing algorithm. For example, on the data set, the maximum accuracy we obtained was 86.35%, which exceeded the corresponding technical level. The ablation experiment was conducted on the experiment itself, and the comprehensive evaluation of the complete MSSN(scale 1+2+3) was the best in various performance indexes, demonstrating the feasibility of the innovative method in this paper.

Hierarchical classification of insects with multitask learning and anomaly detection

Cameras and computer vision are revolutionising the study of insects, creating new research opportunities within agriculture, epidemiology, evolution, ecology and monitoring of biodiversity. However, the diversity of insects and close resemblances of many species are a major challenge for image-based species-level classification. Here, we present an algorithm to hierarchically classify insects from images, leveraging a simple taxonomy to (1) classify specimens across multiple taxonomic ranks simultaneously, and (2) identify the lowest rank at which a reliable classification can be reached. Specifically, we propose multitask learning, a loss function incorporating class dependency at each taxonomic rank, and anomaly detection based on outlier analysis to quantify the uncertainty. First, we compile a dataset of 41,731 images of insects, combining images from time-lapse monitoring of floral scenes with images from the Global Biodiversity Information Facility (GBIF). Second, we adapt state-of-the-art convolutional neural networks, ResNet and EfficientNet, for the hierarchical classification of insects belonging to three orders, five families and nine species. Third, we assess model generalization for 11 species unseen by the trained models. Here, anomaly detection is used to predict the higher rank of the species which were not present in the training set. We found that incorporating a simple taxonomy into our model increased the accuracy at higher taxonomic ranks. As expected, our algorithm correctly classified new insect species at higher taxonomic ranks, while classification was uncertain at lower taxonomic ranks. Anomaly detection can effectively flag novel taxa that are visually distinct from species in the training data. However, five novel taxa were consistently mistaken for visually similar species in the training data. Above all, we have demonstrated a practical approach to hierarchical classification based on species taxonomy and uncertainty during automated in situ monitoring of live insects. Our method is simple and versatile, forming a valuable step towards high-level classification of species not found in training data.

Detecting common coccinellids found in sorghum using deep learning models

Increased global production of sorghum has the potential to meet many of the demands of a growing human population. Developing automation technologies for field scouting is crucial for long-term and low-cost production. Since 2013, sugarcane aphid (SCA) Melanaphis sacchari (Zehntner) has become an important economic pest causing significant yield loss across the sorghum production region in the United States. Adequate management of SCA depends on costly field scouting to determine pest presence and economic threshold levels to spray insecticides. However, with the impact of insecticides on natural enemies, there is an urgent need to develop automated-detection technologies for their conservation. Natural enemies play a crucial role in the management of SCA populations. These insects, primary coccinellids, prey on SCA and help to reduce unnecessary insecticide applications. Although these insects help regulate SCA populations, the detection and classification of these insects is time-consuming and inefficient in lower value crops like sorghum during field scouting. Advanced deep learning software provides a means to perform laborious automatic agricultural tasks, including detection and classification of insects. However, deep learning models for coccinellids in sorghum have not been developed. Therefore, our objective was to develop and train machine learning models to detect coccinellids commonly found in sorghum and classify them according to their genera, species, and subfamily level. We trained a two-stage object detection model, specifically, Faster Region-based Convolutional Neural Network (Faster R-CNN) with the Feature Pyramid Network (FPN) and also one-stage detection models in the YOLO (You Only Look Once) family (YOLOv5 and YOLOv7) to detect and classify seven coccinellids commonly found in sorghum (i.e., Coccinella septempunctata, Coleomegilla maculata, Cycloneda sanguinea, Harmonia axyridis, Hippodamia convergens, Olla v-nigrum, Scymninae). We used images extracted from the iNaturalist project to perform training and evaluation of the Faster R-CNN-FPN and YOLOv5 and YOLOv7 models. iNaturalist is an imagery web server used to publish citizen’s observations of images pertaining to living organisms. Experimental evaluation using standard object detection metrics, such as average precision (AP), AP@0.50, etc., has shown that the YOLOv7 model performs the best on the coccinellid images with an AP@0.50 as high as 97.3, and AP as high as 74.6. Our research contributes automated deep learning software to the area of integrated pest management, making it easier to detect natural enemies in sorghum.

Nine Mitochondrial Genomes of Phasmatodea with Two Novel Mitochondrial Gene Rearrangements and Phylogeny.

The classification of stick and leaf insects (Order Phasmatodea) is flawed at various taxonomic ranks due to a lack of robust phylogenetic relationships and convergent morphological characteristics. In this study, we sequenced nine new mitogenomes that ranged from 15,011 bp to 17,761 bp in length. In the mitogenome of Carausis sp., we found a translocation of trnR and trnA, which can be explained by the tandem duplication/random loss (TDRL) model. In the Stheneboea repudiosa Brunner von Wattenwyl, 1907, a novel mitochondrial structure of 12S rRNA-CR1-trnI-CR2-trnQ-trnM was found for the first time in Phasmatodea. Due to the low homology of CR1 and CR2, we hypothesized that trnI was inverted through recombination and then translocated into the middle of the control region. Control region repeats were frequently detected in the newly sequenced mitogenomes. To explore phylogenetic relationships in Phasmatodea, mtPCGs from 56 Phasmatodean species (composed of 9 stick insects from this study, 31 GenBank data, and 16 data derived from transcriptome splicing) were used for Bayesian inference (BI), and maximum likelihood (ML) analyses. Both analyses supported the monophyly of Lonchodinae and Necrosciinae, but Lonchodidae was polyphyletic. Phasmatidae was monophyletic, and Clitumninae was paraphyletic. Phyllidae was located at the base of Neophasmatodea and formed a sister group with the remaining Neophasmatodea. Bacillidae and Pseudophasmatidae were recovered as a sister group. Heteroptergidae was monophyletic, and the Heteropteryginae sister to the clade (Obriminae + Dataminae) was supported by BI analysis and ML analysis.

Lightweight Field Insect Recognition and Classification Model Based on Improved Deep Learning under Complex Background

Insect monitoring in the field is an extremely important part of the agricultural production system. Recent advances in computer technology have provided the technical foundation for automatic field insect monitoring. In insect automatic monitoring, insect recognition and classification based on images is one of the most active research areas. Rapid advancements in computer vision technology based on deep learning have provided new ideas for implementing automatic field insect monitoring. Firstly, the field insect images are preprocessed and input to the lightweight algorithm for feature extraction, and the prediction networks of different sizes are output by multiscale feature fusion; then, the joint cross-merge ratio is introduced for automatic identification and classification of field insects. Compared with other algorithms, the simulation results show that the proposed algorithm has higher accuracy, less time consumption, and stronger robustness. It effectively solves the insect accumulation and background interference problems and can identify field insects online in real time.

Identification of medically and forensically relevant flies using a decision treelearning method.

Blow flies, flesh flies, and house flies can provide excellent evidence for forensic entomologists and are also essential to the fields of public health, medicine, and animal health. In all questions, the correct identification of fly species is an important initial step. The usual methods based on morphology or even molecular approaches can reach their limits here, especially when dealing with larger numbers of specimens. Since machine learning already plays a major role in many areas of daily life, such as education, business, industry, science, and medicine, applications for the classification of insects have been reported. Here, we applied the decision tree method with wing morphometric data to construct a model for discriminating flies of three families [Calliphoridae, Sarcophagidae, Muscidae] and seven species [Chrysomya megacephala (Fabricius), Chrysomya rufifacies (Macquart), Chrysomya (Ceylonomyia) nigripes Aubertin, Lucilia cuprina (Wiedemann), Hemipyrellia ligurriens (Wiedemann), Musca domestica Linneaus, and Parasarcophaga (Liosarcophaga) dux Thomson]. One hundred percent overall accuracy was obtained at a family level, followed by 83.33% at a species level. The results of this study suggest that non-experts might utilize this identification tool. However, more species and also samples per specimens should be studied to create a model that can be applied to the different fly species in Thailand.

Fine-grained image classification of microscopic insect pest species: Western Flower thrips and Plague thrips

Accurate identification of insect pests is essential in crop management as they are one of the primary causes of yield losses. However, differences between insect species demand different pest control strategies. Hence, research on new technology for fine-grained classification of insect pests is potentially important. Morphologically similar microscopic pest species classification has received little attention in the literature, and is targeted by this study as a means to address the need for agricultural pest management. We propose a novel computational method for deep learning-based, fine-grained classification of microscopic insects using the Vision Transform (ViT) architecture. This architecture employs an attention mechanism motivated by domain knowledge. The proposed approach consists of two main modules, a Data Preprocessing Module to segment relevant insect features and split the insect into body segments to inform identification, and a Domain Knowledge-Driven Stacked Model based on ViT to generate the prediction from each body segment and to fuse predictions for each segment into an accurate species-level classification. We tested the approach using an image dataset of two economically devastating thrip species – Western Flower thrips (Frankliniella occidentalis) and Plague thrips (Thrips imaginis). These insects are small (∼1mm), exhibit minute inter-species differences, and require different pest control strategies. We compared our model with the original ViT model, RestNet101, and RestNet50. Experimental results achieve an F1-score of 0.978, a 3.27% improvement over the baselines. This is important in the horticultural context given the yield losses that these pest insects are known to cause if their populations remain incorrectly quantified.

Jigsaw dissection activity enhances student ability to relate morphology and ecology in aquatic insects

ABSTRACT Functional feeding guild classification of aquatic insects is partly based on mouthpart morphology, but the link between mouthpart morphology and ecological feeding roles is often missed by students in the classroom. We implemented a Jigsaw activity in a freshwater biology course to help students connect morphology and ecology. Paired students dissected two common (to the whole class) and one unique aquatic insect’s mouthparts and predicted their ecological feeding roles. Students then divided into new groups and taught peers about their unique insect. A pre- and post-activity survey measured students’ ability to relate morphology and feeding roles. Open-ended questions graded via a rubric showed students scored significantly higher and provided more answers discussing feeding roles. Likert-type questions probing students’ perceptions of mouthpart importance resulted in marginally higher importance ratings of mouthparts for identification but no differences for insect feeding. On an end-of-the-semester assessment, students generally rated the activity as helpful. Some reported the activity to be difficult due to small insect size. The activity enhanced students’ understanding of the link between mouthparts and feeding roles but may have decreased their engagement due to perceived difficulty. Further modification alleviating difficulty may improve student perceptions while retaining knowledge gains.

Classification and detection of insects from field images using deep learning for smart pest management: A systematic review

Insect pest is one of the main causes affecting agricultural crop yield and quality all over the world. Rapid and reliable insect pest monitoring plays a crucial role in population prediction and control actions. The great breakthrough of deep learning (DL) technology has resulted in its successful applications in various fields, including automatic insect pest monitoring. DL creates both new strengths and a series of challenges for data processing in smart pest monitoring (SPM). This review outlines the technical methods of DL frameworks and their applications in SPM with emphasis on insect pest classification and detection using field images. The methodologies and technical details evolved in insect pest classification and detection using DL are summarized and distilled during different processing stages: image acquisition, data preprocessing and modeling techniques. Finally, a general framework is provided to facilitate the smart insect monitoring and future challenges and trends are highlighted. In a word, our purpose is to provide researchers and technicians with a better understanding of DL techniques and their state-of-art achievements in SPM, which can promote the implement of various SPM applications.

Technological Advances to Address Current Issues in Entomology: 2020 Student Debates

The 2020 Student Debates of the Entomological Society of America (ESA) were live-streamed during the Virtual Annual Meeting to debate current, prominent entomological issues of interest to members. The Student Debates Subcommittee of the National ESA Student Affairs Committee coordinated the student efforts throughout the year and hosted the live event. This year, four unbiased introductory speakers provided background for each debate topic while four multi-university teams were each assigned a debate topic under the theme ‘Technological Advances to Address Current Issues in Entomology’. The two debate topics selected were as follows: 1) What is the best taxonomic approach to identify and classify insects? and 2) What is the best current technology to address the locust swarms worldwide? Unbiased introduction speakers and debate teams began preparing approximately six months before the live event. During the live event, teams shared their critical thinking and practiced communication skills by defending their positions on either taxonomical identification and classification of insects or managing the damaging outbreaks of locusts in crops.

Visualization and categorization of ecological acoustic events based on discriminant features

Although sound classification in soundscape studies are generally performed by experts, the large growth of acoustic data presents a major challenge for performing such task. At the same time, the identification of more discriminating features becomes crucial when analyzing soundscapes, and this occurs because natural and anthropogenic sounds are very complex, particularly in Neotropical regions, where the biodiversity level is very high. In this scenario, the need for research addressing the discriminatory capability of acoustic features is of utmost importance to work towards automating these processes. In this study we present a method to identify the most discriminant features for categorizing sound events in soundscapes. Such identification is key to classification of sound events. Our experimental findings validate our method, showing high discriminatory capability of certain extracted features from sound data, reaching an accuracy of 89.91% for classification of frogs, birds and insects simultaneously. An extension of these experiments to simulate binary classification reached accuracy of 82.64%,100.0% and 99.40% for the classification between combinations of frogs-birds, frogs-insects and birds-insects, respectively.

Machine learning ensemble with image processing for pest identification and classification in field crops

In agriculture field, yield loss is a major problem due to attack of various insects in field crops. Traditional insect identification and classification methods are time-consuming and require entomologist experts. Early information about the attack of insects helps farmers to control the crop damage to improve the productivity and reduce the use of pesticides. This research work focuses on the classification of crop insects by applying machine vision and knowledge-based techniques with image processing by using different feature descriptors including texture, color, shape, histogram of oriented gradients (HOG) and global image descriptor (GIST). A combination of all these features was used in the classification of insects. In this research, several machine learning algorithms including both base classifiers and ensemble classifiers were applied for three different insect datasets and the performances of classification results were evaluated by majority voting. Naive bayes (NB), support vector machine (SVM), K-nearest-neighbor (KNN) and multi-layer perceptron (MLP) were used as base classifiers. Ensemble classifiers include random forest (RF), bagging and XGBoost were utilized; 10-fold cross-validation test was conducted to achieve a better classification and identification of insects. The experimental results showed that the classification accuracy is improved by majority voting with ensemble classifiers in the combination of texture, color, shape, HOG and GIST features.