A Systematic Review of Species Classification Using Deep Learning Algorithms and Gender Identification of Tribolium castaneum Using Convolutional Neural Networks

© 2025 Academia Sinica, Taiwan Open Access A Systematic Review of Species Classification Using Deep Learning Algorithms and Gender Identification of Tribolium castaneum Using Convolutional Neural Networks Anurupa Mistry1, Chetas Hedaoo2, Archana Sharbidre3,* , Jayashri Bagade4,* , and Sangeeta V. Pandit5 1Department of Zoology, Savitribai Phule Pune University, Pune, Maharashtra, India. E-mail: [email protected] (Mistry) 2Department of Electronics and telecommunication, Vishwakarma Institute of Information Technology, Pune, Maharashtra, India. E-mail: chetas.22111[email protected] (Hedaoo) 3Department of Zoology, Savitribai Phule Pune University, Pune, Maharashtra, India. *Correspondence: E-mail: [email protected] (Sharbidre) 4Department of Information Technology, Vishwakarma Institute of Technology, Pune, Maharashtra, India. *Correspondence: E-mail: [email protected] (Bagade) 5Department of Zoology, Savitribai Phule Pune University, Pune, Maharashtra, India. E-mail: [email protected] (Pandit) Received 1 September 2023 / Accepted 16 April 2025 / Published 30 July 2025 Communicated by Sheng-Feng Shen Machine learning (ML) constitutes a division of artificial intelligence (AI) that aims to train computers how to perform specific tasks without explicit programming. Traditional ML tools are widely used for classification and identification of animals. However, these methods have some drawbacks because of the extensive manual reliance and the delay in data interpretation. To overcome this, Applied Deep Learning algorithms are used with Artificial Neural Networks (ANN) and Convolution Neural Network (CNN) models introduced to address species classification, characteristics detection, and pattern recognition tasks helping in accurate identification and classification of animals. In this paper, we have tried to compile and deliver a recent comprehensive information on latest available investigations in the field of life sciences particularly used for animal identification. We have also accentuated the diverse applications of machine learning models including other parameters like, features, accuracy gained, database used and their limitations. The red flour beetle, Tribolium castaneum (Coleoptera; Tenebrionidae) is a prevailing and detrimental secondary insect pest of stored grains along with derived products causing 7% to 35% annual loss. Despite of that, nowdays it is also extensively considered as a model organism for genetic disease investigation. While using it in scientific research, exact sex identification of these insects becomes a crucial preliminary step. Generally, pupal stage is used to sort these insects according to their sex and needs expert humans. It is crucial to employ image processing and ML algorithms to quickly identify gender of this insect which is not done yet. We have used a CNN-based smart technique to recognize and categorize gender differences in T. castaneum using microscopic images in order to build an intelligent system for applied research. For this study, a dataset is created by taking 116 microscopic images of both the dorsal and ventral sides of pupae of two different sexes. In this algorithm, a 2D matrix of feature map is selected sequentially and the maximum value in the matrix is selected to generate a pooled feature map. The Rectified Linear Unit (ReLU) activation function is used for the CNN. The classification model has an accuracy between 97 and 98% with an F-score of 0.67. These results demonstrate the robustness of the classification model, which does not rely heavily on manual intervention compared to traditional Citation: Mistry A, Hedaoo C, Sharbidre A, Bagade J, Pandit SV. 2025. A systematic review of species classification using deep learning algorithms and gender identification of Tribolium castaneum using convolutional neural networks. Zool Stud 64:24. doi:10.6620/ZS.2025.64-24. Zoological Studies 64:24 (2025) doi:10.6620/ZS.2025.64-24 1 © 2025 Academia Sinica, Taiwan BACKGROUND Tribolium castaneum, (Herbst 1797) commonly known as the red flour beetle and belonging to the Coleoptera order within the Tenebrionidae family, is a prevalent and destructive secondary insect pest that primarily targets stored grains and their derived products. This species exhibits sexual dimorphism (Sokoloff 1974; Rees 2004; Mahroof and Hagstrum 2012). Under optimal conditions, the developmental time for T. castaneum is approximately five days for eggs, twenty days for larvae, and seven days for pupae (Sokoloff 1974; Dawson 1964). Both larvae and adult beetles infest stored food and grains, posing a significant threat to agricultural commodities. Hana (2013) reported that the damage inflicted by these beetles accounts for a considerable percentage, ranging from 7% to 35%, of total agricultural production on an annual basis. Nowdays, T. castaneum have gained recognition as a valuable model organism for investigating the underlying causes of genetic diseases. Notably, T. castaneum was the first species within the Coleoptera order to have its genome sequenced (Richards et al. 2008; Herndon et al. 2020). This type of insect species is progressively employed across a diverse array of biomedical investigations, covering fields like neurodegenerative ailments (such as Parkinson’s disease), the signaling pathway for diuretics (which involves the function of vasopressin-like peptide and its receptor), interactions between hosts and pathogens (encompassing antagonistic interactions and coevolution), as well as the domains of pharmacology and toxicology (specifically in the analysis of the impacts of psychoactive substances) (Denell 2008; Grunwald et al. 2013; Bingsohn et al. 2016; Adamski et al. 2019). Although there exist certain dissimilarities in cellular characteristics and overall structure between humans and the red flour beetles, a multitude of genetic, physiological, and immunological traits remain consistent. This conservation renders them a valuable model for investigating diverse facets of human biology. T. castaneum’s utilization as a model for practical research extends beyond postharvest management, encompassing inquiries into aging, the environment, and pest control (Thomson et al. 2014; Wijayaratne et al. 2018). Several studies have been conducted on the evolutionary and the preperi and post-mating sexual selection behavior of T. castaneum (Michalczyk et al. 2010). The red flour beetle, known for its reddish-brown coloration and three-segmented clubbed antennae (Bousquet 1990), exhibits distinct sexual dimorphism. In T. castaneum, differentiation between males and females can be established by the presence of genital papillae during the pupal stage and sex patches in the bodies of adult insects. This differentiation is applicable to both pupal and adult stages. Notably, sex determination is most straightforward during the pupal stage (Kramarz et al. 2016). The morphological characteristics of the insect, influenced by both genotype and phenotype, indirectly impact the process of gender classification. Female pupae display pointed genital papillae, whereas male pupae possess stubby and barely noticeable papillae. Accurate identification of the sex of individuals is a crucial initial step in characterizing the population. As the sizes of the beetles are very small (3–4 mm), it is difficult to be perceived with human eyes. However there is need identify it using microscopic images. Perseverance of large number of microscopic images create fatigue to human subjects which will endup in to incorrect outcome. This repeated task will be very well handled by machine. Thus machine learning plays a very vital role in classification of beetles. There is an urgent need to integrate some fast processing techniques to speed up the experiments going on them. Machine learning has emerged as a viable alternative to traditional technical methodologies in various domains of science and technology. By leveraging data-driven approaches, machine learning techniques offer the potential to expedite the design process, minimize complexity, and enhance costeffectiveness (Simeone 2018). Machine learning is a subset of artificial intelligence dedicated to instructing computers in the execution of particular tasks, all without necessitating direct, explicit programming. Computers are fed structured data and ‘learn’ to become better at evaluating and acting on that data over time. A computational framework inspired by the structure of biological neural networks, which forms the foundation of the human brain, is commonly denoted as an artificial neural machine learning (ML) tools and automates the processes of feature extraction and gender classification regardless of the position of the pupae in the images. Key words: Species classification, Deep learning, CNN, Tribolium, Castaneum, Gender identification page 2 of 15 Zoological Studies 64:24 (2025) © 2025 Academia Sinica, Taiwan network. These networks are capable of effectively processing vast quantities of data. Artificial neural networks (ANNs) have been shown to be effective tools for various kinds of tasks, but they also have a number of disadvantages. As ANNs to generalize effectively, a lot of labelled training data is often needed. Overfitting or low accuracy might result from a lack of data or data with poor quality. Neural networks frequently perform the function of “black boxes,” which means they can make accurate predictions but cannot be interpreted. The “curse of dimensionality” refers to the exponential increase in data required to generalize the machine learning model accurately as the number of dimensions or characteristics rises. Additionally, ANN requires features that are handmade for model training and testing. Very few characteristics enables male and female T. castaneum pupae to be distinguished from one another. Because the pupae body is white in colour and has less texture, it is difficult for conventional machine learning approaches to correctly recognize it. Female and male pupae 117 could be distinguished by the size and shape of genital papillae, located anterior to the 118 urogomphi. Females have larger and finger like papillae whereas males has smaller papillae. To overcome this problems we need deep learning network to classify the beetles. Convolution Neural Network (CNN) model is used to classify beetls automatically. A Convolutional Neural Network (CNN) can comprise tens or even hundreds of layers, with each layer designed to learn and recognize different features within an image. During training, every image undergoes filtering at multiple resolutions, and the outcome of each convolution is employed as input for the subsequent layer. Starting with fundamental attributes such as brightness and edges, these filters can progress towards more intricate aspects, ultimately culminating in features that distinctly identify the object. Deep learning algorithms, notably convolutional neural networks (CNN), have garnered substantial attention due to their capabilities in pattern recognition tasks related to image analysis. Their popularity is notably prominent in the field of biological sciences. In our proposed study, we aim to devise an intelligent approach utilizing deep learning techniques to discern and categorize disparities observed in both species and gender based on microscopic images captured from ventral and dorsal views. This endeavor seeks to contribute to the advancement of intelligent systems within the realm of applied research. Literature survey The table 1 (presented below at the end of manuscript) provides a comprehensive overview of recent investigations in the field of life sciences, highlighting the diverse applications of machine learning models. Predominantly, supervised learning models have been employed to address species classification, characteristics detection, and pattern recognition tasks. An array of machine learning algorithms, including support vector machines (SVM), logistic regression (LG), random forests (RF), gradient boosting (GB), k-nearest neighbors (kNN), decision trees (DT), and deep learning (DL), have been employed to achieve these goals. The utilized datasets encompass both publicly available resources and researchergenerated collections through sample acquisition. The fundamental strategy in constructing classification models entails dividing the dataset into a training set for model development and a test set for the purpose of validating and evaluating the model’s dependability. Table 1. Summery of features, accuracy, model and limitations S. No. Ref. No. Features Model Used Accuracy Database Limitations 1 Themozhi et al. 2019 Automatic feature extraction for image classification Deep CNN model for classification 95.97–97.47% National Bureau of Agricultural Insect Resources (NBAIR) dataset, Xie1 and Xie2 Lower accuracy for higher mini batch size 2 Lee et al. 2021 machine learning model developed to diagnose malaria by leveraging patientrelated information support vector machine, random forest (RF), multi-layered perceptron, AdaBoost, gradient boosting (GB), and CatBoost 56.9–85.6% Dataset containing information on parasitic diseases as well as a broader dataset encompassing various other diseases gathered from patient information found within PubMed abstracts spanning the years from 1956 to 2019 Datasets utilized have small sizes, and they incorporate a constrained set of features without undergoing the feature selection process page 3 of 15Zoological Studies 64:24 (2025) © 2025 Academia Sinica, Taiwan S. No. Ref. No. Features Model Used Accuracy Database Limitations 3 Safavi et al. 2022 ExtraTreesClassifier algorithm for selecting important predictive features in forecasting the disease occurrence and artificial neural network (ANN) algorithm in predicting the occurrence of LSDV infection in unseen data ExtraTreesClassifier and ANN 97% Data from multiple sources, including the Global Animal Disease Information System of FAO (Food and Agriculture Organization), meteorological data, the Gridded Livestock of the World (GLW 3) database, the GLC-SHARE BetaRelease v1.0 dataset, and the Natural Earth database Study incorporates data obtained from inactive accounts within veterinary facilities across different countries. The dataset comprises a limited amount of information and is characterized by a small number of predictor variables utilized for analysis 4 González-Pérez et al. 2022 Automated categorization of mosquitoes based on their genus and gender by using five distinctive features extracted from wingbeat recordings logistic regression, (LR), gradient boosting (GB), random forests (RF), support vector machines (SVM) and a fully connected deep neural network (DNN) Genus classification: 94.2%, Sex classification of Aedes: 99.4%, sex classification of Culex: 100% Flight recordings of 4335 mosquito through a novel optical sensor Slight overfitting: more training samples for genus classification model 5 Kirkeby et al. 2021 3 methods for automatic classification of insect groups Fourier transformation of wingbeat frequency, Random Forest Classifier and 3-layer Neural network 80% 10,000 records of airborne insects discovered in oilseed rape (Brassica napus) fields, captured via an optical remote sensor only 4 species of pests considered 6 Pataki et al. 2021 Deep learning model to find tiger mosquitoes (Aedes albopictus) from 7686 citizen-made mosquito photos between 2014 and 2019 deep learning model, ResNet5026 96% Mosquito Alert’s curated database Data size used for testing is not optimum 7 Kittichai et al. 2021 One stage and two stage learning methods for classifying species and gender of different mosquito species deep learning model, YOLO 97–98.9% 10564 captured images of mosquitos small number of images for two species in the training set. Some species are not identified through the learning methods 8 Cannet et al. 2022 Automatized identification of species of tsetse flies using deep learning architecture and Wing Interference Patterns CNN 33–100% A collection of 1,766 images depicting 23 distinct species of Glossina (tsetse flies) A notably limited quantity of images belonging to a specific species is present within the test dataset for WIPs 9 Lei et al. 2019 3 convolutional layer model for identifying handwritten digits Dilated CNN and HDC models 60–100% MNIST data set 10 Antipov et al. 2016 CNN model for gender predication from face image CNN Ensemble model 96.8–97.3% CASIA Web Face and Labelled Faces in the Wild (LFW) Number of images in CASIA Web Face database is excessive with respect to the number of subjects 11 Chola et al. 2022 A classification model for determining the gender of Drosophila melanogaster by utilizing a combination of color, shape, and texture features. support vector machines (SVM), Naive Bayes (NB), and K-nearest neighbour (KNN) 90% Photographs of Drosophila specimens obtained from the National Drosophila Stock Centre, Department of Studies in Zoology, University of Mysore, India The dataset comprises a relatively small quantity of images, specifically 100 images categorized into two distinct classes 12 Ozdemir et al. 2022 21 base criteria (keys) for classification of insect order using deep learning models SSD MobileNET, YoloV4, and Faster R-CNN InceptionV3 67–81% 1500 insect images Image issues can deteriorate the performance of the model Table 1. (Continued) page 4 of 15Zoological Studies 64:24 (2025) © 2025 Academia Sinica, Taiwan S. No. Ref. No. Features Model Used Accuracy Database Limitations 13 Rabinovich et al. 2021 Experimental design using machine learning by taking temperature, exposure times, stage and sex of adult kissing bugs as features support vector machine, GBMs, Bayesian generalized linear models, linear models fitted with ordinary least squares 80% Dataset of 228 insects through a combination of 4 features Limited size of dataset 14 Motta et al. 2019 Autonomous classification of adult mosquitoes by extracting features from the mosquito images using CNN model CNN (LeNet, AlexNet, GoogleNet) 57.5–83.9% 4056 mosquito images extracted from ImageNet platform Limited number of images lead to risk of overfitting 15 Bjerge et al. 2022 Insect Classification and Tracking algorithm (ICT) for real-time classification and tracking of insect species using intelligent camera system and deep learning model deep learning model, YOLO 89% 2121 background images without insects and 5757 images with insects Precision of the tracking algorithm is highly dependent on the duration of visibility of insects on the camera 16 Zare et al. 2022 Boosting method to train classifier and feature extraction from microscopic images for detecting leishmaniasis Viola-Jones algorithm 83% A dataset encompassing 300 images extracted from 50 laboratory slides obtained from lesions under suspicion of leishmaniasis size of data set is quite low and accuracy depends on the resolution of images 17 Bellin et al. 2021 Classifier models for identifying two species of mosquitos using geometric morphometrics data and pairwise comparison for feature extraction support vector machine (SVM), random forest (RF), artificial neural network (ANN) and an ensemble model (EN) 73–81% 664 mosquito specimens of Maculipennis complex The proportion of two species in the test set is highly skewed (training set: 1:1 and test set: 24:222) 18 Markovic et al. 2021 Classifier models to predict the appearance of insects during a season on a daily basis using 21 parameters K-Nearest Neighbours, Support Vector Machines, Decision Tree, Random Forest, Multi-layer Perceptron classifier, Ada Boost, Gaussian Naive Bayes and Quadratic Discriminant, Analysis 75–86.3% Helicoverpa armigera insects from 17 locations in the northern part of Serbia during 2019 and 2020 Temperature and humidity are the only environmental parameters considered 19 Shen et al. 2018 Classifier model for detection of stored grain insects by applying an inception structure for convolution neural network R-CNN 88% 12508 images of six different species of insect Accuracy is highly dependent on the resolution of insect images 20 Wittek et al. 2022 Supervised machine learning predictive classifiers for pigeon behaviours using multivariate time series data for 10,424,241 frames as input Decision Trees, Random Forest 87% Eight naïve adult homing pigeons each receiving 10–20 sessions Absence of filters during the implementation of machine-learning based tracking software DeepLabCut that resulted in tracking glitches and instances of anatomically implausible movements observed in pigeons during the tracking process 21 Borba et al. 2021 Distinguishing taxonomic species by analyzing morphological, morphometric, and ecological data from capilliards J48, Random Tree, REPTree, LMT, Majority Voting 82–97% Samples procured from two helminth collections associated with institutions, containing a total of 28 distinct species and 8 different genera Utiilized dataset provides only a limited representation of the actual biological diversity observed within capillariids Table 1. (Continued) page 5 of 15Zoological Studies 64:24 (2025) © 2025 Academia Sinica, Taiwan S. No. Ref. No. Features Model Used Accuracy Database Limitations 22 Abdelaziz et al. 2022 Automated classification of vertebrate species from the 3D images of their remains using 8 extracted physical features Support Vector Machines (SVM), K-Nearest neighbours (KNN) and decision tree (DT) classifiers 83.4–93.7% 2052 3D images for three main classes Models show very high training accuracy implying that there might be issues of overfitting. K-Fold cross validation is not performed 23 Patel et al. 2020 Deep learning classification of Galápagos Snake Species using 6 external parameters extracted from images R-CNN 75% 247 images of snakes making up 9 species Dataset size is limited, not enough images to train the model properly and model classification is highly dependent on the resolution of images 24 Acevedo et al. 2009 Automated classification of calls of nine frogs and three bird species using four standard call variables or eleven variables that included three standard call variables and a coarse representation of call structure Support Vector Machines, Decision Trees and Discriminant Analysis 71.45–94.95% 10,061 isolated calls The model accuracy is dependent on the species type and call frequency 25 Xie et al. 2016 Acoustic classification model of frogs using 14 features extracted from frog call recordings linear discriminant analysis, K-nearest neighbour, support vector machines, random forest, and artificial neural network 94–99% Recordings of 24 frog with the duration ranging from eight to fifty-five seconds The accuracy diminishes with higher background noise 26 Petrescu et al. 2021 Fear classification model using 40 types of features from the physiological data Decision Trees, k-Nearest Neighbours, Support Vector Machine and artificial networks 91.7–93.5% Peripheral signals from DAEP dataset Imbalanced classes and single self-assessment of the emotional status for the video extract 27 Shia et al. 2021 Physical features extracted from images for unsupervised classification of malignant tumours in breast combination of locally weighted learning (LWL) and sequential minimal optimisation 84.70% 677 US images Smaller dataset, clinical limitation of the application and biases associated with the observers 28 Lapp et al. 2021 Automated call recognition method for frog calls and choruses using 9 parameters RIBBIT (repeat intervalbased bioacoustic identification tool) classifier 90% 70 Audio files Smaller dataset and accuracy dependent on heavily overlapping choruses, background noise and other species with similar vocalizations 29 Bisgin et al. 2018 Species identification of beetles based on 3 sets of image features SVM, ANN 80–85% set of 6900 images of 15 species of beetles Limiting number of specimen images per species, quality of images and difficult pairs due to high entomological similarities 30 Zhu et al. 2021 Neural network for identification of 3 specific types of promoters in DNA sequence of species including Homo sapiens, Mus musculus, Drosophila melanogaster and Arabidopsis thaliana Capsule neural network 80–98% promoter sequences for four different species from the EPDNew database Validity of model is compared against independent dataset that are subjected to continuous updating, the other tools selected for comparison only focusses on single species and most approaches do not identify all the promoters properly 31 Bisgin et al. 2022 Automated recognition through elytral pattern of foodcontaminating beetles CNN 90% 27 species of beetles collected from U.S. Department of Agriculture’s (USDA) Animal and Plant Health Inspection Service (APHIS) laboratory Accuracy dependent on better resolution and higher number of images for training set Table 1. (Continued) page 6 of 15Zoological Studies 64:24 (2025) © 2025 Academia Sinica, Taiwan S. No. Ref. No. Features Model Used Accuracy Database Limitations 32 Tannous et al. 2023 Automated identification of insect species using feature pyramid extracted from images with 3 different resolutions and scales CNN 93% 1826 images of 2 species of insects Small sized and morphologically similar insects are difficult to identify 33 Loti et al. 2021 Machine learning based automated identification of chili pest and disease in leaves using features extracted through 6 deep learning tools support vector machine (SVM), a random forest (RF), and artificial neural network (ANN) 49–92% 974 images of leaves Small number of testing samples of 2 classes, loss of certain features during feature extraction process and patterns of discoloration 34 Veiner et al. 2022 Analyzing transcriptomic patterns and identifying genes linked to the honeybee waggle dance by employing the top 20 gene features for characterization. Support Vector Machine (SVM), Random Forest (RF), Generalized Linear Model (GLMNET) 66.7–100% 15314 gene counts of whole honeybee genome across 32 bees Small size of training and test set 35 Gupta et al. 2023 Data augmentation with deep learning methodology for automatic identification of castor pest insects convolutional neural networks VGG16, VGG19, and ResNet50 71.2–82.18% Dataset of 372 images organized into six different insect pest classes Data unbalancing (disproportionate number of species in dataset for classification) 36 Aladhadh et al. 2022 Pest detection using a deep learning framework using cross stage partial network (CSP) for feature extraction from insect images CNN, Faster RCNN, YOLO-5 57.3–98% Ants class: 392 images, grasshopper class: 315 images, palm weevil class: 48 images, shield bug class: 392 images, and wasps’ class: 318 images Disproportionate number of insect classes in the training and test datasets 37 Liu et al. 2022 Automated recognition of tomato pests using deep learning model implementing Triplet Attention Module (TAM) for feature extraction Deep learning model YOLOv4-TAM 95% 2,893 images of induced plate pests collected from Shouguang tomato greenhouse Image quality affects the accuracy and detection of anchor boxes that correspond to the pest dataset 38 Alsanea et al. 2022 Autodetection model for red palm weevil using regionbased CNN to extract the features to enclose image with the bounding boxes convolutional neural network (R-CNN) 99% 6000 images generated from available 300 images using data augmentation techniques Non-availability of the dataset for the proposed model, dataset too small for the robust model creation 39 Dai et al. 2022 Autodetection of citrus psyllids using deep learning method by implementing Highresolution network (HRNet) for feature extraction from the images Cascade region-based convolution neural networks (R-CNN) 89% Dataset comprising of 500 high-definition sample images of plants sourced from the Citrus HLB Test Base at South China Agricultural University Small target detection range of citrus psyllid in the image 40 Spiesman et al. 2021 classification and identification of various bumble bee species using images by applying deep learning model Deep learning models ResNet, Wide ResNet, InceptionV3, and MnasNet 85.8–91.7% 120,000 images belonging to 42 species of bumble bees Significant fluctuations in error rates for species with limited sample sizes, primarily due to the extent of differences within the same species and their distinct characteristics from other species 41 Zhao et al. 2022 automatic recognition of mosquito species by implementing an identification model based on the Swin Transformer architecture Convolutional neural network (CNN) models 80–100% 9,900 mosquito images covering 7 genera and 17 species Lack of images of particular sex of some mosquito species lead to unbalanced dataset Table 1. (Continued) page 7 of 15Zoological Studies 64:24 (2025) © 2025 Academia Sinica, Taiwan Accuracy measurements reveal that deep learning variants, including artificial neural networks (ANN) and convolutional neural networks (CNN), demonstrate superior robustness compared to other classification models. Nevertheless, it is important to acknowledge that the accuracy of these models is influenced by certain limitations, such as the quantity and quality of the datasets employed, as well as class imbalance, which arises when multiple species classes are involved in the classification and identification studies. It is widely acknowledged that there has been minimal research conducted so far regarding gender classification using computational methods in T. castaneum. In this proposed study, we aim to utilize a CNN-based intelligent approach to detect and differentiate gender disparities from microscopic images. This endeavor is aimed at contributing to the advancement of intelligent systems within the domain of applied research. The following table offers a comprehensive overview of recent investigations conducted in the field of life sciences (Table 1), highlighting the various applications of machine learning models. Primarily, supervised learning models have been utilized to address tasks such as species classification, characteristics detection, and pattern recognition. To achieve these objectives, a variety of machine learning algorithms, including support vector machines (SVM), logistic regression (LG), random forests (RF), gradient boosting (GB), k-nearest neighbors (kNN), decision trees (DT), and deep learning (DL), have been implemented. The datasets used encompass both publicly available resources and collections generated by researchers through sample acquisition. The fundamental approach to developing classification models involves partitioning the dataset to create a training set for model training and a test set for the purpose of validating and assessing the model’s credibility. Accuracy measurements indicate that deep learning variants, such as artificial neural networks (ANN) and convolutional neural networks (CNN), exhibit superior robustness compared to other classification models. Researchers have employed various machine learning and deep learning classification models to study insects and pests. For example, Kirkeby et al. 2021, utilized three different methods to classify insect groups and achieved an impressive accuracy rate of 80%. Chola et al. (2022), employed classical machine learning methods to classify the gender of Drosophila melanogaster, achieving a maximum accuracy of 90%. Rabinovich et al. (2021), used machine learning models for experimental design, testing the thermal limits of kissing bugs and achieving an accuracy of 80%. Veiner et al. (2022), employed Support Vector Machine (SVM), Random Forest (RF), and Generalized Linear Model (GLMNET) to characterize and identify genes associated with honeybee waggle dance, achieving accuracy levels ranging from 67% to 100%. Perez et al. (2022), utilized a deep neural network to classify mosquitoes by genus and sex, achieving an accuracy exceeding 94%. Similar studies were conducted by Pataki et al. (2021); Kittichai et al. (2021); Motta et al. (2019); Bellin et al. (2021); and Zhao et al. (2022), who used deep learning models such as ResNet5016 and YOLO, as well as neural network models like ANN and CNN, to classify mosquito species based on insect images. These studies achieved accuracies ranging from 54% to 100%. Themozhi et al. (2019) and Aladhadh et al. (2022), applied CNN models to classify and detect crop pests using images, achieving accuracy levels higher than 95%. Liu et al. (2022), used a deep learning model to classify tomato pests from a collection of images, achieving an accuracy of 95%. Additionally, researchers have employed faster deep learning models like R-CNN for classifying various insects. Ozdemir et al. in 2022 used R-CNN to identify key indicators for insect classification, achieving an accuracy of over 80%. Shen et al. in 2018 and Alsanea et al. in 2022 applied the R-CNN classification model to images of stored grain insects and for the auto-detection of red palm weevil, respectively, resulting in accuracy levels of 88% and 99%. Bisgin et al. (2022) and Tannous et al. (2023), utilized CNN models for automated identification of food-contaminating beetles and insect species, achieving accuracy levels of 90% and 93%, respectively. Dai et al. (2022), employed cascade region-based convolutional neural networks (R-CNN) for the autodetection of citrus psyllids from images with an accuracy level of 89%. Aladhadh et al. in 2022 applied CNN and faster R-CNN models for the autodetection of pests from insect images with accuracy levels between 57% and 98%. In addition to species classification studies, machine learning and deep learning models have also been applied in various other biological studies. Lee et al. (2020), used support vector machines, random forest (RF), multi-layered perceptron, AdaBoost, gradient boosting (GB), and CatBoost models for malaria diagnosis and achieved accuracy levels between 56.9% and 85.6%. Safavi et al. (2022), employed ExtraTreesClassifier and ANN models for forecasting and predicting the occurrence of LSDV infection, achieving a highest classification accuracy of 97%. Zare et al. (2022), applied a boosting method to train classifiers and extract features from microscopic images for detecting leishmaniasis with an accuracy level of 83%. Petrescu et al. (2021), used decision trees, k-nearest neighbors, support vector machines, and artificial neural network models for fear classification from physiological data, with accuracy levels between page 8 of 15Zoological Studies 64:24 (2025) © 2025 Academia Sinica, Taiwan 91.7% and 93.5%. Shia et al. (2021), employed a combination of locally weighted learning and sequential minimal optimization for unsupervised classification of malignant breast tumors, achieving an accuracy level of 84.7%. Deep learning methods have been applied by Antipov et al. (2016) and Patel et al. (2020), who used CNN ensemble and R-CNN models for gender prediction from face images and classification of Galápagos Snake Species, with accuracies greater than 96% and 75%, respectively. Zhu et al. 2020, applied neural network models for the identification of three specific types of promoters in the DNA sequences of species including Homo sapiens, Mus musculus, Drosophila melanogaster, and Arabidopsis thaliana, with classification accuracy ranging from 80% to 98%. However, it is important to acknowledge that the accuracy of these models is influenced by certain limitations, such as the quantity and quality of the datasets used, as well as class imbalance that occurs when multiple species classes are involved in classification and identification studies. It is well established that the realm of gender classification through computational means in T. castaneum remains significantly underexplored. Given the minute sizes of these beetles, human classification becomes challenging, necessitating the fusion of image processing and machine learning techniques to facilitate species and gender identification, which could speed up the ongoing experiments on them. Here, in this planned work, a machine learning-driven intelligent methodology is developed by utilizing microscopic images (from ventral and dorsal viewpoints) to discern and categorize gender disparities. The ultimate objective is to foster the development of intelligent systems within the applied research domain. MATERIALS AND METHODS Insect rearing and image Acquisition The primary T. casteneum culture was procured from ROSS Lifescience Pvt. Ltd., Pune. It was thereafter cultured in wheat adding 5% yeast at the Zoology department of Savitribai Phule Pune University in an ideal environment at 33 ± °C and 70% relative humidity in a BOD incubator (Halliday et al. 2014). Images of T. castaneum at the pupal stage were acquired using digital stereo microscope (Nikon SMZ1270) and MIchrome 6 (6MP) color microscopic camera. The microscopic picture dataset comprises a total of 116 photographs of pupae of two distinct sexes, male and female, with each class including 58 images. These photos were taken from both the dorsal and ventral sides using constant angle and magnification (40X) with a dark background. Figure 1a–d shows representative photos of male and female T. castaneum pupa. In this study, machine learning model is train and tested with image size 128 × 128 × 3. Fig. 1. Specimen photographs of T. castaneum pupae under the microscope. a) and b) ventral and dorsal view of female pupa, c) and d) ventral and dorsal view of male pupa. page 9 of 15Zoological Studies 64:24 (2025)